WO2022062460A1 - 一种胎儿超声图像的成像质量控制的确定方法及装置 - Google Patents

一种胎儿超声图像的成像质量控制的确定方法及装置 Download PDF

Info

Publication number
WO2022062460A1
WO2022062460A1 PCT/CN2021/096823 CN2021096823W WO2022062460A1 WO 2022062460 A1 WO2022062460 A1 WO 2022062460A1 CN 2021096823 W CN2021096823 W CN 2021096823W WO 2022062460 A1 WO2022062460 A1 WO 2022062460A1
Authority
WO
WIPO (PCT)
Prior art keywords
fetal ultrasound
ultrasound image
target
fetal
feature
Prior art date
Application number
PCT/CN2021/096823
Other languages
English (en)
French (fr)
Inventor
谢红宁
汪南
冼建波
梁喆
吴杰林
刘树郁
Original Assignee
广州爱孕记信息科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 广州爱孕记信息科技有限公司 filed Critical 广州爱孕记信息科技有限公司
Priority to JP2023518459A priority Critical patent/JP2023542961A/ja
Priority to GB2305211.1A priority patent/GB2614643B/en
Priority to KR1020237009518A priority patent/KR20230052967A/ko
Publication of WO2022062460A1 publication Critical patent/WO2022062460A1/zh
Priority to US18/126,363 priority patent/US20230233177A1/en

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
    • A61B8/0866—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving foetal diagnosis; pre-natal or peri-natal diagnosis of the baby
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A61B8/523—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for generating planar views from image data in a user selectable plane not corresponding to the acquisition plane
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/54—Control of the diagnostic device
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/06—Measuring blood flow
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/48—Diagnostic techniques
    • A61B8/488—Diagnostic techniques involving Doppler signals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image

Definitions

  • the present invention relates to the technical field of image processing, and in particular, to a method and device for determining the imaging quality of fetal ultrasound images.
  • the methods for quality control of fetal ultrasound images are mainly as follows: Quantitative evaluation of fetal ultrasound images by medical staff with relevant experience to determine whether the key structures in the fetal ultrasound images exist and whether the geometric shapes of the key structures are standard, so as to realize the fetal ultrasound images. quality control.
  • Quantitative evaluation of fetal ultrasound images by medical staff with relevant experience to determine whether the key structures in the fetal ultrasound images exist and whether the geometric shapes of the key structures are standard, so as to realize the fetal ultrasound images. quality control.
  • quality control due to the subjectivity of medical staff and easy fatigue after working for a long time, this can easily lead to low accuracy of quality control of fetal ultrasound images.
  • the technical problem to be solved by the present invention is to provide a method and a device for determining the imaging quality control of fetal ultrasound images, which can improve the accuracy of quality control of fetal ultrasound images.
  • a first aspect of the present invention discloses a method for determining imaging quality control of fetal ultrasound images, the method comprising:
  • parameters of a fetal ultrasound image being used to determine the imaging quality of the fetal ultrasound image
  • the imaging score of the fetal ultrasound image is determined according to the parameters of the fetal ultrasound image, and the imaging quality of the fetal ultrasound image is determined according to the imaging score of the fetal ultrasound image.
  • the parameters for obtaining fetal ultrasound images include:
  • the parameter determination model includes a feature determination model and/or a section determination A model, wherein, when the parameter determination model is the feature determination model, the parameters of the fetal ultrasound image include the characteristic parameters of the fetal ultrasound image, and the characteristic parameters of the fetal ultrasound image include the part features of the fetal ultrasound image parameters and/or structural feature parameters; when the parameter determination model is the slice determination model, the parameters of the fetal ultrasound image include slice parameters of the fetal ultrasound image, and the slice parameters of the fetal ultrasound image include the fetal ultrasound image The slice score for the standard slice of the image; and/or,
  • the parameters of the fetal ultrasound image include characteristic parameters and/or slice parameters of the fetal ultrasound image
  • the characteristic parameters of the fetal ultrasound image include location characteristic parameters and/or structural characteristic parameters of the fetal ultrasound image
  • the slice parameters of the fetal ultrasound image include slice scores of standard slices of the fetal ultrasound image.
  • the fetal ultrasound image is composed of consecutive multiple frames of sub-fetal ultrasound images
  • determining the imaging score of the fetal ultrasound image according to the parameters of the fetal ultrasound image includes:
  • each of the target chapters includes several consecutive frames of the child fetal ultrasound images, and each of the target chapters includes all the child fetal ultrasound images are different from each other, and the total number of all the sub-fetal ultrasound images included in each of the target sections is equal to the total number of all the sub-fetal ultrasound images included in the fetal ultrasound image;
  • the score of the target chapter is calculated according to the parameters of the target feature of each frame of the fetal son ultrasound image included in each target chapter, and the target feature of each frame of the son fetal ultrasound image includes the part of the son fetal ultrasound image at least one of features, structural features, and standard sections;
  • the scores for all of the target sections are determined as imaging scores for the fetal ultrasound image.
  • the fetal ultrasound image corresponds to at least one target category
  • the target category includes a feature category or a slice category
  • each target category corresponds to a target feature The number is greater than or equal to 1;
  • the target feature when the target category is the feature category, the target feature includes a structural feature or a part feature; when the target category is the cut plane category, the target feature includes a standard cut plane;
  • Each of the target categories corresponds to at least one frame of the child fetal ultrasound images, and all the child fetal ultrasound images corresponding to each target category are different from each other and all the child fetal ultrasound images corresponding to all the target categories
  • the fetal ultrasound images make up the fetal ultrasound images.
  • performing a chapter division operation on the fetal ultrasound image to obtain at least one target chapter including:
  • the position where the child fetal ultrasound image of the starting frame corresponding to each target category is located is the position where the child fetal ultrasound image containing the target feature of the target category appears for the first time in the fetal ultrasound image, and each target
  • the position of the sub-fetal ultrasound image corresponding to the termination frame of the category is the position where the sub-fetal ultrasound image containing the target feature of the target category appears last in the fetal ultrasound image or the position in the fetal ultrasound image that contains the target category.
  • the starting frame of the target feature is the position where the sub-fetal ultrasound images start to appear consecutively for the first predetermined number of frames of the sub-fetal ultrasound images.
  • the score of the target chapter is calculated according to the parameters of the target feature of each frame of the fetal ultrasound image included in each of the target chapters, include:
  • the target feature of each frame of the child fetal ultrasound image is the part feature of the child fetal ultrasound image
  • the target feature of each frame of the child fetal ultrasound image is the structural feature of the child fetal ultrasound image
  • the structural feature according to the class probability of the structural feature of each frame of the child fetal ultrasound image included in each target section, the structural feature The position probability and the weight value of the structural feature are calculated, and the score of the target chapter is calculated;
  • the target feature of each frame of the child fetal ultrasound image is the standard slice of the child fetal ultrasound image
  • the method further includes:
  • the method further includes:
  • the score of each of the target chapters is updated to the target score of the target chapter, and the operation of determining that the scores of all the target chapters are the imaging scores of the fetal ultrasound image is triggered.
  • the determining of the imaging score of the fetal ultrasound image according to the parameters of the fetal ultrasound image includes:
  • the part feature parameter of the fetal ultrasound image includes the part feature score of the fetal ultrasound image, and the part feature score of the fetal ultrasound image is determined.
  • the value is the imaging score of the fetal ultrasound image; and/or,
  • the structural feature parameter of the fetal ultrasound image includes the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the structure The weight value of the feature;
  • the structural feature score of the structural feature is calculated, and the structural feature score is determined as the fetal ultrasound. the imaging score of the image; and/or,
  • the structural feature parameters of the fetal ultrasound image include the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the structural feature
  • the weight value of the fetal ultrasound image, the part feature parameter of the fetal ultrasound image includes the class probability of the part feature of the fetal ultrasound image
  • the class probability of the part feature of the fetal ultrasound image the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature, the structural feature score of the structural feature is calculated, and determined.
  • the structural feature score is used as the imaging score of the fetal ultrasound image; and/or, the fetal ultrasound is determined according to the category probability of the part feature of the fetal ultrasound image and the category probability of the structural feature of the fetal ultrasound image.
  • the standard slice of the image, and according to the parameters of the structural features in the standard slice of the fetal ultrasound image, the slice score of the standard slice of the fetal ultrasound image is calculated as the imaging score of the fetal ultrasound image, the fetal ultrasound image Structural feature parameters of an ultrasound image include parameters of structural features within a standard slice of the fetal ultrasound image.
  • the method before the determination of the imaging quality of the fetal ultrasound image according to the imaging score of the fetal ultrasound image, the method further includes:
  • the detection result corresponding to the fetal ultrasound image is determined, and the detection result corresponding to the fetal ultrasound image is used to determine the imaging quality of the fetal ultrasound image, and the detection result corresponding to the fetal ultrasound image includes a feature detection result, a biological path at least one of line detection results and Doppler blood flow spectrum detection results, the feature detection results include at least one of part feature detection results, structural feature detection results, and standard section detection results;
  • determining the imaging quality of the fetal ultrasound image according to the imaging score of the fetal ultrasound image includes:
  • the imaging quality of the fetal ultrasound image is determined according to the imaging score of the fetal ultrasound image and the characteristic result corresponding to the fetal ultrasound image.
  • a second aspect of the present invention discloses a device for determining imaging quality control of fetal ultrasound images, the device comprising:
  • an acquisition module for acquiring parameters of a fetal ultrasound image, the parameters of the fetal ultrasound image being used to determine the imaging quality of the fetal ultrasound image;
  • a first determining module configured to determine an imaging score of the fetal ultrasound image according to parameters of the fetal ultrasound image
  • the second determination module is configured to determine the imaging quality of the fetal ultrasound image according to the imaging score of the fetal ultrasound image.
  • the manner in which the acquisition module acquires the parameters of the fetal ultrasound image is specifically:
  • the parameter determination model includes a feature determination model and/or a section determination A model, wherein, when the parameter determination model is the feature determination model, the parameters of the fetal ultrasound image include the characteristic parameters of the fetal ultrasound image, and the characteristic parameters of the fetal ultrasound image include the part features of the fetal ultrasound image parameters and/or structural feature parameters; when the parameter determination model is the slice determination model, the parameters of the fetal ultrasound image include slice parameters of the fetal ultrasound image, and the slice parameters of the fetal ultrasound image include the fetal ultrasound image The slice score for the standard slice of the image; and/or,
  • the parameters of the fetal ultrasound image include characteristic parameters and/or slice parameters of the fetal ultrasound image
  • the characteristic parameters of the fetal ultrasound image include location characteristic parameters and/or structural characteristic parameters of the fetal ultrasound image
  • the slice parameters of the fetal ultrasound image include slice scores of standard slices of the fetal ultrasound image.
  • the fetal ultrasound image consists of multiple frames of consecutive sub-fetal ultrasound images
  • the first determining module includes:
  • a division submodule configured to perform a chapter division operation on the fetal ultrasound image to obtain at least one target chapter, each of the target chapters includes several consecutive frames of the child fetal ultrasound images, and each of the target chapters includes all the child fetal ultrasound images are different from each other, and the total number of all the child fetal ultrasound images included in each of the target sections is equal to the total number of all the child fetal ultrasound images included in the fetal ultrasound image;
  • the calculation submodule is used to calculate the score of each target section according to the parameters of the target feature of each frame of the fetal ultrasound image included in each of the target chapters, and the target of each frame of the fetal ultrasound image
  • the features include at least one of site features, structural features and standard slices of the fetal ultrasound image
  • the fetal ultrasound image corresponds to at least one target category
  • the target category includes a feature category or a slice category
  • each target category corresponds to a target feature The number is greater than or equal to 1;
  • the target feature when the target category is the feature category, the target feature includes a structural feature or a part feature; when the target category is the cut plane category, the target feature includes a standard cut plane;
  • Each of the target categories corresponds to at least one frame of the child fetal ultrasound images, and all the child fetal ultrasound images corresponding to each target category are different from each other and all the child fetal ultrasound images corresponding to all the target categories
  • the fetal ultrasound images make up the fetal ultrasound images.
  • the division submodule performs a chapter division operation on the fetal ultrasound image, and the method for obtaining at least one target chapter is specifically:
  • the position where the child fetal ultrasound image of the starting frame corresponding to each target category is located is the position where the child fetal ultrasound image containing the target feature of the target category appears for the first time in the fetal ultrasound image, and each target
  • the position of the sub-fetal ultrasound image corresponding to the termination frame of the category is the position where the sub-fetal ultrasound image containing the target feature of the target category appears last in the fetal ultrasound image or the position in the fetal ultrasound image that contains the target category.
  • the starting frame of the target feature is the position where the sub-fetal ultrasound images start to appear consecutively for the first predetermined number of frames of the sub-fetal ultrasound images.
  • the calculation submodule calculates the target section of the target section according to the parameters of the target feature of each frame of the fetal ultrasound image included in each target section.
  • the way of scoring is as follows:
  • the target feature of each frame of the child fetal ultrasound image is the part feature of the child fetal ultrasound image
  • the target feature of each frame of the child fetal ultrasound image is the structural feature of the child fetal ultrasound image
  • the structural feature according to the class probability of the structural feature of each frame of the child fetal ultrasound image included in each target section, the structural feature The position probability and the weight value of the structural feature are calculated, and the score of the target chapter is calculated;
  • the target feature of each frame of the child fetal ultrasound image is the standard slice of the child fetal ultrasound image
  • the determining submodule is further configured to, after the dividing submodule performs a chapter division operation on the fetal ultrasound image to obtain at least one target chapter, determining the total number of frames of ultrasound images of all the son-fetals included in each of the target sections;
  • the device also includes:
  • the calculation module is used for calculating the score of each target section according to the parameters of the target feature of each frame of the fetal ultrasound image included in each target section by the first determining module.
  • the score of the chapter is divided by the total number of frames of all the fetal ultrasound images included in the target chapter to obtain the target score of the target chapter;
  • an update module for updating the score of each of the target chapters to the target score of the target chapter, and triggering the second determination module to perform the determination that the scores of all the target chapters are the fetus Manipulation of imaging scores of ultrasound images.
  • the manner in which the first determining module determines the imaging score of the fetal ultrasound image according to the parameters of the fetal ultrasound image is specifically:
  • the part feature parameter of the fetal ultrasound image includes the part feature score of the fetal ultrasound image, and the part feature score of the fetal ultrasound image is determined.
  • the value is the imaging score of the fetal ultrasound image; and/or,
  • the structural feature parameter of the fetal ultrasound image includes the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the structure The weight value of the feature;
  • the structural feature score of the structural feature is calculated, and the structural feature score is determined as the fetal ultrasound. the imaging score of the image; and/or,
  • the structural feature parameters of the fetal ultrasound image include the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the structural feature
  • the weight value of the fetal ultrasound image, the part feature parameter of the fetal ultrasound image includes the class probability of the part feature of the fetal ultrasound image
  • the class probability of the part feature of the fetal ultrasound image the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature, the structural feature score of the structural feature is calculated, and determined.
  • the structural feature score is used as the imaging score of the fetal ultrasound image; and/or, the fetal ultrasound is determined according to the category probability of the part feature of the fetal ultrasound image and the category probability of the structural feature of the fetal ultrasound image.
  • the standard slice of the image, and according to the parameters of the structural features in the standard slice of the fetal ultrasound image, the slice score of the standard slice of the fetal ultrasound image is calculated as the imaging score of the fetal ultrasound image, the fetal ultrasound image Structural feature parameters of an ultrasound image include parameters of structural features within a standard slice of the fetal ultrasound image.
  • the device further includes:
  • a third determination module configured to determine a detection result corresponding to the fetal ultrasound image before the second determination module determines the imaging quality of the fetal ultrasound image according to the imaging score of the fetal ultrasound image, and the fetal ultrasound image
  • the detection result corresponding to the image is used to determine the imaging quality of the fetal ultrasound image
  • the detection result corresponding to the fetal ultrasound image includes at least one of a feature detection result, a biological diameter detection result, and a Doppler blood flow spectrum detection result.
  • the feature detection result includes at least one of a part feature detection result, a structural feature detection result, and a standard section detection result;
  • the manner in which the second determining module determines the imaging quality of the fetal ultrasound image according to the imaging score of the fetal ultrasound image is specifically:
  • the imaging quality of the fetal ultrasound image is determined according to the imaging score of the fetal ultrasound image and the characteristic result corresponding to the fetal ultrasound image.
  • a third aspect of the present invention discloses another device for determining imaging quality control of fetal ultrasound images, the device comprising:
  • a processor coupled to the memory
  • the processor invokes the executable program code stored in the memory to execute the method for determining imaging quality control of a fetal ultrasound image disclosed in the first aspect of the present invention.
  • a fourth aspect of the present invention discloses a computer storage medium, the computer storage medium stores computer instructions, and when the computer instructions are invoked, is used to perform the determination of the imaging quality control of the fetal ultrasound image disclosed in the first aspect of the present invention method.
  • a method and a device for determining the imaging quality of a fetal ultrasound image are provided.
  • the method acquires parameters of the fetal ultrasound image, and the parameters of the fetal ultrasound image are used to determine the imaging quality of the fetal ultrasound image;
  • the imaging score of the fetal ultrasound image is determined according to the parameters of the fetal ultrasound image, and the imaging quality of the fetal ultrasound image is determined according to the imaging score of the fetal ultrasound image.
  • the imaging quality of the fetal ultrasound image can be quickly and accurately determined, thereby achieving accurate and accurate imaging quality of the fetal ultrasound image.
  • FIG. 1 is a schematic flowchart of a method for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of another method for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of a device for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention
  • FIG. 4 is a schematic structural diagram of another device for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of another device for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention.
  • the invention discloses a method and a device for determining the imaging quality of a fetal ultrasound image, which can automatically determine the imaging quality of the fetal ultrasound image according to the determined imaging score of the fetal ultrasound image, and can quickly and accurately determine the fetal ultrasound image Therefore, the imaging quality of fetal ultrasound images can be accurately and quickly controlled, and high-quality fetal ultrasound images can be obtained, which is conducive to obtaining accurate fetal growth and development.
  • determining the imaging quality of fetal ultrasound images It is also possible to know the standardization of the staff in the process of detecting fetal ultrasound images and whether the items required to be detected by the fetus have been completely detected. Each of them will be described in detail below.
  • FIG. 1 is a schematic flowchart of a method for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention.
  • the method for determining imaging quality control of fetal ultrasound images described in FIG. 1 can be applied to an imaging quality determination server (service device), wherein the imaging quality determination server may include a local imaging quality determination server or a cloud imaging quality determination server , the embodiments of the present invention are not limited.
  • the method for determining the imaging quality control of the fetal ultrasound image may include the following operations:
  • the fetal ultrasound image is any fetal ultrasound image whose imaging quality needs to be determined.
  • the fetal ultrasound image may be a single frame picture or a dynamic image.
  • the parameters of the fetal ultrasound image may include the parameters of the single-frame fetal ultrasound image, and further, may also include the parameters corresponding to the fetal ultrasound video corresponding to the fetal ultrasound image. Examples are not limited.
  • the imaging quality of the fetal ultrasound image may represent the imaging quality of the single-frame fetal ultrasound image, or may represent the imaging quality corresponding to the fetal ultrasound video where the fetal ultrasound image is located, which is not limited in this embodiment of the present invention.
  • the parameters for obtaining the fetal ultrasound image may include:
  • the fetal ultrasound image is input into the determined parameter determination model for analysis, and the analysis result output by the parameter determination model is obtained as a parameter of the fetal ultrasound image.
  • the fetal ultrasound image when the fetal ultrasound image is a single-frame picture, the fetal ultrasound image may be continuously input into the parameter determination model for analysis according to a predetermined frame rate (for example: 30 frames/second), And the analysis results output by the parameter determination model in turn are obtained as parameters of each frame of fetal ultrasound images.
  • a predetermined frame rate for example: 30 frames/second
  • the analysis results output by the parameter determination model in turn are obtained as parameters of each frame of fetal ultrasound images.
  • the parameter determination model can also perform a frame segmentation operation on the fetal ultrasound image to obtain multiple frames of child fetal ultrasound images, and analyze the multiple frames of child fetal ultrasound images respectively to obtain multiple frames. Parameters of frame sub-fetal ultrasound images. This increases the possibility of acquiring parameters of the fetal ultrasound image by performing processing operations on the static or dynamic fetal ultrasound image.
  • the fetal ultrasound image has a unique corresponding frame sequence number.
  • the fetal ultrasound image has a unique corresponding frame sequence number.
  • the parameter determination model includes a feature determination model and/or a slice determination model, wherein the characteristic determination model is a model capable of determining characteristic parameters of a fetal ultrasound image, and the slice determination model is capable of determining a feature of a fetal ultrasound image Parametric model.
  • the parameter determination model may include at least one of parameters capable of acquiring fetal ultrasound images, such as a target detection model, an instance segmentation model, and a semantic segmentation model, which are not limited in this embodiment of the present invention.
  • the parameters of the fetal ultrasound image include the characteristic parameters of the fetal ultrasound image, wherein the characteristic parameters of the fetal ultrasound image include the part characteristic parameters of the fetal ultrasound image and/or structural feature parameters.
  • the part feature parameter of the fetal ultrasound image includes the category of the part feature of the fetal ultrasound image and the category probability (also called confidence) of the part feature of the fetal ultrasound image. Further, the part feature parameter of the fetal ultrasound image may further include graphic coordinates of the part feature of the fetal ultrasound image.
  • the structural feature parameter of the fetal ultrasound image includes the category of the structural feature of the fetal ultrasound image and the category probability (also called confidence) of the structural feature of the fetal ultrasound image.
  • the structural feature parameter of the fetal ultrasound image further includes at least one of graphic coordinates, size, and position probability of the structural feature of the fetal ultrasound image, which is not limited in this embodiment of the present invention.
  • the feature information of the fetal ultrasound image also includes polygonal contour information of the structural features of the fetal ultrasound image, such as polygonal contour coordinates, so that the more content the structural feature parameters of the fetal ultrasound image include, the more conducive to improving fetal ultrasound. The accuracy and efficiency of determining the imaging quality of an image.
  • the graphic coordinates of the above-mentioned part features or structural features may include polygon coordinates or elliptical coordinates, wherein the polygon coordinates may include odd polygon coordinates or even polygon coordinates, for example: pentagonal coordinates, rectangular coordinates, polygon coordinates Selecting the shape that depends on the part feature or the structural feature can improve the accuracy of the coordinate acquisition of the part feature and the structural feature.
  • the parameters of the fetal ultrasound image include slice parameters of the fetal ultrasound image
  • the slice parameters of the fetal ultrasound image include slice scores of standard slices of the fetal ultrasound image
  • the slice parameter of the fetal ultrasound image further includes a slice type of the standard slice of the fetal ultrasound image.
  • the embodiment of the present invention can also analyze the fetal ultrasound image input parameter determination model, can quickly realize the automatic acquisition of the parameters of the fetal ultrasound image, without manual participation, can improve the accuracy and reliability of the parameter acquisition of the fetal ultrasound image, thereby Improve the accuracy and efficiency of determining the imaging score of fetal ultrasound images.
  • the parameters for obtaining the fetal ultrasound image may include:
  • the determined parameters for the fetal ultrasound image sent by the terminal device and/or input by an authorized person are received as parameters of the fetal ultrasound image.
  • the parameters of the fetal ultrasound image include characteristic parameters and/or slice parameters of the fetal ultrasound image
  • the characteristic parameters of the fetal ultrasound image include the position characteristic parameters and/or structural characteristic parameters of the fetal ultrasound image
  • the fetal ultrasound image The slice parameters of the ultrasound image include slice scores of standard slices of the fetal ultrasound image.
  • the terminal device establishes communication with the imaging quality determination server (service device) in advance.
  • the embodiment of the present invention can also acquire parameters of the fetal ultrasound image by means of transmission by the terminal device and/or input by authorized personnel, and can enrich the acquisition method of the parameters of the fetal ultrasound image.
  • the parameters of the fetal ultrasound image can be obtained through all the above methods, which can enrich the way of obtaining the parameters of the fetal ultrasound image and improve the possibility of obtaining the parameters of the fetal ultrasound image;
  • the characteristic parameters and slice parameters of the fetal ultrasound image are used to obtain the imaging score of the fetal ultrasound image, which can improve the accuracy of obtaining the imaging score of the fetal ultrasound image.
  • the above-mentioned fetal ultrasound image is composed of consecutive multiple frames of sub-fetal ultrasound images, and, as an optional embodiment, determining the imaging score of the fetal ultrasound image according to the parameters of the fetal ultrasound image may include:
  • the score of the target section is calculated, and the scores of all target sections are determined as the imaging scores of the fetal ultrasound image.
  • the target feature of each frame of fetal fetal ultrasound image includes at least one of a part feature, a structural feature, and a standard slice of the fetal fetal ultrasound image.
  • the part features of the fetal ultrasound image include but are not limited to abdominal features, cranial features, lung features, arm features, toe features, and heart features.
  • the structural features of the sonographic ultrasound image include, but are not limited to, the structural features of gastric vesicles, the structural features of the umbilical vein, the structural features of the transparent compartment, the structural features of the thalamus, the structural features of the lateral ventricle of the liver, the structural features of the descending aorta, Rib structure features, inferior vena cava structure features.
  • the standard slices of the sonographic ultrasound image include, but are not limited to, the head-rump length measurement slice, the biparietal diameter measurement slice, the NT measurement slice, the face midline slice, the frontomaxillary angle measurement slice, the humerus length measurement slice, Femoral length measurement section, double upper limb section, double lower limb section, fetal heart rate measurement section, tricuspid valve spectral measurement section, venous catheter spectral measurement section, gastric bubble section, bladder section, double umbilical artery section, gender display section, nasal bone measurement Section, bowel diameter measurement section, ulna and radius long-diameter section, middle cerebral artery section, gallbladder-umbilical vein section, ductus arteriosus section, pulmonary vein entering left atrium section, abdominal circumference section, anal section, humerus long-diameter section, cervical measurement section, Femoral long diameter section, coronary sinus section, conus medullary positioning section, spinal coronal section, spine section, spinal
  • the target feature of each frame of the fetal ultrasound image includes a standard slice in at least one orientation, where the orientation includes a coronal orientation, a sagittal orientation, and a horizontal orientation.
  • abdominal features include horizontal abdominal features, sagittal abdominal features, and coronal abdominal features
  • abdominal girth sections include horizontal abdominal girth sections, sagittal abdominal girth sections, and coronal abdominal girth sections
  • gastric vesicle structural features include horizontal gastric vesicle structural features, sagittal abdominal girth sections Structural characteristics of gastric vesicles and coronal vesicles.
  • each target chapter includes several consecutive frames of sub-fetal ultrasound images, and all sub-fetal ultrasound images included in each target chapter are different from each other, and the total number of all sub-fetal ultrasound images included in each target chapter Equal to the total number of fetal ultrasound images included in all child fetal ultrasound images.
  • the chapter division of the fetal ultrasound image may be divided in real time, that is, while successively multiple frames of the fetal ultrasound image are input into the above parameter determination model for analysis, and the analysis of the sequential output of the parameter determination model is obtained.
  • all the child fetal ultrasound images are sectioned while being a parameter of each frame of the child fetal ultrasound images.
  • Performing chapter division on the fetal ultrasound images may also be to perform chapter division on all the child fetal ultrasound images after the parameters of all the child fetal ultrasound images are acquired, which is not limited in the embodiment of the present invention.
  • the fetal ultrasound image corresponds to at least one target category
  • the target category includes a feature category or a slice category
  • the number of target features corresponding to each target category is greater than or equal to 1.
  • the target features include structural features or part features
  • the target category when the target category is a slice category, the target features include standard slices; each target category corresponds to at least one frame of sub-fetal ultrasound images, and each All child fetal ultrasound images corresponding to the target categories are different from each other, and all child fetal ultrasound images corresponding to all target categories constitute a fetal ultrasound image.
  • the embodiment of the present invention can also automatically divide the fetal ultrasound image into chapters of different categories, and use the calculated score of each chapter as the imaging score of the fetal ultrasound image, which can improve the imaging score of the fetal ultrasound image
  • the accuracy and efficiency of the acquisition of fetal ultrasound images can be improved, so as to improve the accuracy and reliability of the imaging quality of fetal ultrasound images, and to achieve accurate and rapid control of the imaging quality of fetal ultrasound images, which is conducive to the acquisition of high-quality fetal ultrasound images. It is beneficial to improve the accuracy and reliability of the determination of fetal growth and development.
  • a chapter division operation is performed on the fetal ultrasound image to obtain at least one target chapter, which may include:
  • the starting frame sub-fetal ultrasound image corresponding to each target category, the ending frame sub-fetal ultrasound image corresponding to the target category, and the determined position of the starting frame sub-fetal ultrasound image corresponding to the target category correspond to the target category
  • the termination frame where the sub-fetal ultrasound images are located between all sub-fetal ultrasound images is determined as the corresponding target chapter for each target category.
  • the position of the initial frame sub-fetal ultrasound image corresponding to each target category is the position where the sub-fetal ultrasound image containing the target features of the target category appears for the first time in the fetal ultrasound image, and each target category corresponds to
  • the ending frame where the child fetal ultrasound image is located is the last occurrence of the child fetal ultrasound image containing the target feature of the target category in the fetal ultrasound image or from the start of the target feature containing the target category in the fetal ultrasound image
  • Frame sub-fetal ultrasound images begin to appear continuously at the position where the preset number of frames of sub-fetal ultrasound images are located, which is beneficial to improve the accuracy of determining the position of the fetal ultrasound image of the termination frame corresponding to each target category, thereby improving the target of each target category.
  • the position of the sub-fetal ultrasound image of the termination frame corresponding to each target category is the preset number of frames that appear continuously in the fetal ultrasound image from the initial frame sub-fetal ultrasound image that contains the target feature of the target category.
  • the case where the fetal ultrasound image is located is applicable to the case where the fetal ultrasound image is divided into chapters in real time.
  • the target category is the structural feature category of gastric vesicles
  • the fetal ultrasound image consists of 100 sub-fetal ultrasound images.
  • the gastric vesicle structural feature appears for the first time at the position of the sub-fetal ultrasound image in the 5th frame, and in the 50th frame of the sub-fetal ultrasound image. If the position appears for the last time, the position of the sub-fetal ultrasound image of the starting frame corresponding to the gastric bubble structure feature category is the position of the fifth frame of the sub-fetal ultrasound image, and the position of the end frame of the sub-fetal ultrasound image is the position of the 50th sub-fetal ultrasound image.
  • the position of the sub-fetal ultrasound image of the frame, or the preset number of frames corresponding to the structural feature category of the gastric bubble is 30 frames, then the position of the 34th frame of the sub-fetal ultrasound image will appear continuously from the position of the fifth frame of the sub-fetal ultrasound image. is the position of the fetal ultrasound image of the termination frame corresponding to the structural feature category of the gastric vesicle.
  • the target category is the standard abdominal circumference view
  • the fetal ultrasound image is composed of 100 sub-fetal ultrasound images
  • the abdominal circumference standard view category appears for the first time at the position of the child fetal ultrasound image in the 5th frame, and in the 50th sub-fetal ultrasound image. If the position of the image appears for the last time, the position of the sub-fetal ultrasound image of the start frame corresponding to the abdominal standard slice category is the position of the fifth frame of the sub-fetal ultrasound image, and the position of the end frame of the fetal ultrasound image is the position of the 50th frame.
  • the position of the fetal ultrasound image of the frame, or the preset number of frames corresponding to the standard slice category of the abdominal circumference is 30 frames, then the position where the 34th frame of the child fetal ultrasound image appears continuously from the position of the fifth frame of the child fetal ultrasound image is: The position of the sub-fetal ultrasound image in the termination frame corresponding to the standard slice category of abdominal circumference.
  • all the fetal ultrasound images included in the target section corresponding to each target category include at least fetal ultrasound images containing the target features of the target category, and the target section corresponding to each target category includes the target category of the target.
  • the number of features is greater than or equal to 1.
  • all fetal fetal ultrasound images included in the target section corresponding to each target category also include fetal fetal ultrasound images that do not contain the target features of the target category.
  • the chapter corresponding to the structural feature category of gastric vesicles includes 50 frames of fetal ultrasound images, of which 45 sub-fetal ultrasound images contain the structural feature category of gastric vesicles, and the structural features included in the remaining 5 sub-fetal ultrasound images are finger structural features .
  • the embodiment of the present invention can also automatically determine the position of each type of part feature or structural feature or the position of the fetal ultrasound image of the start frame and the position of the end frame of the fetal ultrasound image of the standard slice, so that each type of part feature or structure can be realized.
  • the automatic determination of the chapters corresponding to the features or standard slices is beneficial to improve the determination efficiency and accuracy of each chapter, thereby improving the calculation efficiency and accuracy of the score of each chapter.
  • the score of the target chapter is calculated, including:
  • each frame of child fetal ultrasound image is the part feature of the child fetal ultrasound image
  • the target feature of each sub-fetal ultrasound image is the structural feature of the sub-fetal ultrasound image
  • the class probability of the structural feature of each frame of the sub-fetal ultrasound image included in each target chapter the position probability of the structural feature, and the structure
  • the weight value of the feature calculate the score of the target chapter
  • each frame of sub-fetal ultrasound image is the standard section of the sub-fetal ultrasound image
  • the calculation formula for the score of the target chapter corresponding to each feature category is:
  • H i P i ⁇ Q i ⁇ O i ;
  • S 1 is the score of the target chapter corresponding to each feature category
  • H i is the structural feature score of the i-th structural feature corresponding to the feature category in the target chapter
  • M is the target chapter in the target chapter.
  • Pi is the confidence level of the ith structural feature corresponding to the feature category in the target chapter
  • Q i is the ith structural feature corresponding to the feature category in the target chapter.
  • the position probability of , O i is the weight value of the i-th structural feature corresponding to the feature category in the target chapter.
  • the parameters of the structural feature of each frame of sub-fetal ultrasound images included in each target chapter also include the probability of the location where the structural feature is located.
  • the i-th structure corresponding to the feature category in the target chapter The formula for calculating the structural feature score of the feature is:
  • H i P i ⁇ Q i ⁇ O i ⁇ C i ;
  • C i is the probability of the position of the i-th structural feature corresponding to the feature category in the target chapter.
  • the calculation formula of the target chapter corresponding to each slice category is:
  • S 2 is the score of the target chapter corresponding to each aspect category
  • M is the total number of standard aspects corresponding to the aspect category in the target chapter
  • K j is the target chapter corresponding to the aspect category.
  • the calculation formula of the target chapter corresponding to each part category is:
  • S 3 is the score of the target chapter corresponding to each part category
  • M is the total number of part features corresponding to the part category in the target chapter
  • W 1 is the first part corresponding to the part category in the target chapter.
  • the score of each target chapter is The average value of the scores corresponding to at least one of the three orientations of the target feature corresponding to the target category may be included.
  • the structural features included in chapter A are the structural features of gastric alveoli corresponding to the structural feature category of gastric vesicles, then the structures corresponding to the horizontal, sagittal, and coronal orientations of each structural feature of gastric alveoli in chapter A are calculated.
  • the feature score is calculated, and the mean value of the structural feature scores corresponding to the three orientations of all gastric vesicle structural features is calculated as the score of Section A.
  • the average value of the scores of the multiple orientations of the part feature and the standard section please refer to the same average value of the multiple orientations of the structural feature, which will not be repeated here.
  • the calculation accuracy of the score of the chapter can be further improved, thereby further improving the determination of the imaging quality of the fetal ultrasound image. Accuracy, which in turn facilitates the acquisition of high-quality fetal ultrasound images.
  • the embodiment of the present invention can also calculate the structural feature score corresponding to each type of structural feature or the section score corresponding to each type of section or the part feature score corresponding to each type of part feature. It can also enrich the way of determining the score of the chapter, and improve the accuracy and reliability of the determination of the score of the chapter;
  • the chapter scores obtained by the slice score jointly determine the imaging quality of the fetal ultrasound image, which can further improve the accuracy and reliability of the determination of the imaging quality of the fetal ultrasound image, thereby further facilitating the acquisition of higher-quality fetal ultrasound images.
  • each standard slice since each standard slice includes at least one structural feature, the slice score of each standard slice can be directly sent by the above-mentioned terminal device, input by authorized personnel, and output by the slice determination model. In addition to the acquisition method, it can also be calculated based on the structural feature score of each structural feature contained in the standard section, that is, based on the structural feature score of each structural feature contained in each standard section of each type of standard section. The section score of each type of standard section, and after calculating the score of the chapter corresponding to the standard section of this category based on the section score of each category of standard section, obtain the calculated section score of each type of standard section. The average of the chapter's score and the directly obtained section score of the standard section of the category is taken as the score of the section.
  • chapter B corresponds to the target category of abdominal circumference slices.
  • Chapter B includes 5 abdominal circumference slices.
  • the section score of section B was calculated with a score of 45.1; the structural features of the abdominal girth section included gastric vesicle structural features, umbilical vein structural features, and liver structural features, while each abdominal girth section in Section B included gastric vesicles.
  • the structural feature score corresponding to the structural feature is 14.5, the structural feature score corresponding to the umbilical vein structural feature is 16, and the structural feature score corresponding to the liver structural feature is 15.5, then the score of Chapter B is calculated from the structural feature score corresponding to the structural feature.
  • the value is 46, and the average of 46 and 45.1, 45.55, is taken as the final score for Chapter B.
  • the accuracy of determining the imaging score of the fetal ultrasound image can be further improved, thereby further improving the fetal ultrasound image.
  • the accuracy of the determination of the imaging quality of an image is obtained by obtaining the mean value of the chapter scores obtained in different ways as the score of the chapter, that is, the imaging score of the fetal ultrasound image.
  • the part feature includes a plurality of standard sections
  • the standard section includes a plurality of structural features
  • the score is calculated to obtain the average of the score of the chapter and the score of the chapter corresponding to the part feature as the final score of the chapter.
  • the method further includes:
  • the method further includes:
  • the score of each target chapter is updated to the target score of the target chapter, and the execution of step 103 is triggered.
  • the number of fetal ultrasound images included in the chapter corresponding to the structural feature category of gastric vesicles is 100 frames, and the score of the chapter corresponding to the structural feature category of gastric vesicles is 180 points, then 180 is divided by 100 to obtain 1.8 as For the score of this chapter, the score of the chapter corresponding to the structural feature category of gastric vesicles is updated to 1.8.
  • this optional embodiment further obtains the new score of the chapter based on the score of the chapter and the total number of frames of the chapter, and changes the imaging score of the fetal ultrasound image into The new score can further improve the accuracy of determining the imaging score of the fetal ultrasound image, thereby helping to improve the accuracy of determining the imaging quality of the fetal ultrasound image.
  • determining the imaging score of the fetal ultrasound image according to the parameters of the fetal ultrasound image including:
  • the site feature parameters of the fetal ultrasound image include the site feature score of the fetal ultrasound image, and it is determined that the site feature score of the fetal ultrasound image is the imaging of the fetal ultrasound image points; and/or,
  • the structural feature parameter of the fetal ultrasound image includes the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature;
  • the structural feature score of the structural feature is calculated, and the structural feature score is determined as the imaging score of the fetal ultrasound image. value;
  • the structural feature parameter of the fetal ultrasound image includes the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature.
  • the part feature parameter of the fetal ultrasound image includes the class probability of the part feature of the fetal ultrasound image;
  • the class probability of the part feature of the fetal ultrasound image the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature, the structural feature score of the structural feature is calculated, and the structure is determined.
  • the feature score is used as the imaging score of the fetal ultrasound image; and/or, according to the category probability of the part feature of the fetal ultrasound image and the category probability of the structural feature of the fetal ultrasound image, the standard section of the fetal ultrasound image is determined, and according to the fetal ultrasound image.
  • the parameters of the structural features in the standard section of the ultrasound image, and the section score of the standard section of the fetal ultrasound image is calculated as the imaging score of the fetal ultrasound image.
  • the structural feature parameters of the fetal ultrasound image include the standard section of the fetal ultrasound image. parameters of the structural features.
  • the embodiment of the present invention can also realize the calculation of the score of the fetal ultrasound image by separately calculating the part feature score, the structural feature score and the standard slice score of the fetal ultrasound image, which can not only enrich the score of the fetal ultrasound image.
  • the determination method improves the determination accuracy of the imaging quality of the fetal ultrasound image, thereby further realizing precise and rapid control of the imaging quality of the fetal ultrasound image.
  • the imaging score of the fetal ultrasound image is stored, which is beneficial to optimize the imaging quality determination server according to the imaging score, and further facilitates obtaining high-quality fetal ultrasound images.
  • the structural features of the standard slice of the fetal ultrasound image include at least key structural features of the standard slice. Further, other structural features are also included.
  • the standard slice of the fetal ultrasound image is acquired, it is further determined that the standard slice is a normal standard slice or a suspected standard slice according to the structural features included in the standard slice. For example, in the standard view of abdominal circumference, gastric vesicle and umbilical vein are the key structural features, and liver, descending aorta, ribs, and inferior vena cava are other structural features.
  • the standard abdominal circumference section includes the key structural features of gastric bleb and umbilical vein, it also includes For other structural features of the liver, descending aorta, ribs, and inferior vena cava, the standard abdominal circumference section is the normal standard section.
  • the standard abdominal circumference section includes the key structural features of gastric vesicle and umbilical vein, it does not include liver, descending aorta, and ribs.
  • the standard view of the abdominal circumference is determined to be a suspected standard view.
  • the method for determining the imaging quality of the fetal ultrasound image described in FIG. 1 can automatically determine the imaging quality of the fetal ultrasound image according to the determined imaging score of the fetal ultrasound image, and can quickly and accurately determine the quality of the fetal ultrasound image.
  • the imaging quality of fetal ultrasound images can be accurately and rapidly controlled, and high-quality fetal ultrasound images can be obtained, which is conducive to obtaining accurate fetal growth and development. It is possible to know the standardization of the staff in the process of detecting fetal ultrasound images and whether the items required to be detected by the fetus have been completely detected.
  • FIG. 2 is a schematic flowchart of another method for determining imaging quality control of fetal ultrasound images disclosed in an embodiment of the present invention.
  • the method for determining imaging quality control of fetal ultrasound images described in FIG. 2 may be applied to an imaging quality determination server (service device), wherein the imaging quality determination server may include a local imaging quality determination server or a cloud imaging quality determination server , the embodiments of the present invention are not limited.
  • the method for determining the imaging quality control of the fetal ultrasound image may include the following operations:
  • the detection result corresponding to the fetal ultrasound image is used to determine the imaging quality of the fetal ultrasound image
  • the detection result corresponding to the fetal ultrasound image includes a feature detection result, a biological diameter detection result, and a Doppler blood flow
  • the feature detection results include at least one of part feature detection results, structural feature detection results, and standard section detection results, which are not limited in this embodiment of the present invention.
  • the feature detection result is used to indicate whether the feature to be detected is completely detected, that is, whether at least one of the part feature, structural feature and standard section to be detected has been detected.
  • the method may further include:
  • step 204 When it is determined that the result is yes, trigger the execution of step 204;
  • the detection prompt is used to indicate that there are undetected features (for example, the long-diameter section of the humerus is not detected, etc.), the biological diameter of the fetal ultrasound image is not detected, and the fetal ultrasound image is not detected. at least one of the Doppler blood flow spectra. And the detection prompt is used to prompt the authorized personnel to detect the undetected content.
  • step 204 may be triggered.
  • the detection and detection of the fetal ultrasound image when the detection and detection of the fetal ultrasound image is obtained, it is first judged whether the detection result meets the detection requirements.
  • the detection prompt of the ultrasound image can prompt the authorized personnel to have undetected content and supervise the operation behavior of the authorized personnel, which is convenient for the authorized personnel to detect the undetected content, thereby facilitating the acquisition of accurate fetal ultrasound imaging. score, thereby improving the accuracy of determining the imaging quality of the fetal ultrasound image, thereby realizing precise and rapid control of the imaging quality of the fetal ultrasound image.
  • the embodiment of the present invention determines the imaging quality of the fetal ultrasound image by acquiring the detection results of the fetal ultrasound image, such as whether to detect all standard slices that need to be detected, and combining the imaging score of the fetal ultrasound image with the detection result. , which can further improve the accuracy of determining the imaging quality of fetal ultrasound images, thereby further realizing accurate and rapid control of the imaging quality of fetal ultrasound images, and further obtaining high-quality fetal ultrasound images, which is conducive to obtaining accurate fetal growth and development. condition.
  • the method further includes:
  • the chapter where the abnormal feature is located is determined as the abnormal feature position, where the position includes chapters , at least one of standard cut planes and parts.
  • the abnormal feature position is output to an authorized person.
  • the chapter in which the lateral ventricle is located is determined as the abnormal chapter, and the abnormal characteristic chapter is output to the authorized personnel.
  • the optimal abnormal feature position is selected from the abnormal feature positions corresponding to the multiple abnormal features, for example, the chapter on the optimal abnormal feature. Further, when an abnormal feature occurs, the score corresponding to the abnormal feature position is multiplied by the determined coefficient (for example: 10) to obtain the score corresponding to the abnormal feature position, and the abnormal feature position with the highest score is obtained as the optimal value. Abnormal feature location.
  • the position of the abnormal feature is determined, for example: the chapter on the optimal abnormal feature, and the position is output to the authorized personnel, which is convenient for the authorized personnel to quickly Identify and locate abnormal features.
  • step 201 for other descriptions of step 201, step 202, and step 204, please refer to the detailed description of step 101 to step 103 in Embodiment 1, which is not repeated in this embodiment of the present invention.
  • the method for determining the imaging quality control of the fetal ultrasound image described in FIG. 2 can automatically determine the imaging quality of the fetal ultrasound image according to the determined imaging score of the fetal ultrasound image, and can quickly and accurately determine the quality of the fetal ultrasound image.
  • the imaging quality of fetal ultrasound images can be accurately and rapidly controlled, and high-quality fetal ultrasound images can be obtained, which is conducive to obtaining accurate fetal growth and development. It is possible to know the standardization of the staff in the process of detecting fetal ultrasound images and whether the items required to be detected by the fetus have been completely detected.
  • the imaging score of the fetal ultrasound image can be automatically combined with the detection results to jointly determine the imaging quality of the fetal ultrasound image, which can further improve the determination accuracy of the imaging quality control of the fetal ultrasound image, thereby further realizing the imaging quality of the fetal ultrasound image. precise and fast control.
  • the embodiment of the present invention discloses a method for determining an imaging score of a fetal ultrasound image.
  • the determination method may be applied to an imaging quality determination server, where the imaging quality determination server may include a local imaging quality determination server or a cloud imaging quality determination server, which is not limited in this embodiment of the present invention.
  • the method for determining the imaging score of the fetal ultrasound image may include the following operations:
  • Step 1 Perform a chapter division operation on the fetal ultrasound image to obtain at least one target chapter.
  • the fetal ultrasound image is composed of consecutive multiple frames of sub-fetal ultrasound images.
  • each target chapter includes several consecutive frames of sub-fetal ultrasound images, and all sub-fetal ultrasound images included in each target chapter are different from each other, and the total number of all sub-fetal ultrasound images included in each target chapter Equal to the total number of fetal ultrasound images included in all child fetal ultrasound images.
  • Step 2 Calculate the score of the target chapter according to the parameters of the target feature of each frame of the sub-fetal ultrasound image included in each target chapter.
  • the target feature of each frame of the fetal son ultrasound image includes at least one of a part feature, a structural feature, and a standard slice of the son fetal ultrasound image.
  • Step 3 Determine the score of all target chapters as the imaging score of the fetal ultrasound image.
  • implementing the method for determining the imaging score of the fetal ultrasound image can automatically divide the fetal ultrasound image into chapters of different categories, and use the calculated score of each chapter as the imaging score of the fetal ultrasound image, which can improve the performance of the fetal ultrasound image.
  • the acquisition accuracy and efficiency of the imaging score of the fetal ultrasound image is beneficial to improve the accuracy and reliability of the imaging quality of the fetal ultrasound image, and realize the precise and rapid control of the imaging quality of the fetal ultrasound image, which is conducive to the acquisition of fetal ultrasound images.
  • High-quality fetal ultrasound images help to improve the accuracy and reliability of fetal growth and development.
  • FIG. 3 is a schematic structural diagram of a device for determining the imaging quality of fetal ultrasound images disclosed in an embodiment of the present invention.
  • the apparatus for determining imaging quality control of fetal ultrasound images described in FIG. 3 may be applied to an imaging quality determination server (service device), wherein the imaging quality determination server may include a local imaging quality determination server or a cloud imaging quality determination server , the embodiments of the present invention are not limited.
  • the device for determining the imaging quality control of the fetal ultrasound image may include an acquisition module 301, a first determination module 302 and a second determination module 303, wherein:
  • the acquiring module 301 is configured to acquire parameters of the fetal ultrasound image, where the parameters of the fetal ultrasound image are used to determine the imaging quality of the fetal ultrasound image.
  • the first determination module 302 is configured to determine the imaging score of the fetal ultrasound image according to the parameters of the fetal ultrasound image.
  • the second determination module 303 is configured to determine the imaging quality of the fetal ultrasound image according to the imaging score of the fetal ultrasound image.
  • the device for implementing the imaging quality control of the fetal ultrasound image described in FIG. 3 can automatically determine the imaging quality of the fetal ultrasound image according to the determined imaging score of the fetal ultrasound image, and can quickly and accurately determine the quality of the fetal ultrasound image.
  • the imaging quality of fetal ultrasound images can be accurately and rapidly controlled, and high-quality fetal ultrasound images can be obtained, which is conducive to obtaining accurate fetal growth and development. It is possible to know the standardization of the staff in the process of detecting fetal ultrasound images and whether the items required to be detected by the fetus have been completely detected.
  • the manner in which the acquiring module 301 acquires the parameters of the fetal ultrasound image is specifically:
  • the fetal ultrasound image is input into the determined parameter determination model for analysis, and the analysis result output by the parameter determination model is obtained as a parameter of the fetal ultrasound image
  • the parameter determination model includes a feature determination model and/or a section determination model, wherein , when the parameter determination model is a feature determination model, the parameters of the fetal ultrasound image include the feature parameters of the fetal ultrasound image, and the feature parameters of the fetal ultrasound image include the position feature parameters and/or structural feature parameters of the fetal ultrasound image;
  • the parameter determination model is a slice determination model
  • the parameters of the fetal ultrasound image include slice parameters of the fetal ultrasound image
  • the slice parameters of the fetal ultrasound image include slice scores of standard slices of the fetal ultrasound image; and/or,
  • the parameters of the fetal ultrasound image include characteristic parameters and/or slice parameters of the fetal ultrasound image
  • the parameters of the fetal ultrasound image include characteristic parameters and/or slice parameters of the fetal ultrasound image
  • the characteristic parameters of the fetal ultrasound image include site characteristic parameters and/or structural characteristic parameters of the fetal ultrasound image
  • the slice parameters of the fetal ultrasound image include slice scores of standard slices of the fetal ultrasound image.
  • the implementation of the determination device described in FIG. 3 can also be analyzed by inputting the fetal ultrasound image into the parameter determination model, which can quickly realize the automatic acquisition of the parameters of the fetal ultrasound image without manual participation, and can improve the accuracy of the parameter acquisition of the fetal ultrasound image. Reliability, thereby improving the accuracy and efficiency of determining the imaging score of the fetal ultrasound image; and acquiring the parameters of the fetal ultrasound image by sending the terminal device and/or inputting by authorized personnel, which can enrich the way of acquiring the parameters of the fetal ultrasound image.
  • the above-mentioned fetal ultrasound image consists of multiple frames of consecutive sub-fetal ultrasound images.
  • the first determination module 302 may include a division sub-module 3021, a calculation sub-module 3022 and a determination sub-module 3023, wherein:
  • the division sub-module 3021 is configured to perform a chapter division operation on the fetal ultrasound images to obtain at least one target chapter, each target chapter includes several consecutive frames of child fetal ultrasound images, and all child fetal ultrasound images included in each target chapter are different from each other , and the total number of all child fetal ultrasound images included in each target section is equal to the total number of all child fetal ultrasound images included in the fetal ultrasound image.
  • the calculation sub-module 3022 is configured to calculate the score of each target section according to the parameters of the target features of each frame of sub-fetal ultrasound images included in each target section, and the target features of each frame of sub-fetal ultrasound images include the sub-fetal ultrasound images At least one of the site features, structural features, and standard cut planes.
  • a determination sub-module 3023 is used to determine the scores of all target chapters as imaging scores of the fetal ultrasound image.
  • the fetal ultrasound image corresponds to at least one target category
  • the target category includes a feature category or a slice category
  • the number of target features corresponding to each target category is greater than or equal to 1.
  • the target category when the target category is a feature category, the target feature includes structural features or part features; when the target category is a section category, the target feature includes a standard section.
  • each target category corresponds to at least one frame of child fetal ultrasound images, and all child fetal ultrasound images corresponding to each target category are different from each other, and all child fetal ultrasound images corresponding to all target categories constitute a fetal ultrasound image.
  • implementing the determination device described in FIG. 4 can automatically divide the fetal ultrasound image into chapters of different categories, and use the calculated score of each chapter as the imaging score of the fetal ultrasound image, thereby improving the fetal ultrasound image.
  • the accuracy and efficiency of the acquisition of the imaging score are improved, which is beneficial to improve the accuracy and reliability of the imaging quality of the fetal ultrasound image, and further facilitates the acquisition of high-quality fetal ultrasound images.
  • the division submodule 3021 performs chapter division operation on the fetal ultrasound image, and the mode of obtaining at least one target chapter is specifically:
  • the starting frame sub-fetal ultrasound image corresponding to each target category, the ending frame sub-fetal ultrasound image corresponding to the target category, and the determined position of the starting frame sub-fetal ultrasound image corresponding to the target category correspond to the target category All sub-fetal ultrasound images between the positions where the sub-fetal ultrasound images of the termination frame are located are determined as the target chapters corresponding to each target category;
  • the position of the child fetal ultrasound image corresponding to the starting frame of each target category is the position where the child fetal ultrasound image containing the target features of the target category appears for the first time in the fetal ultrasound image, and the termination frame corresponding to each target category is located in the fetal ultrasound image.
  • the location of the fetal ultrasound image is the last occurrence of the child fetal ultrasound image containing the target feature of the target category in the fetal ultrasound image or the child fetal ultrasound image from the starting frame containing the target feature of the target category in the fetal ultrasound image.
  • the images start to continuously appear at the position where the pre-set number of frames of the sub-fetal ultrasound images are located.
  • implementing the determination device described in FIG. 4 can also automatically first determine the position of the fetal ultrasound image of the starting frame and the position of the fetal ultrasound image of the ending frame of each type of part features or structural features or standard slices.
  • the automatic determination of the chapters corresponding to the part feature or the structural feature or the standard section is beneficial to improve the determination efficiency and accuracy of each chapter, thereby improving the calculation efficiency and accuracy of the score of each chapter.
  • the calculation sub-module 3022 calculates the score of the target chapter according to the parameters of the target features of each frame of sub-fetal ultrasound images included in each target chapter, specifically as follows: :
  • each frame of child fetal ultrasound image is the part feature of the child fetal ultrasound image
  • the target feature of each sub-fetal ultrasound image is the structural feature of the sub-fetal ultrasound image
  • the class probability of the structural feature of each frame of the sub-fetal ultrasound image included in each target chapter the position probability of the structural feature, and the structure
  • the weight value of the feature calculate the score of the target chapter
  • each frame of sub-fetal ultrasound image is the standard section of the sub-fetal ultrasound image
  • implementing the determination device described in FIG. 4 can also calculate the structural feature score corresponding to each type of structural feature or the section score corresponding to each type of section or the part feature score corresponding to each type of part feature.
  • the determination of the score of the chapter can also enrich the way of determining the score of the chapter, and improve the accuracy and reliability of the score of the chapter;
  • the score and the score of the chapter obtained through the slice score jointly determine the imaging quality of fetal ultrasound images, which can further improve the accuracy and reliability of the determination of the imaging quality of fetal ultrasound images, thereby further facilitating the acquisition of higher-quality images.
  • Fetal ultrasound image can also calculate the structural feature score corresponding to each type of structural feature or the section score corresponding to each type of section or the part feature score corresponding to each type of part feature.
  • the apparatus further includes a calculation module 304 and an update module 305, wherein:
  • the determination submodule 3023 is further configured to perform a chapter division operation on the fetal ultrasound image in the division submodule 3021, and after obtaining at least one target chapter, determine the total number of frames of all fetal fetal ultrasound images included in each target chapter;
  • the calculation module 304 is configured to, after the first determination module 302 calculates the score of the target chapter according to the parameters of the target feature of each frame of sub-fetal ultrasound images included in each target chapter, divide the score of each target chapter by The total number of frames of all fetal fetal ultrasound images included in the target chapter, and the target score of the target chapter is obtained.
  • the update module 305 is configured to update the score of each target chapter to the target score of the target chapter, and trigger the second determination module 303 to perform the above-mentioned determination that the scores of all target chapters are equal to the imaging score of the fetal ultrasound image. operate.
  • the determination sub-module 3023 may be triggered to perform the above-mentioned determination of all child fetuses included in each target chapter Manipulate the total number of frames of the ultrasound image.
  • implementing the determination device described in FIG. 4 can also obtain a new score of the chapter based on the score of the chapter and the total number of frames of the chapter after obtaining the score of the chapter, and image the fetal ultrasound image.
  • the score is changed to the new score, which can further improve the accuracy of determining the imaging score of the fetal ultrasound image, thereby helping to improve the accuracy of determining the imaging quality of the fetal ultrasound image.
  • the manner in which the first determining module 302 determines the imaging score of the fetal ultrasound image according to the parameters of the fetal ultrasound image is specifically:
  • the site feature parameters of the fetal ultrasound image include the site feature score of the fetal ultrasound image, and it is determined that the site feature score of the fetal ultrasound image is the value of the site feature score of the fetal ultrasound image. Imaging Score; and/or,
  • the structural feature parameter of the fetal ultrasound image includes the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature;
  • the structural feature score of the structural feature is calculated, and the structural feature score is determined as the imaging score of the fetal ultrasound image. value;
  • the structural feature parameter of the fetal ultrasound image includes the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature.
  • the part feature parameter of the fetal ultrasound image includes the class probability of the part feature of the fetal ultrasound image;
  • the class probability of the part feature of the fetal ultrasound image the class probability of the structural feature of the fetal ultrasound image, the position probability of the structural feature, and the weight value of the structural feature, the structural feature score of the structural feature is calculated, and the structure is determined.
  • the feature score is used as the imaging score of the fetal ultrasound image; and/or, according to the category probability of the part feature of the fetal ultrasound image and the category probability of the structural feature of the fetal ultrasound image, the standard section of the fetal ultrasound image is determined, and according to the fetal ultrasound image.
  • the parameters of the structural features in the standard section of the ultrasound image, and the section score of the standard section of the fetal ultrasound image is calculated as the imaging score of the fetal ultrasound image.
  • the structural feature parameters of the fetal ultrasound image include the standard section of the fetal ultrasound image. parameters of the structural features.
  • implementing the determination device described in FIG. 4 can also realize the calculation of the score of the fetal ultrasound image by separately calculating the part feature score, the structural feature score and the standard section score of the fetal ultrasound image, which can not only enrich the fetal ultrasound image.
  • the method of determining the score of the image improves the accuracy of determining the imaging quality of the fetal ultrasound image, thereby further realizing the precise and rapid control of the imaging quality of the fetal ultrasound image.
  • the apparatus further includes a third determination module 306, wherein:
  • the third determination module 306 is configured to determine the detection result corresponding to the fetal ultrasound image before the second determination module 302 determines the imaging quality of the fetal ultrasound image according to the imaging score of the fetal ultrasound image, and the detection result corresponding to the fetal ultrasound image is used for Determine the imaging quality of the fetal ultrasound image, and the detection result corresponding to the fetal ultrasound image includes at least one of a feature detection result, a biological diameter line detection result, and a Doppler blood flow spectrum detection result, and the feature detection result includes part features At least one of detection results, structural feature detection results and standard section detection results;
  • the manner in which the second determining module 302 determines the imaging quality of the fetal ultrasound image according to the imaging score of the fetal ultrasound image is specifically:
  • the imaging quality of the fetal ultrasound image is determined according to the imaging score of the fetal ultrasound image and the characteristic result corresponding to the fetal ultrasound image.
  • implementing the determination device described in FIG. 4 can also obtain the detection result of the fetal ultrasound image, such as whether to detect all the standard slices that need to be detected, and combine the imaging score of the fetal ultrasound image with the detection result to jointly determine the detection result.
  • the imaging quality of fetal ultrasound images can further improve the accuracy of determining the imaging quality of fetal ultrasound images, so as to further achieve accurate and rapid control of the imaging quality of fetal ultrasound images, and further obtain high-quality fetal ultrasound images, which is conducive to obtaining Accurate fetal growth and development.
  • FIG. 5 is another device for determining the imaging quality of fetal ultrasound images disclosed in an embodiment of the present invention.
  • the method for determining imaging quality control of fetal ultrasound images described in FIG. 5 can be applied to an imaging quality determination server (service device), wherein the imaging quality determination server may include a local imaging quality determination server or a cloud imaging quality determination server , the embodiments of the present invention are not limited.
  • the device for determining the imaging quality control of the fetal ultrasound image may include:
  • a memory 501 storing executable program code
  • processor 502 coupled to the memory 501;
  • an input interface 503 coupled with the processor 502 and an output interface 504;
  • the processor 502 invokes the executable program code stored in the memory 501 to execute some or all of the steps in the method for determining imaging quality control of fetal ultrasound images described in Embodiment 1 or Embodiment 2.
  • An embodiment of the present invention discloses a computer-readable storage medium, which stores a computer program for electronic data exchange, wherein the computer program enables a computer to perform the imaging quality control of fetal ultrasound images described in Embodiment 1 or Embodiment 2 some or all of the steps in the determination method.
  • An embodiment of the present invention discloses a computer program product.
  • the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the description in the first embodiment or the second embodiment. Part or all of the steps in a method for determining imaging quality control of fetal ultrasound images.
  • modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in One place, or it can be distributed over multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.
  • Read-Only Memory ROM
  • Random Access Memory Random Access Memory
  • PROM Programmable Read-only Memory
  • EPROM Erasable Programmable Read Only Memory
  • OTPROM One-time Programmable Read-Only Memory
  • EEPROM Electronically Erasable Programmable Read-Only Memory
  • CD-ROM Compact Disc Read -Only Memory
  • the method and device for determining the imaging quality control of fetal ultrasound images disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention. It is not intended to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that it is still possible to modify the technical solutions described in the foregoing embodiments, or to modify some of the technical features. Equivalent replacements are made; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Surgery (AREA)
  • Pathology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Gynecology & Obstetrics (AREA)
  • Pregnancy & Childbirth (AREA)
  • Physiology (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)

Abstract

一种胎儿超声图像的成像质量控制的确定方法及装置，该方法包括：获取胎儿超声图像的参数，该胎儿超声图像的参数用于确定该胎儿超声图像的成像质量(101)；根据该胎儿超声图像的参数确定该胎儿超声图像的成像分值(102)，并根据该胎儿超声图像的成像分值确定该胎儿超声图像的成像质量(103)。该方法通过根据确定出的胎儿超声图像的成像分值自动确定胎儿超声图像的成像质量，能够快速且准确地确定胎儿超声图像的成像质量，从而实现胎儿超声图像的成像质量的精确且快速控制，进而获取到高质量的胎儿超声图像，有利于获取到准确的胎儿生长发育情况；通过确定出的胎儿超声图像的成像质量，还能够知晓工作人员在检测胎儿超声图像过程中的规范性。

Description

一种胎儿超声图像的成像质量控制的确定方法及装置 技术领域
本发明涉及图像处理技术领域，尤其涉及一种胎儿超声图像的成像质量控制的确定方法及装置。
背景技术
随着社会的进步以及人们获取健康新生儿意识的加强，越来越多的孕妇按照产检计划定期前往医院进行产检来获知胎儿的生长发育情况。
实际应用中，为了清楚且准确地确定胎儿的生长发育情况，需要获取到高质量的胎儿超声图像，而为了获取高质量的胎儿超声图像，需要对胎儿超声图像的质量进行控制。目前，对胎儿超声图像进行质量控制的方法主要为：由具有相关经验的医护人员判断胎儿超声图像中关键结构是否存在以及关键结构的几何形状是否标准来定量评估胎儿超声图像，从而实现胎儿超声图像的质量控制。然而，实践发现，由于医护人员存在一定的主观性且长时间工作之后容易疲劳，这很容易导致胎儿超声图像的质量控制准确性低。
发明内容
本发明所要解决的技术问题在于，提供一种胎儿超声图像的成像质量控制的确定方法及装置，能够提高胎儿超声图像的质量控制准确性。
为了解决上述技术问题，本发明第一方面公开了一种胎儿超声图像的成像质量控制的确定方法，所述方法包括：
获取胎儿超声图像的参数，所述胎儿超声图像的参数用于确定所述胎儿超声图像的成像质量；
根据所述胎儿超声图像的参数确定所述胎儿超声图像的成像分值，并根据所述胎儿超声图像的成像分值确定所述胎儿超声图像的成像质量。
作为一种可选的实施方式，在本发明第一方面中，所述获取胎儿超声图像的参数，包括：
将胎儿超声图像输入确定出的参数确定模型中进行分析，并获取所述参数确定模型输出的分析结果，作为所述胎儿超声图像的参数，所述参数确定模型包括特征确定模型和/或切面确定模型，其中，当所述参数确定模型为所述特征确定模型时，所述胎儿超声图像的参数包括该胎儿超声图像的特征参数，所述胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数和/或结构特征参数；当所述参数确定模型为所述切面确定模型时，所述胎儿超声图像的参数包括该胎儿超声图像的切面参数，所述胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值；和/或，
接收确定出的终端设备发送的和/或授权人员输入的针对胎儿超声图像的参数，作为胎儿超声图像的参数，所述胎儿超声图像的参数包括该胎儿超声图像的特征参数和/或切面参数，所述胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数和/或结构特征参数，所述胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值。
作为一种可选的实施方式，在本发明第一方面中，所述胎儿超声图像由连续多帧子胎儿超声图像组成；
其中，所述根据所述胎儿超声图像的参数确定所述胎儿超声图像的成像分值，包括：
对所述胎儿超声图像执行章节划分操作，得到至少一个目标章节，每个所 述目标章节包括连续若干帧所述子胎儿超声图像，且每个所述目标章节包括的所有所述子胎儿超声图像互不相同，以及每个所述目标章节包括的所有所述子胎儿超声图像的总数量等于所述胎儿超声图像包括的所有所述子胎儿超声图像的总数量；
根据每个所述目标章节包括的每帧所述子胎儿超声图像的目标特征的参数，计算该目标章节的分值，每帧所述子胎儿超声图像的目标特征包括该子胎儿超声图像的部位特征、结构特征以及标准切面中的至少一种；
确定所有所述目标章节的分值为所述胎儿超声图像的成像分值。
作为一种可选的实施方式，在本发明第一方面中，所述胎儿超声图像对应至少一种目标类别，所述目标类别包括特征类别或者切面类别，每个所述目标类别对应的目标特征的数量大于等于1；
其中，当所述目标类别为所述特征类别时，所述目标特征包括结构特征或者部位特征；当所述目标类别为所述切面类别时，所述目标特征包括标准切面；
每个所述目标类别均对应至少一帧所述子胎儿超声图像，且每个所述目标类别对应的所有所述子胎儿超声图像均互不相同且所有所述目标类别对应的所有所述子胎儿超声图像组成所述胎儿超声图像。
作为一种可选的实施方式，在本发明第一方面中，所述对所述胎儿超声图像执行章节划分操作，得到至少一个目标章节，包括：
确定所述胎儿超声图像包括的每个所述目标类别对应的起始帧子胎儿超声图像所在的位置以及该目标类别对应的终止帧子胎儿超声图像所在的位置；
将每个所述目标类别对应的起始帧子胎儿超声图像、该目标类别对应的终止帧子胎儿超声图像以及确定出的该目标类别对应的起始帧子胎儿超声图像所在的位置与该目标类别对应的终止帧子胎儿超声图像所在的位置之间的所有子胎儿超声图像，确定为每个所述目标类别对应的目标章节；
其中，每个所述目标类别对应的起始帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在所述胎儿超声图像中首次出现的位置，每个所述目标类别对应的终止帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在所述胎儿超声图像中最后一次出现的位置或者在所述胎儿超声图像中从包含该目标类别的目标特征的起始帧子胎儿超声图像开始连续出现第预设数量帧子胎儿超声图像所在的位置。
作为一种可选的实施方式，在本发明第一方面中，所述根据每个所述目标章节包括的每帧所述子胎儿超声图像的目标特征的参数，计算该目标章节的分值，包括：
当每帧所述子胎儿超声图像的目标特征为该子胎儿超声图像的部位特征时，计算每个所述目标章节包括的每帧所述子胎儿超声图像的部位特征的部位特征分值之和，作为该目标章节的分值；
当每帧所述子胎儿超声图像的目标特征为该子胎儿超声图像的结构特征时，根据每个所述目标章节包括的每帧所述子胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该目标章节的分值；
当每帧所述子胎儿超声图像的目标特征为该子胎儿超声图像的标准切面时，计算每个所述目标章节包括的每帧所述子胎儿超声图像的标准切面的切面分值之和，作为该目标章节的分值。
作为一种可选的实施方式，在本发明第一方面中，所述对所述胎儿超声图像执行章节划分操作，得到至少一个目标章节之后，所述方法还包括：
确定每个所述目标章节包括的所有所述子胎儿超声图像的总帧数；
以及，所述根据每个所述目标章节包括的每帧所述子胎儿超声图像的目标特征的参数，计算该目标章节的分值之后，所述方法还包括：
将每个所述目标章节的分值除以该目标章节包括的所有所述子胎儿超声图 像的总帧数，得到该目标章节的目标分值；
将每个所述目标章节的分值更新为该目标章节的目标分值，并触发执行所述的确定所有所述目标章节的分值为所述胎儿超声图像的成像分值的操作。
作为一种可选的实施方式，在本发明第一方面中，所述根据所述胎儿超声图像的参数确定所述胎儿超声图像的成像分值，包括：
当所述胎儿超声图像的参数为所述胎儿超声图像的部位特征参数时，所述胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征分值，确定所述胎儿超声图像的部位特征分值为该胎儿超声图像的成像分值；和/或，
当所述胎儿超声图像的参数为所述胎儿超声图像的结构特征参数时，所述胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值；
根据所述胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为所述胎儿超声图像的成像分值；和/或，
当所述胎儿超声图像的参数为所述胎儿超声图像的特征参数时，所述胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，所述胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征的类别概率；
根据所述胎儿超声图像的部位特征的类别概率、该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为所述胎儿超声图像的成像分值；和/或，根据所述胎儿超声图像的部位特征的类别概率以及该胎儿超声图像的结构特征的类别概率，确定所述胎儿超声图像的标准切面，并根据所述胎儿超声图像的标准切面内的结构特征的参数，计算所述胎儿超声图像的标准切面的切面分值，作为所述胎儿超声图像的成像分值，所述胎儿超声图像的结构特征参数包括该胎儿超声图像的标准切面内的结构特征的参数。
作为一种可选的实施方式，在本发明第一方面中，所述根据所述胎儿超声图像的成像分值确定所述胎儿超声图像的成像质量之前，所述方法还包括：
确定所述胎儿超声图像对应的检测结果，所述胎儿超声图像对应的检测结果用于确定所述胎儿超声图像的成像质量，且所述胎儿超声图像对应的检测结果包括特征检测结果、生物学径线检测结果以及多普勒血流频谱检测结果中的至少一种，所述特征检测结果包括部位特征检测结果、结构特征检测结果、标准切面检测结果中的至少一种；
以及，所述根据所述胎儿超声图像的成像分值确定所述胎儿超声图像的成像质量，包括：
根据所述胎儿超声图像的成像分值以及所述胎儿超声图像对应的特征结果确定所述胎儿超声图像的成像质量。
本发明第二方面公开了一种胎儿超声图像的成像质量控制的确定装置，所述装置包括：
获取模块，用于获取胎儿超声图像的参数，所述胎儿超声图像的参数用于确定所述胎儿超声图像的成像质量；
第一确定模块，用于根据所述胎儿超声图像的参数确定所述胎儿超声图像的成像分值；
第二确定模块，用于根据所述胎儿超声图像的成像分值确定所述胎儿超声图像的成像质量。
作为一种可选的实施方式，在本发明第二方面中，所述获取模块获取胎儿超声图像的参数的方式具体为：
将胎儿超声图像输入确定出的参数确定模型中进行分析，并获取所述参数 确定模型输出的分析结果，作为所述胎儿超声图像的参数，所述参数确定模型包括特征确定模型和/或切面确定模型，其中，当所述参数确定模型为所述特征确定模型时，所述胎儿超声图像的参数包括该胎儿超声图像的特征参数，所述胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数和/或结构特征参数；当所述参数确定模型为所述切面确定模型时，所述胎儿超声图像的参数包括该胎儿超声图像的切面参数，所述胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值；和/或，
接收确定出的终端设备发送的和/或授权人员输入的针对胎儿超声图像的参数，作为胎儿超声图像的参数，所述胎儿超声图像的参数包括该胎儿超声图像的特征参数和/或切面参数，所述胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数和/或结构特征参数，所述胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值。
作为一种可选的实施方式，在本发明第二方面中，所述胎儿超声图像由多帧连续子胎儿超声图像组成；
以及，所述第一确定模块包括：
划分子模块，用于对所述胎儿超声图像执行章节划分操作，得到至少一个目标章节，每个所述目标章节包括若干连续帧所述子胎儿超声图像，且每个所述目标章节包括的所有所述子胎儿超声图像互不相同，以及每个所述目标章节包括的所有所述子胎儿超声图像的总数量等于所述胎儿超声图像包括的所有所述子胎儿超声图像的总数量；
计算子模块，用于根据每个所述目标章节包括的每帧所述子胎儿超声图像的目标特征的参数，计算每个所述目标章节的分值，每帧所述子胎儿超声图像的目标特征包括该子胎儿超声图像的部位特征、结构特征以及标准切面中的至少一种；
确定子模块，用于确定所有所述目标章节的分值为所述胎儿超声图像的成像分值。
作为一种可选的实施方式，在本发明第二方面中，所述胎儿超声图像对应至少一种目标类别，所述目标类别包括特征类别或者切面类别，每个所述目标类别对应的目标特征的数量大于等于1；
其中，当所述目标类别为所述特征类别时，所述目标特征包括结构特征或者部位特征；当所述目标类别为所述切面类别时，所述目标特征包括标准切面；
每个所述目标类别均对应至少一帧所述子胎儿超声图像，且每个所述目标类别对应的所有所述子胎儿超声图像均互不相同且所有所述目标类别对应的所有所述子胎儿超声图像组成所述胎儿超声图像。
作为一种可选的实施方式，在本发明第二方面中，所述划分子模块对所述胎儿超声图像执行章节划分操作，得到至少一个目标章节的方式具体为：
确定所述胎儿超声图像包括的每个所述目标类别对应的起始帧子胎儿超声图像所在的位置以及该目标类别对应的终止帧子胎儿超声图像所在的位置；
将每个所述目标类别对应的起始帧子胎儿超声图像、该目标类别对应的终止帧子胎儿超声图像以及确定出的该目标类别对应的起始帧子胎儿超声图像所在的位置与该目标类别对应的终止帧子胎儿超声图像所在的位置之间的所有子胎儿超声图像，确定为每个所述目标类别对应的目标章节；
其中，每个所述目标类别对应的起始帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在所述胎儿超声图像中首次出现的位置，每个所述目标类别对应的终止帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在所述胎儿超声图像中最后一次出现的位置或者在所述胎儿超声图像中从包含该目标类别的目标特征的起始帧子胎儿超声图像开始连续出现第预设数量帧子胎儿超声图像所在的位置。
作为一种可选的实施方式，在本发明第二方面中，所述计算子模块根据每个所述目标章节包括的每帧所述子胎儿超声图像的目标特征的参数，计算该目标章节的分值的方式具体为：
当每帧所述子胎儿超声图像的目标特征为该子胎儿超声图像的部位特征时，计算每个所述目标章节包括的每帧所述子胎儿超声图像的部位特征的部位特征分值之和，作为该目标章节的分值；
当每帧所述子胎儿超声图像的目标特征为该子胎儿超声图像的结构特征时，根据每个所述目标章节包括的每帧所述子胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该目标章节的分值；
当每帧所述子胎儿超声图像的目标特征为该子胎儿超声图像的标准切面时，计算每个所述目标章节包括的每帧所述子胎儿超声图像的标准切面的切面分值之和，作为该目标章节的分值。
作为一种可选的实施方式，在本发明第二方面中，所述确定子模块，还用于在所述划分子模块对所述胎儿超声图像执行章节划分操作，得到至少一个目标章节之后，确定每个所述目标章节包括的所有所述子胎儿超声图像的总帧数；
以及，所述装置还包括：
计算模块，用于在所述第一确定模块根据每个所述目标章节包括的每帧所述子胎儿超声图像的目标特征的参数，计算该目标章节的分值之后，将每个所述目标章节的分值除以该目标章节包括的所有所述子胎儿超声图像的总帧数，得到该目标章节的目标分值；
更新模块，用于将每个所述目标章节的分值更新为该目标章节的目标分值，并触发所述第二确定模块执行所述的确定所有所述目标章节的分值为所述胎儿超声图像的成像分值的操作。
作为一种可选的实施方式，在本发明第二方面中，所述第一确定模块根据所述胎儿超声图像的参数确定所述胎儿超声图像的成像分值的方式具体为：
当所述胎儿超声图像的参数为所述胎儿超声图像的部位特征参数时，所述胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征分值，确定所述胎儿超声图像的部位特征分值为该胎儿超声图像的成像分值；和/或，
当所述胎儿超声图像的参数为所述胎儿超声图像的结构特征参数时，所述胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值；
根据所述胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为所述胎儿超声图像的成像分值；和/或，
当所述胎儿超声图像的参数为所述胎儿超声图像的特征参数时，所述胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，所述胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征的类别概率；
根据所述胎儿超声图像的部位特征的类别概率、该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为所述胎儿超声图像的成像分值；和/或，根据所述胎儿超声图像的部位特征的类别概率以及该胎儿超声图像的结构特征的类别概率，确定所述胎儿超声图像的标准切面，并根据所述胎儿超声图像的标准切面内的结构特征的参数，计算所述胎儿超声图像的标准切面的切面分值，作为所述胎儿超声图像的成像分值，所述胎儿超声图像的结构特征参数包括该胎儿超声图像的标准切面内的结构特征的参数。
作为一种可选的实施方式，在本发明第二方面中，所述装置还包括：
第三确定模块，用于在所述第二确定模块根据所述胎儿超声图像的成像分 值确定所述胎儿超声图像的成像质量之前，确定所述胎儿超声图像对应的检测结果，所述胎儿超声图像对应的检测结果用于确定所述胎儿超声图像的成像质量，且所述胎儿超声图像对应的检测结果包括特征检测结果、生物学径线检测结果以及多普勒血流频谱检测结果中的至少一种，所述特征检测结果包括部位特征检测结果、结构特征检测结果以及标准切面检测结果中的至少一种；
以及，所述第二确定模块根据所述胎儿超声图像的成像分值确定所述胎儿超声图像的成像质量的方式就具体为：
根据所述胎儿超声图像的成像分值以及所述胎儿超声图像对应的特征结果确定所述胎儿超声图像的成像质量。
本发明第三方面公开了另一种胎儿超声图像的成像质量控制的确定装置，所述装置包括：
存储有可执行程序代码的存储器；
与所述存储器耦合的处理器；
所述处理器调用所述存储器中存储的所述可执行程序代码，执行本发明第一方面公开的胎儿超声图像的成像质量控制的确定方法。
本发明第四方面公开了一种计算机存储介质，所述计算机存储介质存储有计算机指令，所述计算机指令被调用时，用于执行本发明第一方面公开的胎儿超声图像的成像质量控制的确定方法。
与现有技术相比，本发明实施例具有以下有益效果：
本发明实施例中，提供了一种胎儿超声图像的成像质量控制的确定方法及装置，该方法：获取胎儿超声图像的参数，该胎儿超声图像的参数用于确定该胎儿超声图像的成像质量；根据该胎儿超声图像的参数确定该胎儿超声图像的成像分值，并根据该胎儿超声图像的成像分值确定该胎儿超声图像的成像质量。可见，实施本发明通过根据确定出的胎儿超声图像的成像分值自动确定胎儿超声图像的成像质量，能够快速且准确地确定胎儿超声图像的成像质量，从而实现胎儿超声图像的成像质量的精确且快速控制，进而获取到高质量的胎儿超声图像，有利于获取到准确的胎儿生长发育情况；通过确定出的胎儿超声图像的成像质量，还能够知晓工作人员在检测胎儿超声图像过程中的规范性以及胎儿所需检测的项目是否完全检测完毕。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例公开的一种胎儿超声图像的成像质量控制的确定方法的流程示意图；
图2是本发明实施例公开的另一种胎儿超声图像的成像质量控制的确定方法的流程示意图；
图3是本发明实施例公开的一种胎儿超声图像的成像质量控制的确定装置的结构示意图；
图4是本发明实施例公开的另一种胎儿超声图像的成像质量控制的确定装置的结构示意图；
图5是本发明实施例公开的又一种胎儿超声图像的成像质量控制的确定装置的结构示意图。
具体实施方式
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施 例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、装置、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本发明的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
本发明公开了一种胎儿超声图像的成像质量控制的确定方法及装置，能够通过根据确定出的胎儿超声图像的成像分值自动确定胎儿超声图像的成像质量，能够快速且准确地确定胎儿超声图像的成像质量，从而实现胎儿超声图像的成像质量的精确且快速控制，进而获取到高质量的胎儿超声图像，有利于获取到准确的胎儿生长发育情况；通过确定出的胎儿超声图像的成像质量，还能够知晓工作人员在检测胎儿超声图像过程中的规范性以及胎儿所需检测的项目是否完全检测完毕。以下分别进行详细说明。
实施例一
请参阅图1，图1是本发明实施例公开的一种胎儿超声图像的成像质量控制的确定方法的流程示意图。其中，图1所描述的胎儿超声图像的成像质量控制的确定方法可以应用于成像质量确定服务器(服务设备)中，其中，该成像质量确定服务器可以包括本地成像质量确定服务器或云成像质量确定服务器，本发明实施例不做限定。如图1所示，该胎儿超声图像的成像质量控制的确定方法可以包括以下操作：
101、获取胎儿超声图像的参数，该胎儿超声图像的参数用于确定该胎儿超声图像的成像质量。
本发明实施例中，胎儿超声图像为任一需要确定其成像质量的胎儿超声图像。进一步的，胎儿超声图像可以为单帧图片，也可以为动态图像。其中，当胎儿超声图像为单帧图片时，胎儿超声图像的参数可以包括该单帧胎儿超声图像的参数，进一步的，还可以包括该胎儿超声图像对应的胎儿超声视频对应的参数，本发明实施例不做限定。此时，胎儿超声图像的成像质量可以表示该单帧胎儿超声图像的成像质量，也可以表示该胎儿超声图像所在的胎儿超声视频对应的成像质量，本发明实施例不做限定。
本发明实施例中，作为一种可选的实施方式，获取胎儿超声图像的参数，可以包括：
将胎儿超声图像输入确定出的参数确定模型中进行分析，并获取参数确定模型输出的分析结果，作为该胎儿超声图像的参数。
本发明实施例中，进一步可选的，当胎儿超声图像为单帧图片时，可以按照预先确定出的帧率(例如：30帧/秒)将胎儿超声图像连续输入参数确定模型中进行分析，并获取参数确定模型依次输出的分析结果，作为每帧胎儿超声图像的参数。这样通过将连续多帧的胎儿超声图像输入参数确定模型进行分析，有利于减少因单帧胎儿超声图像包含的特征信息太少导致获取到的胎儿超声图像的参数过少甚至没有而导致无法确定胎儿超声图像的成像质量的情况发生， 以及有利于快速获取胎儿超声图像的参数。或者，当胎儿超声图像为动态图像时，该参数确定模型还能够对该胎儿超声图像执行帧分割操作，得到多帧子胎儿超声图像，并分别对多帧子胎儿超声图像进行分析，获取到多帧子胎儿超声图像的参数。这样通过对静态或者动态的胎儿超声图像执行处理操作，提高了胎儿超声图像的参数的获取可能性。
本发明实施例中，又进一步可选的，胎儿超声图像存在唯一对应的帧序号，这样通过为每帧胎儿超声图像设定唯一的帧序号，能够在胎儿超声图像的成像质量的确定过程中，清楚区分每帧胎儿超声图像以及有利于对胎儿超声图像的相关信息(例如：成像分值)的进行管理。
本发明实施例中，参数确定模型包括特征确定模型和/或切面确定模型，其中，该特征确定模型为能够确定胎儿超声图像的特征参数的模型，该切面确定模型为能够确定胎儿超声图像的特征参数的模型。其中，参数确定模型可以包括目标检测模型、实例分割模型以及语义分割模型等能够获取到胎儿超声图像的参数中的至少一种，本发明实施例不做限定。
本发明实施例中，当上述参数确定模型为特征确定模型时，该胎儿超声图像的参数包括该胎儿超声图像的特征参数，其中，该胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数和/或结构特征参数。
本发明实施例中，胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征的类别以及该胎儿超声图像的部位特征的类别概率(也称置信度)。进一步的，该胎儿超声图像的部位特征参数还可以包括该胎儿超声图像的部位特征的图形坐标。
本发明实施例中，胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别以及该胎儿超声图像的结构特征的类别概率(也称置信度)。进一步的，该胎儿超声图像的结构特征参数还包括该胎儿超声图像的结构特征的图形坐标、尺寸、位置概率中的至少一种，本发明实施例不做限定。又进一步的，该胎儿超声图像的特征信息还包括该胎儿超声图像的结构特征的多边形轮廓信息，例如：多边形轮廓坐标，这样胎儿超声图像的结构特征参数包括的内容越多越有利于提高胎儿超声图像的成像质量的确定精准性以及效率。
本发明实施例中，上述部位特征或结构特征的图形坐标均可以包括多边形坐标或椭圆形坐标，其中，多边形坐标可以包括奇数多边形坐标或偶数多边形坐标，例如：五角形坐标、长方形坐标，多边形坐标的选取取决于部位特征或结构特征的形状，这样能够提高部位特征、结构特征的坐标获取准确性。
本发明实施例中，当参数确定模型为切面确定模型时，该胎儿超声图像的参数包括该胎儿超声图像的切面参数，该胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值。进一步的，该胎儿超声图像的切面参数还包括该胎儿超声图像的标准切面的切面类别。这样通过切面确定模型自动获取胎儿超声图像的切面参数，能够提高胎儿超声图像的切面参数的获取效率以及精准性。
可见，本发明实施例还能够通过将胎儿超声图像输入参数确定模型进行分析，能够快速实现胎儿超声图像的参数自动获取，无需人工参与，能够提高胎儿超声图像的参数获取准确性以及可靠性，从而提高胎儿超声图像的成像分值的确定精准性以及效率。
本发明实施例中，作为另一种可选的实施方式，获取胎儿超声图像的参数，可以包括：
接收确定出的终端设备发送的和/或授权人员输入的针对胎儿超声图像的参数，作为胎儿超声图像的参数。
本发明实施例中，胎儿超声图像的参数包括该胎儿超声图像的特征参数和/或切面参数，该胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数 和/或结构特征参数，该胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值。
本发明实施例中，需要说明的是，针对胎儿超声图像的参数的其他描述请参阅上述实施方式中针对胎儿超声图像的参数的详细描述，在该可选的实施方式不再赘述。
该可选的方式中，终端设备预先与成像质量确定服务器(服务设备)建立通信。
可见，本发明实施例还能够通过终端设备发送和/或授权人员输入的方式获取胎儿超声图像的参数，能够丰富胎儿超声图像的参数的获取方式。
本发明实施例中，需要说明的是，胎儿超声图像的参数可以是通过以上所有方式获取的，这样能够丰富胎儿超声图像的参数的获取途径，提高胎儿超声图像的参数的获取可能性；以及结合胎儿超声图像的特征参数以及切面参数，来获取胎儿超声图像的成像分值，能够提高胎儿超声图像的成像分值的获取精准性。
102、根据上述胎儿超声图像的参数确定该胎儿超声图像的成像分值。
本发明实施例中，上述胎儿超声图像由连续多帧子胎儿超声图像组成，以及，作为一种可选的实施方式，根据胎儿超声图像的参数确定胎儿超声图像的成像分值，可以包括：
对胎儿超声图像执行章节划分操作，得到至少一个目标章节；
根据每个目标章节包括的每帧子胎儿超声图像的目标特征的参数，计算该目标章节的分值，并确定所有目标章节的分值为胎儿超声图像的成像分值。
本发明实施例中，可选的，每帧子胎儿超声图像的目标特征包括该子胎儿超声图像的部位特征、结构特征以及标准切面中的至少一种。
本发明实施例中，该子胎儿超声图像的部位特征包括但不限于腹部特征、颅脑特征、肺部特征、手臂特征、脚趾特征、心脏特征。
本发明实施例中，该子胎儿超声图像的结构特征包括但不限于胃泡结构特征、脐静脉结构特征、透明隔腔结构特征、丘脑结构特征、侧脑室肝脏结构特征、降主动脉结构特征、肋骨结构特征、下腔静脉结构特征。
本发明实施例中，该子胎儿超声图像的标准切面包括但不限于头臀长测量切面、双顶径测量切面、NT测量切面、颜面正中切面、额上颌夹角测量切面、肱骨长测量切面、股骨长测量切面、双上肢切面、双下肢切面、胎心率测量切面、三尖瓣频谱测量切面、静脉导管频谱测量切面、胃泡切面、膀胱切面、双脐动脉切面、性别显示切面、鼻骨测量切面、肠管内径测量切面、尺桡骨长径切面、大脑中动脉切面、胆囊脐静脉切面、动脉导管弓切面、肺静脉入左心房切面、腹围切面、肛门切面、肱骨长径切面、宫颈测量切面、股骨长径切面、冠状静脉窦切面、脊髓圆锥定位切面、脊柱冠状切面、脊柱切面、脊柱切面、胫-腓骨长径切面、NF测量切面、膀胱+双脐动脉切面、脐动脉频谱测量切面、脐带插入胎盘切面、脐带绕颈切面、脐带入口切面、三血管气管切面、上下腔静脉入右心房切面、上牙槽突横切面、肾长径测量切面、食管-气管切面、手切面、双顶径切面、双肾横切面、四腔心切面、胎盘切面、头颅正中切面、头颅经阴道切面、小脑切面、性别显示切面、胸腹切面、颜面部表面呈像切面、眼距测量切面、羊水切面、右室流出道切面、主动脉弓切面足切面、左侧无名静脉汇入右上腔切面、左室流出道切面、左右肺动脉分叉切面、耳朵切面。
本发明实施例中，每帧子胎儿超声图像的目标特征均包括至少一个方位的标准切面，其中，该方位包括冠状方位、矢状方位以及水平方位。例如：腹部特征包括水平腹部特征、矢状腹部特征、冠状腹部特征；腹围切面包括水平腹围切面、矢状腹围切面、冠状腹围切面；胃泡结构特征包括水平胃泡结构特征、矢状胃泡结构特征、冠状胃泡结构特征。
本发明实施例中，每个目标章节包括连续若干帧子胎儿超声图像，且每个目标章节包括的所有子胎儿超声图像互不相同，以及每个目标章节包括的所有子胎儿超声图像的总数量等于胎儿超声图像包括的所有子胎儿超声图像的总数量。
本发明实施例中，对胎儿超声图像执行章节划分可以实时划分，即一边将胎儿超声图像的连续多帧子胎儿超声图像依次输入上述参数确定模型进行分析，并获取该参数确定模型依次输出的分析结果，作为每帧子胎儿超声图像的参数的同时，对所有子胎儿超声图像进行章节划分。对胎儿超声图像执行章节划分也可以为在获取完毕所有子胎儿超声图像的参数之后，再对所有子胎儿超声图像进行章节划分，本发明实施例不做限定。
本发明实施例中，进一步可选的，上述胎儿超声图像对应至少一种目标类别，该目标类别包括特征类别或者切面类别，每个目标类别对应的目标特征的数量大于等于1。其中，当目标类别为特征类别时，目标特征包括结构特征或者部位特征；当目标类别为切面类别时，目标特征包括标准切面；每个目标类别均对应至少一帧子胎儿超声图像，且每个目标类别对应的所有子胎儿超声图像均互不相同且所有目标类别对应的所有子胎儿超声图像组成胎儿超声图像。
可见，本发明实施例还能够自动将胎儿超声图像划分为不同类别的章节，并将计算出的每个章节的分值，作为胎儿超声图像的成像分值，能够提高胎儿超声图像的成像分值的获取准确性以及效率，从而有利于提高胎儿超声图像的成像质量的确定精准性以及可靠性，实现胎儿超声图像的成像质量的精确且快速控制，进而有利于获取到高质量的胎儿超声图像，有利于提高胎儿的生长发育情况的确定精准性以及可靠性。
在该可选的实施方式中，进一步可选的，对胎儿超声图像执行章节划分操作，得到至少一个目标章节，可以包括：
确定胎儿超声图像包括的每个目标类别对应的起始帧子胎儿超声图像所在的位置以及该目标类别对应的终止帧子胎儿超声图像所在的位置；
将每个目标类别对应的起始帧子胎儿超声图像、该目标类别对应的终止帧子胎儿超声图像以及确定出的该目标类别对应的起始帧子胎儿超声图像所在的位置与该目标类别对应的终止帧子胎儿超声图像所在的位置之间的所有子胎儿超声图像，确定为每个目标类别对应的目标章节。
本发明实施例中，每个目标类别对应的起始帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在胎儿超声图像中首次出现的位置，每个目标类别对应的终止帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在胎儿超声图像中最后一次出现的位置或者在胎儿超声图像中从包含该目标类别的目标特征的起始帧子胎儿超声图像开始连续出现第预设数量帧子胎儿超声图像所在的位置，有利于提高每个目标类别对应的终止帧胎儿超声图像所在位置的确定准确性，从而提高每个目标类别的目标章节的确定准确性，从而提高目标章节的分值的确定精准性。需要说明的时，每个目标类别对应的终止帧子胎儿超声图像所在的位置为在胎儿超声图像中从包含该目标类别的目标特征的起始帧子胎儿超声图像开始连续出现第预设数量帧子胎儿超声图像所在的位置的情况适用于实时对胎儿超声图像进行划分章节的情况。
举例说明，目标类别为胃泡结构特征类别，胎儿超声图像由100帧子胎儿超声图像组成，胃泡结构特征在第5帧子胎儿超声图像所在的位置首次出现，在第50帧子胎儿超声图像所在的位置最后一次出现，则该胃泡结构特征类别对应的起始帧子胎儿超声图像所在的位置为第5帧子胎儿超声图像所在的位置，终止帧子胎儿超声图像所在的位置为第50帧子胎儿超声图像所在的位置，或胃泡结构特征类别对应的预设数量帧为30帧，则从第5帧子胎儿超声图像所在的 位置开始连续出现第34帧子胎儿超声图像所在的位置为胃泡结构特征类别对应的终止帧子胎儿超声图像所在的位置。
又举例说明，目标类别为腹围标准切面，胎儿超声图像由100帧子胎儿超声图像组成，腹围标准切面类别在第5帧子胎儿超声图像所在的位置首次出现，在第50帧子胎儿超声图像所在的位置最后一次出现，则该腹围标准切面类别对应的起始帧子胎儿超声图像所在的位置为第5帧子胎儿超声图像所在的位置，终止帧胎儿超声图像所在的位置为第50帧胎儿超声图像所在的位置，或腹围标准切面类别对应的预设数量帧为30帧，则从第5帧子胎儿超声图像所在的位置开始连续出现第34帧子胎儿超声图像所在的位置为腹围标准切面类别对应的终止帧子胎儿超声图像所在的位置。
本发明实施例中，每个目标类别对应的目标章节包括的所有子胎儿超声图像至少包括包含该目标类别的目标特征的胎儿超声图像，且每个目标类别对应的目标章节包括该目标类别的目标特征的数量大于等于1。进一步的，每个目标类别对应的目标章节包括的所有子胎儿超声图像还包括不包含该目标类别的目标特征的子胎儿超声图像。例如：胃泡结构特征类别对应的章节包括50帧胎儿超声图像，其中，包含胃泡结构特征类别对应的子胎儿超声图像有45帧，其余5帧子胎儿超声图像包括的结构特征为手指结构特征。
可见，本发明实施例还能够通过自动先确定每类部位特征或者结构特征或标准切面的起始帧胎儿超声图像所在的位置和终止帧胎儿超声图像所在的位置，能够实现每类部位特征或结构特征或标准切面对应章节的自动确定，有利于提高每个章节的确定效率和准确性，从而有利于提高每个章节的分值的计算效率以及准确性。
该可选的实施方式中，又进一步可选的，根据每个目标章节包括的每帧子胎儿超声图像的目标特征的参数，计算该目标章节的分值，包括：
当每帧子胎儿超声图像的目标特征为该子胎儿超声图像的部位特征时，计算每个目标章节包括的每帧子胎儿超声图像的部位特征的部位特征分值之和，作为该目标章节的分值；
当每帧子胎儿超声图像的目标特征为该子胎儿超声图像的结构特征时，根据每个目标章节包括的每帧子胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该目标章节的分值；
当每帧子胎儿超声图像的目标特征为该子胎儿超声图像的标准切面时，计算每个目标章节包括的每帧子胎儿超声图像的标准切面的切面分值之和，作为该目标章节的分值。
本发明实施例中，当每帧子胎儿超声图像的目标特征为该子胎儿超声图像的结构特征时，每个特征类别对应的目标章节的分值的计算公式为：
Figure PCTCN2021096823-appb-000001
H i＝P i×Q i×O i；
式中，S 1为每个特征类别对应的目标章节的分值，H i为在该目标章节内该特征类别对应的第i个结构特征的结构特征分值，M为在该目标章节内该特征类别对应的结构特征的总数量，P i为在该目标章节内该特征类别对应的第i个结构特征的置信度，Q i为在该目标章节内该特征类别对应的第i个结构特征的位置概率，O i为在该目标章节内该特征类别对应的第i个结构特征的权重值。
本发明实施例中，每个目标章节包括的每帧子胎儿超声图像的结构特征的参数还包括该结构特征所在的部位的概率，此时，该目标章节内该特征类别对应的第i个结构特征的结构特征分值的计算公式为：
H i＝P i×Q i×O i×C i；
式中，C i为在该目标章节内该特征类别对应的第i个结构特征所在的部位的概率。这样结构特征的参数越多，有利于提高结构特征的机构特征分值计算准确性，从而有利于进一步提高该结构特征对应的章节的分值的精准性，从而进一步提高胎儿超声图像的成像质量的确定准确性。
该可选的实施方式中，当每帧子胎儿超声图像的目标特征为该子胎儿超声图像的标准切面时，此时，每个切面类别对应的目标章节的计算公式为：
Figure PCTCN2021096823-appb-000002
式中，S 2为每个切面类别对应的目标章节的分值，M为在该目标章节内该切面类别对应的标准切面的总数量，K j为在该目标章节内该切面类别对应的第j个标准切面的切面分值。
该可选的实施方式中，当每帧子胎儿超声图像的目标特征为该子胎儿超声图像的部位特征时，此时，每个部位类别对应的目标章节的计算公式为：
Figure PCTCN2021096823-appb-000003
式中，S 3为每个部位类别对应的目标章节的分值，M为在该目标章节内该部位类别对应的部位特征的总数量，W l为在该目标章节内该部位类别对应的第l个部位特征的部位特征分值。
本发明实施例中，进一步可选的，由于每帧子胎儿超声图像的目标特征均包括水平方位、矢状方位以及冠状方位中的一种或多种特征，因此，每个目标章节的分值可以包括对应目标类别的目标特征的三个方位中的至少一个方位对应的分值的平均值。举例来说，章节A包括的结构特征为胃泡结构特征类别对应的胃泡结构特征，则计算章节A中每个胃泡结构特征的水平方位、矢状方位以及冠状方位三个方位对应的结构特征分值，并计算所有胃泡结构特征的三个方位对应的结构特征分值的均值作为章节A的分值。部位特征、标准切面的多个方位的分值的平均值计算方式请参照结构特征的多个方位的分值的平均值相同，在此不再赘述。这样通过计算结构特征、部位特征、标准切面的多个方位的分值的平均值作为章节的分值，能够进一步提高章节的分值的计算准确性，从而进一步提高胎儿超声图像的成像质量的确定精准性，进而有利于获取到高质量的胎儿超声图像。
可见，本发明实施例还能够通过分别计算每类结构特征对应的结构特征分值或每类切面对应的切面分值或每类部位特征对应的部位特征分值，不仅能够实现章节的分值的确定，还能够丰富章节的分值的确定方式，提高章节的分值的确定准确性以及可靠性；以及通过结构特征分值得到的章节的分值、部位特征分值得到的章节的分值与通过切面分值得到的章节的分值共同确定胎儿超声图像的成像质量，能够进一步提高胎儿超声图像的成像质量的确定准确性以及可靠性，从而进一步有利于获取到更高质量的胎儿超声图像。
本发明实施例中，由于每个标准切面均包括至少一个结构特征，因此，每个标准切面的切面分值除了可以直接由上述终端设备发送、授权人员输入、切面确定模型输出中的至少一种方式获取之外，还可以基于该标准切面所包含的每个结构特征的结构特征分值计算得到，即基于每类标准切面的每个标准切面所包含的每个结构特征的结构特征分值计算每类标准切面的切面分值，并在基于每个类别标准切面的切面分值计算得到该类别标准切面对应的章节的分值之 后，获取由计算得到的每类标准切面的切面分值得到的章节的分值与直接获取到的该类别标准切面的切面分值得到的章节的分值的平均值，作为该章节的分值。举例来说，章节B对应的目标类别的腹围切面类别，章节B包括5个腹围切面，每个腹围切面的切面分值分别为10、8、9、9.5、8.6，则由腹围切面的切面分值计算得到的章节B的分值为45.1；腹围切面的结构特征包括胃泡结构特征、脐静脉结构特征以及肝脏结构特征，而章节B中每个腹围切面包括的胃泡结构特征对应的结构特征分值14.5、脐静脉结构特征对应的结构特征分值16以及肝脏结构特征对应的结构特征分值15.5，则由结构特征对应的结构特征分值计算得到的章节B的分值为46，取46和45.1的均值45.55，作为章节B的最终分值。这样通过获取不同途径获取到的章节的分值的均值作为该章节的分值，即胎儿超声图像的成像分值，能够进一步提高胎儿超声图像的成像分值的确定精准性，从而进一步提高胎儿超声图像的成像质量的确定准确性。
本发明实施例中，进一步的，由于部位特征包括多个标准切面，标准切面包括多个结构特征，因此，当计算部位特征对应的章节的分值时，可以通过取由多个标准切面的切面分值计算得到章节的分值与部位特征对应的章节的分值的均值作为该章节的最终分值，针对举例说明，请参阅前一例子中的标准切面与该标准切面包括的结构特征之间分值关系的详细说明，在此不再赘述。
在一个可选的实施例中，对胎儿超声图像执行章节划分操作，得到至少一个目标章节之后，该方法还包括：
确定每个目标章节包括的所有子胎儿超声图像的总帧数；
以及，根据每个目标章节包括的每帧子胎儿超声图像的目标特征的参数，计算该目标章节的分值之后，该方法还包括：
将每个目标章节的分值除以该目标章节包括的所有子胎儿超声图像的总帧数，得到该目标章节的目标分值；
将每个目标章节的分值更新为该目标章节的目标分值，并触发执行步骤103。
举例来说，胃泡结构特征类别对应的章节包含的胎儿超声图像的数量为100帧，且该胃泡结构特征类别对应的章节的分值为180分，则将180除以100，得到1.8作为该章节的分值，则将胃泡结构特征类别对应的章节的分值更新为1.8。
可见，该可选的实施例在获取到章节的分值之后，进一步基于章节的分值与该章节的总帧数，得到该章节的新分值，且将胎儿超声图像的成像分值更为该新分值，能够进一步提高胎儿超声图像的成像分值的确定准确性，进而有利于提高胎儿超声图像的成像质量的确定准确性。
本发明实施例中，作为另一种可选的实施方式，根据胎儿超声图像的参数确定胎儿超声图像的成像分值，包括：
当胎儿超声图像的参数为胎儿超声图像的部位特征参数时，胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征分值，确定胎儿超声图像的部位特征分值为该胎儿超声图像的成像分值；和/或，
当胎儿超声图像的参数为胎儿超声图像的结构特征参数时，该胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值；
根据胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为胎儿超声图像的成像分值；和/或，
当胎儿超声图像的参数为胎儿超声图像的特征参数时，该胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，该胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征的类别概率；
根据胎儿超声图像的部位特征的类别概率、该胎儿超声图像的结构特征的 类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为胎儿超声图像的成像分值；和/或，根据胎儿超声图像的部位特征的类别概率以及该胎儿超声图像的结构特征的类别概率，确定胎儿超声图像的标准切面，并根据胎儿超声图像的标准切面内的结构特征的参数，计算胎儿超声图像的标准切面的切面分值，作为胎儿超声图像的成像分值，该胎儿超声图像的结构特征参数包括该胎儿超声图像的标准切面内的结构特征的参数。
可见，本发明实施例还能够通过分别计算该胎儿超声图像的部位特征分值、结构特征分值以及标准切面分值，实现胎儿超声图像的分值的计算，不仅能够丰富胎儿超声图像的分值确定方式，提高胎儿超声图像的成像质量的确定准确性，从而进一步实现胎儿超声图像的成像质量的精确且快速控制。
103、根据上述胎儿超声图像的成像分值确定该胎儿超声图像的成像质量。
本发明实施例中，进一步可选的，保存胎儿超声图像的成像分值，从而有利于根据该成像分值优化成像质量确定服务器，进而进一步有利于获取到高质量的胎儿超声图像。
本发明实施例中，胎儿超声图像的标准切面的结构特征至少包括该标准切面的关键结构特征。进一步的，还包括其他结构特征。当获取到胎儿超声图像的标准切面之后，进一步根据该标准切面包括的结构特征确定该标准切面是正常标准切面或者疑似标准切面。例如：腹围标准切面，胃泡、脐静脉为关键结构特征，肝脏、降主动脉、肋骨、下腔静脉为其他结构特征，如果腹围标准切面包括胃泡、脐静脉关键结构特征，还包括肝脏、降主动脉、肋骨、下腔静脉其他结构特征，则该腹围标准切面为正常标准切面，当腹围标准切面包括胃泡、脐静脉关键结构特征，不包括肝脏、降主动脉、肋骨、下腔静脉中的至少一种结构特征时，确定该腹围标准切面疑似标准切面。
可见，实施图1所描述的胎儿超声图像的成像质量控制的确定方法能够通过根据确定出的胎儿超声图像的成像分值自动确定胎儿超声图像的成像质量，能够快速且准确地确定胎儿超声图像的成像质量，从而实现胎儿超声图像的成像质量的精确且快速控制，进而获取到高质量的胎儿超声图像，有利于获取到准确的胎儿生长发育情况；通过确定出的胎儿超声图像的成像质量，还能够知晓工作人员在检测胎儿超声图像过程中的规范性以及胎儿所需检测的项目是否完全检测完毕。
实施例二
请参阅图2，图2是本发明实施例公开的另一种胎儿超声图像的成像质量控制的确定方法的流程示意图。其中，图2所描述的胎儿超声图像的成像质量控制的确定方法可以应用于成像质量确定服务器(服务设备)中，其中，该成像质量确定服务器可以包括本地成像质量确定服务器或云成像质量确定服务器，本发明实施例不做限定。如图2所示，该胎儿超声图像的成像质量控制的确定方法可以包括以下操作：
201、获取胎儿超声图像的参数，该胎儿超声图像的参数用于确定该胎儿超声图像的成像质量。
202、根据上述胎儿超声图像的参数确定该胎儿超声图像的成像分值。
203、确定上述胎儿超声图像对应的检测结果。
本发明实施例中，该胎儿超声图像对应的检测结果用于确定胎儿超声图像的成像质量，且该胎儿超声图像对应的检测结果包括特征检测结果、生物学径线检测结果以及多普勒血流频谱检测结果中的至少一种，该特征检测结果包括部位特征检测结果、结构特征检测结果、标准切面检测结果中的至少一种，本发明实施例不做限定。
本发明实施例中，特征检测结果用于表示需要检测的特征是否完全检测完 毕，即，需要检测的部位特征、结构特征以及标准切面中的至少一种是否检测完毕。
在一个可选的实施例中，当执行完毕步骤203之后，该方法还可以包括：
根据上述胎儿超声图像对应的检测结果是否满足确定出的检测要求；
当判断出结果为是时，触发执行步骤204；
当判断出结果为否时，生成胎儿超声图像的检测提示，并输出该检测提示。
该可选的实施例中，该检测提示用于表示存在未检测到特征(例如：未检测到肱骨长径切面等)、未检测到胎儿超声图像的生物学径线以及未检测到胎儿超声图像的多普勒血流频谱中的至少一种。且该检测提示用于提示授权人员对未检测到的内容进行检测。
该可选的实施例中，可选的，输出检测提示之后，可以触发执行步骤204。
可见，该可选的实施例在得到胎儿超声图像的检测检测，先判断该检测结果是否满足检测要求，若满足，则执行后续胎儿超声图像的成像质量的确定操作，若不满足，则输出胎儿超声图像的检测提示，能够提示授权人员存在未检测到的内容以及对授权人员的操作行为进行监督，便于授权人员对未检测到的内容进行检测，从而有利于获取到准确的胎儿超生图像的成像分值，进而提高胎儿超生图像的成像质量的确定准确性，进而实现胎儿超声图像的成像质量的精确且快速控制。
可见，本发明实施例通过获取胎儿超声图像的检测结果，比如：是否对需要检测的所有标准切面进行检测，并将胎儿超声图像的成像分值结合该检测结果共同确定该胎儿超声图像的成像质量，能够进一步提高胎儿超声图像的成像质量的确定准确性，从而进一步实现胎儿超声图像的成像质量的精确且快速控制，进而进一步获取到高质量的胎儿超声图像，有利于获取到准确的胎儿生长发育情况。
在另一个可选的实施例中，该方法还包括：
在获取到胎儿超声图像的目标特征之后，检测胎儿超声图像的目标特征中是否存在异常特征，当检测到存在异常特征时，确定该异常特征所在的位置章节为异常特征位置，其中该位置包括章节、标准切面以及部位中的至少一种。
该可选的实施例中，进一步可选的，当确定出异常特征位置后，向授权人员输出该异常特征位置。
举例来说，当检测到侧脑室异常(例如：脑积水等)时，则确定该侧脑室所在的章节为异常章节，并向授权人员输出该异常特征章节。
该可选的实施例中，进一步可选的，当存在多种异常特征时，从多种异常特征对应的异常特征位置中选择最优异常特征位置，例如：最优异常特征章节。进一步的，当出现异常特征时，该异常特征位置对应的分值乘以确定出的系数(例如：10)，得到该异常特征位置对应的分值，并获取最高分值异常特征位置作为最优异常特征位置。
该可选的实施例中，胎儿超声图像的目标特征的相关描述请参阅实施例一中的相关内容的详细描述，在此不再赘述。
可见，该可选的实施例通过在检测到胎儿超声图像的目标特征存在异常特征之后，确定异常特征所在的位置，例如：最优异常特征章节，并向授权人员输出该位置，便于授权人员快速确认并定位到异常特征。
204、根据上述胎儿超声图像的成像分值以及该胎儿超声图像对应的特征结果确定该胎儿超声图像的成像质量。
本发明实施例中，针对步骤201、步骤202以及步骤204的其他描述请参阅实施例一中针对步骤101-步骤103的详细描述，本发明实施例不再赘述。
可见，实施图2所描述的胎儿超声图像的成像质量控制的确定方法能够通过根据确定出的胎儿超声图像的成像分值自动确定胎儿超声图像的成像质量， 能够快速且准确地确定胎儿超声图像的成像质量，从而实现胎儿超声图像的成像质量的精确且快速控制，进而获取到高质量的胎儿超声图像，有利于获取到准确的胎儿生长发育情况；通过确定出的胎儿超声图像的成像质量，还能够知晓工作人员在检测胎儿超声图像过程中的规范性以及胎儿所需检测的项目是否完全检测完毕。此外，还能够自动将胎儿超声图像的成像分值结合检测结果共同确定该胎儿超声图像的成像质量，能够进一步提高胎儿超声图像的成像质量控制的确定准确性，从而进一步实现胎儿超声图像的成像质量的精确且快速控制。
实施例三
本发明实施例公开了一种胎儿超声图像的成像分值的确定方法。其中，该确定方法可以应用于成像质量确定服务器中，其中，该成像质量确定服务器可以包括本地成像质量确定服务器或云成像质量确定服务器，本发明实施例不做限定。其中，该胎儿超声图像的成像分值的确定方法可以包括以下操作：
步骤一、对胎儿超声图像执行章节划分操作，得到至少一个目标章节。
本发明实施例中，胎儿超声图像由连续多帧子胎儿超声图像组成。
本发明实施例中，每个目标章节包括连续若干帧子胎儿超声图像，且每个目标章节包括的所有子胎儿超声图像互不相同，以及每个目标章节包括的所有子胎儿超声图像的总数量等于胎儿超声图像包括的所有子胎儿超声图像的总数量。
步骤二、根据每个目标章节包括的每帧子胎儿超声图像的目标特征的参数，计算该目标章节的分值。
本发明实施例中，每帧子胎儿超声图像的目标特征包括该子胎儿超声图像的部位特征、结构特征以及标准切面中的至少一种。
步骤三、确定所有目标章节的分值为胎儿超声图像的成像分值。
需要说明的是，针对步骤一至步骤三的其他相关描述请参阅实施例一以及实施例二的详细描述，本发明实施例不再赘述。
可见，实施该胎儿超声图像的成像分值的确定方法能够自动将胎儿超声图像划分为不同类别的章节，并将计算出的每个章节的分值，作为胎儿超声图像的成像分值，能够提高胎儿超声图像的成像分值的获取准确性以及效率，从而有利于提高胎儿超声图像的成像质量的确定精准性以及可靠性，实现胎儿超声图像的成像质量的精确且快速控制，进而有利于获取到高质量的胎儿超声图像，有利于提高胎儿的生长发育情况的确定精准性以及可靠性。
实施例四
请参阅图3，图3是本发明实施例公开的一种胎儿超声图像的成像质量控制的确定装置的结构示意图。其中，图3所描述的胎儿超声图像的成像质量控制的确定装置可以应用于成像质量确定服务器(服务设备)中，其中，该成像质量确定服务器可以包括本地成像质量确定服务器或云成像质量确定服务器，本发明实施例不做限定。如图3所示，该胎儿超声图像的成像质量控制的确定装置可以包括获取模块301、第一确定模块302以及第二确定模块303，其中：
获取模块301，用于获取胎儿超声图像的参数，该胎儿超声图像的参数用于确定胎儿超声图像的成像质量。
第一确定模块302，用于根据胎儿超声图像的参数确定该胎儿超声图像的成像分值。
第二确定模块303，用于根据胎儿超声图像的成像分值确定该胎儿超声图像的成像质量。
可见，实施图3所描述的胎儿超声图像的成像质量控制的确定装置能够通过根据确定出的胎儿超声图像的成像分值自动确定胎儿超声图像的成像质量，能够快速且准确地确定胎儿超声图像的成像质量，从而实现胎儿超声图像的成 像质量的精确且快速控制，进而获取到高质量的胎儿超声图像，有利于获取到准确的胎儿生长发育情况；通过确定出的胎儿超声图像的成像质量，还能够知晓工作人员在检测胎儿超声图像过程中的规范性以及胎儿所需检测的项目是否完全检测完毕。
在一个可选的实施例中，获取模块301获取胎儿超声图像的参数的方式具体为：
将胎儿超声图像输入确定出的参数确定模型中进行分析，并获取该参数确定模型输出的分析结果，作为该胎儿超声图像的参数，该参数确定模型包括特征确定模型和/或切面确定模型，其中，当该参数确定模型为特征确定模型时，该胎儿超声图像的参数包括该胎儿超声图像的特征参数，该胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数和/或结构特征参数；当该参数确定模型为切面确定模型时，该胎儿超声图像的参数包括该胎儿超声图像的切面参数，该胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值；和/或，
接收确定出的终端设备发送的和/或授权人员输入的针对胎儿超声图像的参数，作为胎儿超声图像的参数，该胎儿超声图像的参数包括该胎儿超声图像的特征参数和/或切面参数，该胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数和/或结构特征参数，该胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值。
可见，实施图3所描述的确定装置还能够通过将胎儿超声图像输入参数确定模型进行分析，能够快速实现胎儿超声图像的参数自动获取，无需人工参与，能够提高胎儿超声图像的参数获取准确性以及可靠性，从而提高胎儿超声图像的成像分值的确定精准性以及效率；以及通过终端设备发送和/或授权人员输入的方式获取胎儿超声图像的参数，能够丰富胎儿超声图像的参数的获取方式。
在另一个可选的实施例中，上述胎儿超声图像由多帧连续子胎儿超声图像组成。以及，如图4所示，第一确定模块302可以包括划分子模块3021、计算子模块3022以及确定子模块3023，其中：
划分子模块3021，用于对胎儿超声图像执行章节划分操作，得到至少一个目标章节，每个目标章节包括若干连续帧子胎儿超声图像，且每个目标章节包括的所有子胎儿超声图像互不相同，以及每个目标章节包括的所有子胎儿超声图像的总数量等于胎儿超声图像包括的所有子胎儿超声图像的总数量。
计算子模块3022，用于根据每个目标章节包括的每帧子胎儿超声图像的目标特征的参数，计算每个目标章节的分值，每帧子胎儿超声图像的目标特征包括该子胎儿超声图像的部位特征、结构特征以及标准切面中的至少一种。
确定子模块3023，用于确定所有目标章节的分值为胎儿超声图像的成像分值。
该可选的实施例中，该胎儿超声图像对应至少一种目标类别，该目标类别包括特征类别或者切面类别，每个目标类别对应的目标特征的数量大于等于1。其中，当目标类别为特征类别时，目标特征包括结构特征或者部位特征；当目标类别为切面类别时，目标特征包括标准切面。其中，每个目标类别均对应至少一帧子胎儿超声图像，且每个目标类别对应的所有子胎儿超声图像均互不相同且所有目标类别对应的所有子胎儿超声图像组成胎儿超声图像。
可见，实施图4所描述的确定装置能够通过自动将胎儿超声图像划分为不同类别的章节，并将计算出的每个章节的分值，作为胎儿超声图像的成像分值，能够提高胎儿超声图像的成像分值的获取准确性以及效率，从而有利于提高胎儿超声图像的成像质量的确定精准性以及可靠性，进而有利于获取到高质量的胎儿超声图像。
在又一个可选的实施例中，如图4所示，划分子模块3021对胎儿超声图像 执行章节划分操作，得到至少一个目标章节的方式具体为：
确定胎儿超声图像包括的每个目标类别对应的起始帧子胎儿超声图像所在的位置以及该目标类别对应的终止帧子胎儿超声图像所在的位置；
将每个目标类别对应的起始帧子胎儿超声图像、该目标类别对应的终止帧子胎儿超声图像以及确定出的该目标类别对应的起始帧子胎儿超声图像所在的位置与该目标类别对应的终止帧子胎儿超声图像所在的位置之间的所有子胎儿超声图像，确定为每个目标类别对应的目标章节；
其中，每个目标类别对应的起始帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在胎儿超声图像中首次出现的位置，每个目标类别对应的终止帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在胎儿超声图像中最后一次出现的位置或者在胎儿超声图像中从包含该目标类别的目标特征的起始帧子胎儿超声图像开始连续出现第预设数量帧子胎儿超声图像所在的位置。
可见，实施图4所描述的确定装置还能够通过自动先确定每类部位特征或者结构特征或标准切面的起始帧胎儿超声图像所在的位置和终止帧胎儿超声图像所在的位置，能够实现每类部位特征或结构特征或标准切面对应章节的自动确定，有利于提高每个章节的确定效率和准确性，从而有利于提高每个章节的分值的计算效率以及准确性。
在又一个可选的实施例中，如图4所示，计算子模块3022根据每个目标章节包括的每帧子胎儿超声图像的目标特征的参数，计算该目标章节的分值的方式具体为：
当每帧子胎儿超声图像的目标特征为该子胎儿超声图像的部位特征时，计算每个目标章节包括的每帧子胎儿超声图像的部位特征的部位特征分值之和，作为该目标章节的分值；
当每帧子胎儿超声图像的目标特征为该子胎儿超声图像的结构特征时，根据每个目标章节包括的每帧子胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该目标章节的分值；
当每帧子胎儿超声图像的目标特征为该子胎儿超声图像的标准切面时，计算每个目标章节包括的每帧子胎儿超声图像的标准切面的切面分值之和，作为该目标章节的分值。
可见，实施图4所描述的确定装置还能够通过分别计算每类结构特征对应的结构特征分值或每类切面对应的切面分值或每类部位特征对应的部位特征分值，不仅能够实现章节的分值的确定，还能够丰富章节的分值的确定方式，提高章节的分值的确定准确性以及可靠性；以及通过结构特征分值得到的章节的分值、部位特征分值得到的章节的分值与通过切面分值得到的章节的分值共同确定胎儿超声图像的成像质量，能够进一步提高胎儿超声图像的成像质量的确定准确性以及可靠性，从而进一步有利于获取到更高质量的胎儿超声图像。
在又一个可选的实施例中，如图4所示，该装置还包括计算模块304以及更新模块305，其中：
确定子模块3023，还用于在划分子模块3021对胎儿超声图像执行章节划分操作，得到至少一个目标章节之后，确定每个目标章节包括的所有子胎儿超声图像的总帧数；
计算模块304，用于在第一确定模块302根据每个目标章节包括的每帧子胎儿超声图像的目标特征的参数，计算该目标章节的分值之后，将每个目标章节的分值除以该目标章节包括的所有子胎儿超声图像的总帧数，得到该目标章节的目标分值。
更新模块305，用于将每个目标章节的分值更新为该目标章节的目标分值，并触发第二确定模块303执行上述的确定所有目标章节的分值为胎儿超声图像 的成像分值的操作。
该可选的实施例中，在划分子模块3021执行完毕对胎儿超声图像执行章节划分操作，得到至少一个目标章节之后，可以触发确定子模块3023执行上述的确定每个目标章节包括的所有子胎儿超声图像的总帧数的操作。
可见，实施图4所描述的确定装置还能够通过获取到章节的分值之后，进一步基于章节的分值与该章节的总帧数，得到该章节的新分值，且将胎儿超声图像的成像分值更为该新分值，能够进一步提高胎儿超声图像的成像分值的确定准确性，进而有利于提高胎儿超声图像的成像质量的确定准确性。
在又一个可选的实施例中，如图4所示，第一确定模块302根据胎儿超声图像的参数确定胎儿超声图像的成像分值的方式具体为：
当胎儿超声图像的参数为胎儿超声图像的部位特征参数时，该胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征分值，确定胎儿超声图像的部位特征分值为该胎儿超声图像的成像分值；和/或，
当胎儿超声图像的参数为胎儿超声图像的结构特征参数时，胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值；
根据胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为胎儿超声图像的成像分值；和/或，
当胎儿超声图像的参数为胎儿超声图像的特征参数时，该胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，该胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征的类别概率；
根据胎儿超声图像的部位特征的类别概率、该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为胎儿超声图像的成像分值；和/或，根据胎儿超声图像的部位特征的类别概率以及该胎儿超声图像的结构特征的类别概率，确定胎儿超声图像的标准切面，并根据胎儿超声图像的标准切面内的结构特征的参数，计算胎儿超声图像的标准切面的切面分值，作为胎儿超声图像的成像分值，该胎儿超声图像的结构特征参数包括该胎儿超声图像的标准切面内的结构特征的参数。
可见，实施图4所描述的确定装置还能够通过分别计算该胎儿超声图像的部位特征分值、结构特征分值以及标准切面分值，实现胎儿超声图像的分值的计算，不仅能够丰富胎儿超声图像的分值确定方式，提高胎儿超声图像的成像质量的确定准确性，从而进一步实现胎儿超声图像的成像质量的精确且快速控制。
在又一个可选的实施例中，如图4所示，该装置还包括第三确定模块306，其中：
第三确定模块306，用于在第二确定模块302根据胎儿超声图像的成像分值确定胎儿超声图像的成像质量之前，确定胎儿超声图像对应的检测结果，该胎儿超声图像对应的检测结果用于确定胎儿超声图像的成像质量，且该胎儿超声图像对应的检测结果包括特征检测结果、生物学径线检测结果以及多普勒血流频谱检测结果中的至少一种，该特征检测结果包括部位特征检测结果、结构特征检测结果以及标准切面检测结果中的至少一种；
以及，第二确定模块302根据胎儿超声图像的成像分值确定该胎儿超声图像的成像质量的方式就具体为：
根据胎儿超声图像的成像分值以及该胎儿超声图像对应的特征结果确定胎儿超声图像的成像质量。
可见，实施图4所描述的确定装置还能够通过获取胎儿超声图像的检测结果，比如：是否对需要检测的所有标准切面进行检测，并将胎儿超声图像的成像分值结合该检测结果共同确定该胎儿超声图像的成像质量，能够进一步提高胎儿超声图像的成像质量的确定准确性，从而进一步实现胎儿超声图像的成像质量的精确且快速控制，进而进一步获取到高质量的胎儿超声图像，有利于获取到准确的胎儿生长发育情况。
实施例五
请参阅图5，图5是本发明实施例公开的又一种胎儿超声图像的成像质量控制的确定装置。其中，图5所描述的胎儿超声图像的成像质量控制的确定方法可以应用于成像质量确定服务器(服务设备)中，其中，该成像质量确定服务器可以包括本地成像质量确定服务器或云成像质量确定服务器，本发明实施例不做限定。如图5所示，该胎儿超声图像的成像质量控制的确定装置可以包括：
存储有可执行程序代码的存储器501；
与存储器501耦合的处理器502；
进一步的，还可以包括与处理器502耦合的输入接口503以及输出接口504；
其中，处理器502调用存储器501中存储的可执行程序代码，用于执行实施例一或实施例二所描述的胎儿超声图像的成像质量控制的确定方法中部分或者全部的步骤。
实施例六
本发明实施例公开了一种计算机可读存储介质，其存储用于电子数据交换的计算机程序，其中，该计算机程序使得计算机执行实施例一或实施例二所描述的胎儿超声图像的成像质量控制的确定方法中部分或者全部的步骤。
实施例七
本发明实施例公开了一种计算机程序产品，该计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，且该计算机程序可操作来使计算机执行实施例一或实施例二所描述的胎儿超声图像的成像质量控制的确定方法中部分或者全部的步骤。
以上所描述的装置实施例仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施例的具体描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中,存储介质包括只读存储器(Read-Only Memory，ROM)、随机存储器(Random Access Memory，RAM)、可编程只读存储器(Programmable Read-only Memory，PROM)、可擦除可编程只读存储器(Erasable Programmable Read Only Memory，EPROM)、一次可编程只读存储器(One-time Programmable Read-Only Memory，OTPROM)、电子抹除式可复写只读存储器(Electrically-Erasable Programmable Read-Only Memory，EEPROM)、只读光盘(Compact Disc Read-Only Memory，CD-ROM)或其他光盘存储器、磁盘存储器、磁带存储器、或者能够用于携带或存储数据的计算机可读的任何其他介质。
最后应说明的是：本发明实施例公开的一种胎儿超声图像的成像质量控制的确定方法及装置所揭露的仅为本发明较佳实施例而已，仅用于说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解；其依然可以对前述各项实施例所记载的技术 方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或替换，并不使相应的技术方案的本质脱离本发明各项实施例技术方案的精神和范围。

Claims (10)

  1. 一种胎儿超声图像的成像质量控制的确定方法，其特征在于，所述方法包括：
    获取胎儿超声图像的参数，所述胎儿超声图像的参数用于确定所述胎儿超声图像的成像质量；
    根据所述胎儿超声图像的参数确定所述胎儿超声图像的成像分值，并根据所述胎儿超声图像的成像分值确定所述胎儿超声图像的成像质量。
  2. 根据权利要求1所述的胎儿超声图像的成像质量控制的确定方法，其特征在于，所述获取胎儿超声图像的参数，包括：
    将胎儿超声图像输入确定出的参数确定模型中进行分析，并获取所述参数确定模型输出的分析结果，作为所述胎儿超声图像的参数，所述参数确定模型包括特征确定模型和/或切面确定模型，其中，当所述参数确定模型为所述特征确定模型时，所述胎儿超声图像的参数包括该胎儿超声图像的特征参数，所述胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数和/或结构特征参数；当所述参数确定模型为所述切面确定模型时，所述胎儿超声图像的参数包括该胎儿超声图像的切面参数，所述胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值；和/或，
    接收确定出的终端设备发送的和/或授权人员输入的针对胎儿超声图像的参数，作为胎儿超声图像的参数，所述胎儿超声图像的参数包括该胎儿超声图像的特征参数和/或切面参数，所述胎儿超声图像的特征参数包括该胎儿超声图像的部位特征参数和/或结构特征参数，所述胎儿超声图像的切面参数包括该胎儿超声图像的标准切面的切面分值。
  3. 根据权利要求1或2所述的胎儿超声图像的成像质量控制的确定方法，其特征在于，所述胎儿超声图像由连续多帧子胎儿超声图像组成；
    其中，所述根据所述胎儿超声图像的参数确定所述胎儿超声图像的成像分值，包括：
    对所述胎儿超声图像执行章节划分操作，得到至少一个目标章节，每个所述目标章节包括连续若干帧所述子胎儿超声图像，且每个所述目标章节包括的所有所述子胎儿超声图像互不相同，以及每个所述目标章节包括的所有所述子胎儿超声图像的总数量等于所述胎儿超声图像包括的所有所述子胎儿超声图像的总数量；
    根据每个所述目标章节包括的每帧所述子胎儿超声图像的目标特征的参数，计算该目标章节的分值，每帧所述子胎儿超声图像的目标特征包括该子胎儿超声图像的部位特征、结构特征以及标准切面中的至少一种；
    确定所有所述目标章节的分值为所述胎儿超声图像的成像分值。
  4. 根据权利要求3所述的胎儿超声图像的成像质量控制的确定方法，其特征在于，所述胎儿超声图像对应至少一种目标类别，所述目标类别包括特征类别或者切面类别，每个所述目标类别对应的目标特征的数量大于等于1；
    其中，当所述目标类别为所述特征类别时，所述目标特征包括结构特征或者部位特征；当所述目标类别为所述切面类别时，所述目标特征包括标准切面；
    每个所述目标类别均对应至少一帧所述子胎儿超声图像，且每个所述目标类别对应的所有所述子胎儿超声图像均互不相同且所有所述目标类别对应的所有所述子胎儿超声图像组成所述胎儿超声图像。
  5. 根据权利要求4所述的胎儿超声图像的成像质量控制的确定方法，其特征在于，所述对所述胎儿超声图像执行章节划分操作，得到至少一个目标章节，包括：
    确定所述胎儿超声图像包括的每个所述目标类别对应的起始帧子胎儿超声图像所在的位置以及该目标类别对应的终止帧子胎儿超声图像所在的位置；
    将每个所述目标类别对应的起始帧子胎儿超声图像、该目标类别对应的终止帧子胎儿超声图像以及确定出的该目标类别对应的起始帧子胎儿超声图像所在的位置与该目标类别对应的终止帧子胎儿超声图像所在的位置之间的所有子胎儿超声图像，确定为每个所述目标类别对应的目标章节；
    其中，每个所述目标类别对应的起始帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在所述胎儿超声图像中首次出现的位置，每个所述目标类别对应的终止帧子胎儿超声图像所在的位置为包含该目标类别的目标特征的子胎儿超声图像在所述胎儿超声图像中最后一次出现的位置或者在所述胎儿超声图像中从包含该目标类别的目标特征的起始帧子胎儿超声图像开始连续出现第预设数量帧子胎儿超声图像所在的位置。
  6. 根据权利要求3-5任一项所述的胎儿超声图像的成像质量控制的确定方法，其特征在于，所述根据每个所述目标章节包括的每帧所述子胎儿超声图像的目标特征的参数，计算该目标章节的分值，包括：
    当每帧所述子胎儿超声图像的目标特征为该子胎儿超声图像的部位特征时，计算每个所述目标章节包括的每帧所述子胎儿超声图像的部位特征的部位特征分值之和，作为该目标章节的分值；
    当每帧所述子胎儿超声图像的目标特征为该子胎儿超声图像的结构特征时，根据每个所述目标章节包括的每帧所述子胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该目标章节的分值；
    当每帧所述子胎儿超声图像的目标特征为该子胎儿超声图像的标准切面时，计算每个所述目标章节包括的每帧所述子胎儿超声图像的标准切面的切面分值之和，作为该目标章节的分值。
  7. 根据权利要求3-6任一项所述的胎儿超声图像的成像质量控制的确定方法，其特征在于，所述对所述胎儿超声图像执行章节划分操作，得到至少一个目标章节之后，所述方法还包括：
    确定每个所述目标章节包括的所有所述子胎儿超声图像的总帧数；
    以及，所述根据每个所述目标章节包括的每帧所述子胎儿超声图像的目标特征的参数，计算该目标章节的分值之后，所述方法还包括：
    将每个所述目标章节的分值除以该目标章节包括的所有所述子胎儿超声图像的总帧数，得到该目标章节的目标分值；
    将每个所述目标章节的分值更新为该目标章节的目标分值，并触发执行所述的确定所有所述目标章节的分值为所述胎儿超声图像的成像分值的操作。
  8. 根据权利要求2所述的胎儿超声图像的成像质量控制的确定方法，所述根据所述胎儿超声图像的参数确定所述胎儿超声图像的成像分值，包括：
    当所述胎儿超声图像的参数为所述胎儿超声图像的部位特征参数时，所述胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征分值，确定所述胎儿超声图像的部位特征分值为该胎儿超声图像的成像分值；和/或，
    当所述胎儿超声图像的参数为所述胎儿超声图像的结构特征参数时，所述胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值；
    根据所述胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为所述胎儿超声图像的成像分值；和/或，
    当所述胎儿超声图像的参数为所述胎儿超声图像的特征参数时，所述胎儿超声图像的结构特征参数包括该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，所述胎儿超声图像的部位特征参数包括该胎儿超声图像的部位特征的类别概率；
    根据所述胎儿超声图像的部位特征的类别概率、该胎儿超声图像的结构特征的类别概率、该结构特征的位置概率以及该结构特征的权重值，计算该结构特征的结构特征分值，并确定该结构特征分值，作为所述胎儿超声图像的成像分值；和/或，根据所述胎儿超声图像的部位特征的类别概率以及该胎儿超声图像的结构特征的类别概率，确定所述胎儿超声图像的标准切面，并根据所述胎儿超声图像的标准切面内的结构特征的参数，计算所述胎儿超声图像的标准切面的切面分值，作为所述胎儿超声图像的成像分值，所述胎儿超声图像的结构特征参数包括该胎儿超声图像的标准切面内的结构特征的参数。
  9. 根据权利要求1-8任一项所述的胎儿超声图像的成像质量控制的确定方法，其特征在于，所述根据所述胎儿超声图像的成像分值确定所述胎儿超声图像的成像质量之前，所述方法还包括：
    确定所述胎儿超声图像对应的检测结果，所述胎儿超声图像对应的检测结果用于确定所述胎儿超声图像的成像质量，且所述胎儿超声图像对应的检测结果包括特征检测结果、生物学径线检测结果以及多普勒血流频谱检测结果中的至少一种，所述特征检测结果包括部位特征检测结果、结构特征检测结果以及标准切面检测结果中的至少一种；
    以及，所述根据所述胎儿超声图像的成像分值确定所述胎儿超声图像的成像质量，包括：
    根据所述胎儿超声图像的成像分值以及所述胎儿超声图像对应的特征结果确定所述胎儿超声图像的成像质量。
  10. 一种胎儿超声图像的成像质量控制的确定装置，其特征在于，所述装置包括：
    获取模块，用于获取胎儿超声图像的参数，所述胎儿超声图像的参数用于确定所述胎儿超声图像的成像质量；
    第一确定模块，用于根据所述胎儿超声图像的参数确定所述胎儿超声图像的成像分值；
    第二确定模块，用于根据所述胎儿超声图像的成像分值确定所述胎儿超声图像的成像质量。
PCT/CN2021/096823 2020-09-24 2021-05-28 一种胎儿超声图像的成像质量控制的确定方法及装置 WO2022062460A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2023518459A JP2023542961A (ja) 2020-09-24 2021-05-28 胎児超音波画像の結像品質制御の決定方法及び装置
GB2305211.1A GB2614643B (en) 2020-09-24 2021-05-28 Method and Apparatus for Identification of Imaging Quality of a series of Fetal Ultrasound Images
KR1020237009518A KR20230052967A (ko) 2020-09-24 2021-05-28 태아 초음파 영상의 이미징 품질 제어의 결정 방법 및 장치
US18/126,363 US20230233177A1 (en) 2020-09-24 2023-03-24 Method and Apparatus for Identification of Imaging Quality of Fetal Ultrasound Images

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011015212.9 2020-09-24
CN202011015212.9A CN112155601B (zh) 2020-09-24 2020-09-24 一种胎儿超声图像的成像质量控制的确定方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/126,363 Continuation US20230233177A1 (en) 2020-09-24 2023-03-24 Method and Apparatus for Identification of Imaging Quality of Fetal Ultrasound Images

Publications (1)

Publication Number Publication Date
WO2022062460A1 true WO2022062460A1 (zh) 2022-03-31

Family

ID=73863681

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/096823 WO2022062460A1 (zh) 2020-09-24 2021-05-28 一种胎儿超声图像的成像质量控制的确定方法及装置

Country Status (6)

Country Link
US (1) US20230233177A1 (zh)
JP (1) JP2023542961A (zh)
KR (1) KR20230052967A (zh)
CN (1) CN112155601B (zh)
GB (1) GB2614643B (zh)
WO (1) WO2022062460A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114758287A (zh) * 2022-06-15 2022-07-15 深圳瀚维智能医疗科技有限公司 超声数据处理方法、装置及计算机可读存储介质
CN115082487A (zh) * 2022-08-23 2022-09-20 深圳华声医疗技术股份有限公司 超声图像切面质量评价方法、装置、超声设备及存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112155601B (zh) * 2020-09-24 2022-12-30 广州爱孕记信息科技有限公司 一种胎儿超声图像的成像质量控制的确定方法及装置
CN112155603B (zh) * 2020-09-24 2023-06-09 广州爱孕记信息科技有限公司 胎儿结构特征的权重值确定方法及装置
CN115018839B (zh) * 2022-08-08 2022-11-04 浙江华诺康科技有限公司 用于医学检查的图像识别方法、装置和电子装置

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3545850A1 (en) * 2018-03-27 2019-10-02 Samsung Medison Co., Ltd. Ultrasound imaging apparatus for predicting fetal growth rate and method of operating the same
CN110464380A (zh) * 2019-09-12 2019-11-19 李肯立 一种对中晚孕期胎儿的超声切面图像进行质量控制的方法
CN110604592A (zh) * 2019-03-04 2019-12-24 北京大学第三医院 一种髋关节的成像方法以及髋关节成像系统
CN110613480A (zh) * 2019-01-14 2019-12-27 广州爱孕记信息科技有限公司 基于深度学习的胎儿超声动态影像检测方法及系统
CN111223092A (zh) * 2020-02-28 2020-06-02 长沙大端信息科技有限公司 胎儿超声切面图像自动质控系统及检测方法
US20200202551A1 (en) * 2017-05-11 2020-06-25 Koninklijke Philips N.V. Fetal development monitoring
CN111462060A (zh) * 2020-03-24 2020-07-28 湖南大学 胎儿超声图像中标准切面图像的检测方法和装置
CN112070119A (zh) * 2020-08-11 2020-12-11 长沙大端信息科技有限公司 超声切面图像质量控制方法、装置和计算机设备
CN112155601A (zh) * 2020-09-24 2021-01-01 广州爱孕记信息科技有限公司 一种胎儿超声图像的成像质量控制的确定方法及装置
CN112215806A (zh) * 2020-09-24 2021-01-12 广州爱孕记信息科技有限公司 胎儿超声影像的检测结果的输出控制方法、装置及系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8891881B2 (en) * 2012-01-25 2014-11-18 General Electric Company System and method for identifying an optimal image frame for ultrasound imaging
CN108460765B (zh) * 2018-04-09 2021-03-30 北京无线电计量测试研究所 一种虹膜图像质量检测方法
CN110895802B (zh) * 2018-08-23 2023-09-01 杭州海康威视数字技术股份有限公司 一种图像处理方法及装置
WO2020126712A1 (en) * 2018-12-17 2020-06-25 Koninklijke Philips N.V. Systems and methods for frame indexing and image review

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200202551A1 (en) * 2017-05-11 2020-06-25 Koninklijke Philips N.V. Fetal development monitoring
EP3545850A1 (en) * 2018-03-27 2019-10-02 Samsung Medison Co., Ltd. Ultrasound imaging apparatus for predicting fetal growth rate and method of operating the same
CN110613480A (zh) * 2019-01-14 2019-12-27 广州爱孕记信息科技有限公司 基于深度学习的胎儿超声动态影像检测方法及系统
CN110604592A (zh) * 2019-03-04 2019-12-24 北京大学第三医院 一种髋关节的成像方法以及髋关节成像系统
CN110464380A (zh) * 2019-09-12 2019-11-19 李肯立 一种对中晚孕期胎儿的超声切面图像进行质量控制的方法
CN111223092A (zh) * 2020-02-28 2020-06-02 长沙大端信息科技有限公司 胎儿超声切面图像自动质控系统及检测方法
CN111462060A (zh) * 2020-03-24 2020-07-28 湖南大学 胎儿超声图像中标准切面图像的检测方法和装置
CN112070119A (zh) * 2020-08-11 2020-12-11 长沙大端信息科技有限公司 超声切面图像质量控制方法、装置和计算机设备
CN112155601A (zh) * 2020-09-24 2021-01-01 广州爱孕记信息科技有限公司 一种胎儿超声图像的成像质量控制的确定方法及装置
CN112215806A (zh) * 2020-09-24 2021-01-12 广州爱孕记信息科技有限公司 胎儿超声影像的检测结果的输出控制方法、装置及系统

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114758287A (zh) * 2022-06-15 2022-07-15 深圳瀚维智能医疗科技有限公司 超声数据处理方法、装置及计算机可读存储介质
CN115082487A (zh) * 2022-08-23 2022-09-20 深圳华声医疗技术股份有限公司 超声图像切面质量评价方法、装置、超声设备及存储介质
CN115082487B (zh) * 2022-08-23 2022-12-13 深圳华声医疗技术股份有限公司 超声图像切面质量评价方法、装置、超声设备及存储介质

Also Published As

Publication number Publication date
CN112155601A (zh) 2021-01-01
US20230233177A1 (en) 2023-07-27
CN112155601B (zh) 2022-12-30
JP2023542961A (ja) 2023-10-12
GB2614643B (en) 2024-01-17
KR20230052967A (ko) 2023-04-20
GB202305211D0 (en) 2023-05-24
GB2614643A (en) 2023-07-12

Similar Documents

Publication Publication Date Title
WO2022062460A1 (zh) 一种胎儿超声图像的成像质量控制的确定方法及装置
WO2022062458A1 (zh) 一种胎儿最优标准切面的确定方法及装置
WO2019062835A1 (zh) 超声图像处理方法及系统、超声诊断设备
WO2022062461A1 (zh) 基于超声动态图像的胎儿切面的确定方法及装置
US8010175B2 (en) Patient-specific coronary territory mapping
CN109924956B (zh) 一种颅内动脉瘤图像的形态学参数的测量方法及装置
WO2021190656A1 (zh) 眼底图像黄斑中心定位方法及装置、服务器、存储介质
US9198603B2 (en) Device, method and program for searching for the shortest path in a tubular structure
WO2022062456A1 (zh) 胎儿超声影像的检测结果的输出控制方法、装置及系统
Miao et al. Placenta maps: in utero placental health assessment of the human fetus
CN111275755B (zh) 基于人工智能的二尖瓣瓣口面积检测方法、系统和设备
US10997720B2 (en) Medical image classification method and related device
WO2022109905A1 (zh) 调节血管轮廓及中心线的方法及存储介质
WO2022062459A1 (zh) 一种胎儿结构特征的自动测量方法及装置
CN115565667A (zh) Cto介入治疗成功率的预测方法、装置、设备及介质
Van de Putte et al. Point-of-care ultrasound in pregnancy: gastric, airway, neuraxial, cardiorespiratory
CN113487665B (zh) 一种管腔缺口的测量方法、装置、设备和介质
WO2022062455A1 (zh) 基于胎儿超声图像的胎儿严重畸形检测方法及装置
US20090161926A1 (en) Semi-automatic Segmentation of Cardiac Ultrasound Images using a Dynamic Model of the Left Ventricle
WO2022062457A1 (zh) 胎儿结构特征的权重值确定方法及装置
CN114119645B (zh) 一种图像分割质量的确定方法、系统、设备及介质
WO2021092889A1 (zh) 基于造影图像的流速的筛选方法、装置、系统和存储介质
US20070061168A1 (en) Method and apparatus for evaluating variations between health care service providers
Domínguez-Gallardo et al. Gestational Age-Adjusted Reference Ranges for Fetal Left Ventricle Longitudinal Strain by Automated Cardiac Motion Quantification between 24 and 37 Weeks’ Gestation
CN103995989B (zh) 用于末梢脉管树的边界条件的特定患者的自动调整

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21870847

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023518459

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20237009518

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 202305211

Country of ref document: GB

Kind code of ref document: A

Free format text: PCT FILING DATE = 20210528

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21870847

Country of ref document: EP

Kind code of ref document: A1