WO2019062835A1 - 超声图像处理方法及系统、超声诊断设备 - Google Patents

超声图像处理方法及系统、超声诊断设备 Download PDF

Info

Publication number
WO2019062835A1
WO2019062835A1 PCT/CN2018/108262 CN2018108262W WO2019062835A1 WO 2019062835 A1 WO2019062835 A1 WO 2019062835A1 CN 2018108262 W CN2018108262 W CN 2018108262W WO 2019062835 A1 WO2019062835 A1 WO 2019062835A1
Authority
WO
WIPO (PCT)
Prior art keywords
standard
image
target object
cut surface
ultrasound
Prior art date
Application number
PCT/CN2018/108262
Other languages
English (en)
French (fr)
Inventor
李萍
唐艳红
廖静秋
许龙
Original Assignee
深圳开立生物医疗科技股份有限公司
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 深圳开立生物医疗科技股份有限公司 filed Critical 深圳开立生物医疗科技股份有限公司
Publication of WO2019062835A1 publication Critical patent/WO2019062835A1/zh

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
    • 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
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/13—Tomography
    • A61B8/14—Echo-tomography
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis

Definitions

  • the present invention relates to the field of ultrasonic diagnostic equipment, and in particular, to an ultrasonic image processing method and system, and an ultrasonic diagnostic apparatus.
  • the existing scanning process is roughly as follows: after scanning a series of ultrasonic images, first freeze the image, then play back the movie by sliding the trackball, manually find the required standard cut surface, then unfreeze the image, and then perform real-time scanning. Get the next standard cut surface. Repeat the above steps until all standard sections have been checked. The operation steps are cumbersome and inefficient.
  • an object of the present invention is to provide an ultrasonic image processing method and system, and an ultrasonic diagnostic apparatus.
  • the invention realizes the direct identification and acquisition of the standard cutting surface directly in the real-time ultrasonic scanning state, without manual freezing and thawing operation, and improves the accuracy and efficiency of the ultrasonic scanning.
  • the technical solution adopted by the present invention is: an ultrasonic image processing method, comprising the following steps:
  • the ultrasound image is saved.
  • the step of acquiring the standard aspect of the target object according to the scanning instruction includes:
  • the image corresponding to the maximum matching degree is taken as a standard slice of the target object.
  • the step of matching the at least one image with the standard aspect in the standard facet database, and obtaining the matching degree includes:
  • the matching degree is calculated according to the matching of the image feature information with the preset image feature information in the standard facet database, and the standard facet database stores a plurality of standard facet information and corresponding preset image feature information.
  • step of calculating the matching degree includes:
  • a ratio of the distance to a preset threshold is calculated, and the ratio is used as a matching degree.
  • a standard aspect database is built using machine learning methods based on the standard aspect data.
  • the method further includes:
  • the standard cut surface is measured according to a preset measurement requirement, and the measurement result is obtained.
  • an ultrasonic image processing apparatus comprising:
  • An instruction receiving unit configured to receive a scan instruction for acquiring an ultrasound image of the target object in an ultrasound real-time scanning state
  • An image acquisition unit configured to acquire a standard aspect of the target object according to the scan instruction, and use the standard cut surface as an ultrasound image of the target object;
  • a storage unit for storing the ultrasound image.
  • the step of acquiring the standard aspect of the target object according to the scanning instruction includes:
  • the image corresponding to the maximum matching degree is taken as a standard slice of the target object.
  • the ultrasound image processing apparatus further includes:
  • the measuring unit is configured to measure the standard cut surface according to a preset measurement requirement, and obtain a measurement result.
  • an ultrasonic diagnostic apparatus comprising:
  • a user input component configured to receive a scan instruction for acquiring an ultrasound image of the target object in an ultrasound real-time scan state
  • a processor configured to acquire a standard aspect of the target object according to the scan instruction, and use the standard cut surface as an ultrasound image of the target object;
  • a memory for storing the ultrasound image.
  • the invention acquires the standard cut surface of the target object according to the scan instruction in the real-time ultrasonic scanning state, and uses the obtained standard cut surface as the ultrasonic image of the target object, thereby realizing direct and rapid identification and obtaining the standard cut surface without manual freezing and thawing operation Improve the accuracy and efficiency of the scan.
  • FIG. 1 is a flow chart of an ultrasonic image processing method according to a first embodiment of the present invention
  • FIG. 2 is a flowchart of a method for acquiring a standard aspect of a target object according to a scan instruction according to the first embodiment of the present invention
  • FIG. 4 is a flowchart of a method for calculating a matching degree according to a first embodiment of the present invention
  • FIG. 5 is a flowchart of an ultrasonic image processing method according to a second embodiment of the present invention.
  • FIG. 6 is a schematic structural diagram of an ultrasonic image processing apparatus according to a third embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of an ultrasonic image processing apparatus according to a fourth embodiment of the present invention.
  • Fig. 8 is a schematic structural view of an ultrasonic diagnostic apparatus according to a fifth embodiment of the present invention.
  • FIG. 1 is an ultrasonic image according to a first embodiment of the present invention.
  • Processing method flow chart an ultrasonic image processing method, comprising the following steps:
  • the target object may be a tissue organ to be examined, such as a fetus, a thyroid gland, a breast, a liver, or the like.
  • the scanning instructions may be scanning items in different stages of pregnancy, such as the sagittal section of the cervical canal, the horizontal cross section of the thalamus, and the cross-sectional scanning of the cerebellum. It may also be a scanning item of other tissues and organs, and is not specifically limited herein.
  • the ultrasound image (standard section) of the target object is saved.
  • it can be stored according to the correspondence between the inspector information, the target object, the scan instruction, and the ultrasonic image, and a complete inspector file is created to subsequently invoke the query.
  • the examinee information includes basic information of the user, such as name, age, and the like.
  • the invention acquires the standard cut surface of the target object according to the scan instruction in the real-time ultrasonic scanning state, and uses the obtained standard cut surface as the ultrasonic image of the target object, thereby realizing direct and rapid identification and obtaining the standard cut surface without freezing and thawing operation, Improve the efficiency and accuracy of ultrasound scanning.
  • FIG. 2 is a flowchart of a method for acquiring a standard aspect of a target object according to a scan instruction according to the first embodiment of the present invention, and the step of acquiring a standard aspect of the target object according to the scan instruction includes:
  • the method of the present embodiment in the real-time ultrasonic scanning state, at least one ultrasound image of the target object is acquired according to the scanning instruction.
  • the number of acquired ultrasound images can be freely set.
  • the image is The number can be 10 pieces.
  • the at least one ultrasonic image obtained as described above is processed and matched with a standard cut surface in a pre-stored standard cut surface database to obtain a matching degree. Specifically, taking an ultrasound image of 10 target objects as an example, each ultrasound image is matched with a standard slice in a pre-stored standard slice database to obtain a corresponding matching degree.
  • the image corresponding to the maximum matching degree is used as a standard aspect of the target object.
  • the above matching degrees are sorted to obtain the maximum matching degree, and the ultrasonic image with the largest matching degree is used as the standard aspect of the target object.
  • FIG. 3 is a flowchart of a method in step 202 of the first embodiment of the present invention, and step 202 includes:
  • the feature extraction uses HOG feature extraction
  • the Histogram of Oriented Gradient (HOG) feature is a feature descriptor used for object detection in computer vision and image processing. It consists of calculating and statistic the gradient direction histogram of the local area of the image.
  • HOG Histogram of Oriented Gradient
  • the ultrasound image is divided into small connected regions, which are called cell units, and an image gradient is calculated for each cell unit;
  • the derivation operation can not only capture contours, human figures and some texture information, but also further weaken the influence of illumination.
  • the gradient of the pixel points (x, y) in the ultrasound image is:
  • G X (x, y), G y (x, y), and H (x, y) respectively represent a horizontal direction gradient, a vertical direction gradient, and a pixel value at a pixel point (x, y) in the ultrasonic image.
  • a gradient direction histogram is constructed for each cell unit in order to provide a code for the local image area while maintaining a weak sensitivity to the pose and appearance of the human object in the image.
  • the cell units are combined into a large block, and the gradient histogram is normalized within the block;
  • the gradient amplitude varies widely due to changes in local illumination and changes in background and foreground contrast. It is therefore necessary to normalize the gradient magnitude, in particular to combine the individual cell units into large, spatially connected intervals (blocks). Normalization can further compress lighting, shadows, and edges.
  • the HOG feature is collected according to the normalized gradient histogram
  • All overlapping blocks in the detection window are collected for HOG features and combined into a final image feature vector, ie image feature information of the ultrasound image.
  • the standard facet database stores a plurality of standard facets information and corresponding preset image feature information.
  • a standard cut surface database is established by using a machine learning method.
  • the standard cut surface database stores standard cut surface information of different tissue organs and corresponding preset image feature information.
  • the image feature information of the standard cut surface of the different tissue organs is obtained by using the method for acquiring the image feature information of the ultrasonic image, that is, the preset image feature information in the standard cut surface database, that is, the preset image feature vector.
  • the standard aspect information in the standard facet database includes the name of the standard facet.
  • the names of the standard section of the obstetric ultrasound include the sagittal section of the cervical canal, the transverse section of the thalamus, the horizontal section of the cerebellum, the sagittal section of the spine, the four-chamber view, the fetal heart rate map (Doppler), and the upper abdominal cross section ( AC), umbilical cord abdominal wall entrance abdominal cross section, bladder horizontal cross section, double kidney cross section, femur long axis (FL) section.
  • some obstetric ultrasound standard cuts need to be measured, while some do not need, for example, the sagittal section of the cervical canal does not need to measure the cut surface, and the transverse cross section of the thalamus needs to be measured.
  • the feature image is extracted to obtain image feature information, and combined with the preset image feature information in the standard facet database, thereby determining whether the ultrasound image is a standard slice; realizing the standard slice in the real-time ultrasonic scan state Quick identification, improve the speed and accuracy of ultrasonic standard cut surface recognition, very convenient and fast.
  • FIG. 4 is a flowchart of a method for calculating a matching degree according to the first embodiment of the present invention, and the step of calculating the matching degree includes:
  • the method for calculating the distance between the image feature information and the preset image feature information in the standard face database includes, but is not limited to, calculating an Euclidean distance, a histogram intersection distance, or an angle cosine distance between the two;
  • the Euclidean distance between the calculated image feature vector and the preset image feature vector in the standard facet database is selected for data processing.
  • their Euclidean distance calculation formula is as follows:
  • d(A, B) is the Euclidean distance between point A and point B (points A and B are points in point sets X and Y, respectively), and X i and Y i are points A and B, respectively.
  • the value at the i position, N is the number of elements in the point set X and Y.
  • the image feature vector of the ultrasound image is a point in the three-dimensional space; correspondingly, the preset image feature vector in the standard facet database is a preset point in the three-dimensional space.
  • the Euclidean distance between the image feature vector of the ultrasound image and the preset image feature vector is calculated using the calculation formula of the Euclidean distance.
  • other distance calculation methods are also available, such as a histogram intersection distance or an angle cosine distance, which will not be described here.
  • the ratio of the distance calculated by the above step to the preset value may be used as the matching degree.
  • a second embodiment of the present invention describes an ultrasonic image processing method.
  • the ultrasonic image processing method of this embodiment includes the following steps, as shown in FIG. 5, which is a flowchart of the ultrasonic image processing method according to the second embodiment of the present invention:
  • the present embodiment is further obtained on the basis of the first embodiment of the present invention.
  • the ultrasonic image processing method according to the first embodiment of the present invention obtains a standard slice
  • the standard slice is measured according to a preset measurement requirement to obtain a measurement. result. Specifically, it is judged whether the standard cut surface needs to be measured according to the provisions of the international standard; if the judgment result is YES, the standard cut surface is measured and the measurement result is stored.
  • the measurement method of the ultrasonic image is a conventional method using the ultrasonic image measurement, and will not be described again here.
  • the obstetric ultrasound standard section as an example, taking the horizontal cross section of the thalamus as an example, this standard section needs to be measured, and the measurement results include the double top diameter and the head circumference.
  • the standard cut surface to be measured is measured to assist the user in processing and analyzing the ultrasonic image.
  • the present invention also outputs standard cut surface (ultrasound image) and/or corresponding standard cut surface information and/or storage result prompt information and/or measurement result to help the user directly obtain related information, and store the result prompt information. Indicates whether the user's standard cut surface is stored successfully. Specifically, the above information is displayed and outputted, and the above information may also be output to the user through voice announcement.
  • FIG. 6 is a schematic structural diagram of an ultrasonic image processing apparatus according to a third embodiment of the present invention.
  • the ultrasonic image processing apparatus includes an instruction receiving unit 601, an image acquisition unit 602, and a storage unit 603.
  • the instruction receiving unit 601 is configured to receive a scan instruction for acquiring an ultrasound image of the target object in an ultrasound real-time scanning state.
  • the image obtaining unit 602 is configured to acquire a standard cut surface of the target object according to the scan instruction, and use the standard cut surface as the ultrasonic image of the target object.
  • the storage unit 603 is configured to save an ultrasound image.
  • the invention acquires the standard cut surface of the target object according to the scan instruction in the real-time ultrasonic scanning state, and uses the obtained standard cut surface as the ultrasonic image of the target object, thereby realizing direct and rapid identification and obtaining the standard cut surface without freezing and thawing operation, Improve the efficiency and accuracy of ultrasound scanning.
  • the image acquisition unit 602 includes an ultrasound image acquisition module, a matching degree acquisition module, and a standard aspect acquisition module.
  • an ultrasound image acquisition module configured to acquire at least one image of the target object according to the scan instruction.
  • the matching degree obtaining module is configured to match at least one image with a standard cut surface in a pre-stored standard cut surface database to obtain a matching degree.
  • the standard facet acquisition module is used to use the image corresponding to the maximum matching degree as the standard face of the target object.
  • the standard face acquisition module compares the above matching degrees to obtain the maximum matching degree, and uses the ultrasonic image with the largest matching degree as the standard aspect of the target object.
  • the matching degree obtaining module includes an image feature information acquiring module and a matching degree calculating module.
  • the image feature information acquiring module is configured to perform feature extraction on each image to obtain image feature information.
  • the matching degree calculation module is configured to match the image feature information with the preset image feature information in the standard facet database to calculate the matching degree, and the standard facet database stores a plurality of standard facet information and corresponding preset image feature information.
  • the matching degree calculation module includes a distance calculation sub-module and a matching degree calculation sub-module.
  • a distance calculation submodule configured to calculate a distance between the image feature information and the preset image feature information in the standard facet database
  • the matching degree calculation sub-module is configured to calculate a ratio of the distance to the preset threshold, and use the ratio as the matching degree.
  • the ratio of the calculated distance to the preset value may be used as the matching degree.
  • FIG. 7 is a schematic structural diagram of an ultrasonic image processing apparatus according to a fourth embodiment of the present invention.
  • the ultrasonic image processing apparatus includes an instruction receiving unit 701, an image acquiring unit 702, a storage unit 703, and a measuring unit 704.
  • the instruction receiving unit 701 is configured to receive a scan instruction for acquiring an ultrasound image of the target object in an ultrasound real-time scanning state
  • the image obtaining unit 702 is configured to acquire a standard aspect of the target object according to the scan instruction, and use the standard cut surface as the ultrasound image of the target object;
  • a storage unit 703, configured to save an ultrasound image
  • the measuring unit 704 is configured to measure the standard slice according to the preset measurement requirement, and obtain the measurement result.
  • the present embodiment is further obtained on the basis of the third embodiment of the present invention.
  • the measuring unit 704 judges according to the provisions of the existing international standards. Whether the standard cut surface needs to be measured; if the judgment result is yes, measure the standard cut surface and store the measurement result.
  • the measurement method of the ultrasonic image is a conventional method using the ultrasonic image measurement, and will not be described again here. Taking the obstetric ultrasound standard section as an example, taking the horizontal cross section of the thalamus as an example, this standard section needs to be measured, and the measurement results include the double top diameter and the head circumference.
  • the standard cut surface to be measured is measured to assist the user in processing and analyzing the ultrasonic image.
  • the present invention further includes an output unit for outputting the standard cut surface (ultrasound image) and/or the corresponding standard cut surface information and/or the storage result prompt information and/or the measurement result to help the user directly obtain the related information;
  • the storage result prompt message is used to prompt the user whether the standard aspect is successfully stored.
  • the output unit may display or output the above information, or output the information to the user by means of voice broadcast.
  • FIG. 8 is a schematic structural diagram of an ultrasonic diagnostic apparatus according to a fifth embodiment of the present invention, and ultrasonic diagnosis.
  • the device includes a user input component 801, a processor 802, and a memory 803.
  • the user input component 801 is configured to receive a scan instruction for acquiring an ultrasound image of the target object in an ultrasound real-time scan state.
  • User input components include user input components such as touch screen displays, trackballs, keyboards, and the like.
  • a scan instruction of the ultrasonic image of the acquisition target object input by the user is received.
  • the target object includes tissues and organs of the fetus, thyroid gland, breast, liver, and the like.
  • the scanning instructions may be scanning items in different stages of pregnancy, such as the sagittal section of the cervical canal, the horizontal cross section of the thalamus, and the cross-sectional scanning of the cerebellum. It may also be a scanning item of other tissues and organs, and is not specifically limited herein.
  • the processor 802 is configured to acquire a standard aspect of the target object according to the scan instruction, and use the standard slice as the ultrasound image of the target object.
  • the processor 802 acquires an ultrasound image of the target object according to the scan instruction received by the user input component 801, and processes the acquired ultrasound image to acquire a standard slice of the target object, and uses the standard slice as the ultrasound image of the target object.
  • the memory 803 is configured to save an ultrasound image.
  • the memory 803 holds an ultrasound image of the target object, that is, a standard slice of the target object. When storing, it can be stored according to the correspondence between the inspector information, the target object, the scan instruction, and the ultrasonic image, and a complete inspector file is created to subsequently invoke the query.
  • the examinee information includes basic information of the user, such as name, age, and the like.
  • the standard cut surface of the target object is also measured according to the preset measurement requirements to obtain the measurement result. Specifically, it is determined according to the provisions of the existing international standards whether the standard cut surface needs to be measured; if the judgment result is yes, the standard cut surface is measured and the measurement result is stored.
  • the measurement method of the ultrasonic image is a conventional method using the ultrasonic image measurement, and will not be described again here. Taking the obstetric ultrasound standard section as an example, taking the horizontal cross section of the thalamus as an example, this standard section needs to be measured, and the measurement results include the double top diameter and the head circumference.
  • the standard cut surface to be measured is measured to assist the user in processing and analyzing the ultrasonic image.
  • the present invention also outputs standard cut surface (ultrasound image) and/or corresponding standard cut surface information and/or storage result prompt information and/or measurement result to help the user directly obtain related information, and store the result prompt information for use. Prompts the user whether the standard facets are successfully stored. Specifically, the above information is displayed and outputted, and the above information may also be output to the user through voice announcement.
  • the user input component 801 can use a button for inputting a scan instruction for acquiring an ultrasound image of the target object;
  • the processor 802 can be a terminal having a computing processing capability such as a computer; and
  • the memory 803 can be a memory chip.
  • the ultrasonic diagnostic apparatus further includes an ultrasonic probe for acquiring an ultrasonic image and a display screen for outputting a standard cut surface (ultrasound image) and/or corresponding standard cut surface information and/or storing result prompt information and/or measurement result Wherein the corresponding standard aspect information and/or stored result prompt information and/or measurement results may be output using a voice output such as a horn.
  • the standard image of the frame is automatically stored in the background, accompanied by a prompt for successful storage (the cutting surface does not need to be done) Measurement, direct storage).
  • This prompt can be a prompt tone, or it can be a prompt character or a prompt picture on the main interface of the ultrasound.
  • the probe After the user receives the prompt, start turning the probe to find the next cut surface, that is, the horizontal cross section of the thalamus (no need to freeze the image, slide the trackball, find the standard cut surface, press the storage as in the prior art) Key, unfreeze the frame image, and then scan the next slice). If the system recognizes that the current scanned image contains the standard horizontal cross section of the thalamus, the frame image is automatically stored, and the system automatically The image is automatically measured and the measurement results include the double top diameter and the head circumference.
  • the real-time scan of the next slice is performed until all the measurement data of the 11 slice images and the partial slices are acquired. Then, the user is prompted to obtain multiple aspects of the obstetric level II examination successfully.
  • the invention acquires the standard cut surface of the target object according to the scan instruction in the real-time ultrasonic scanning state, and uses the obtained standard cut surface as the ultrasonic image of the target object, thereby realizing direct and rapid identification and obtaining the standard cut surface without freezing and thawing operation, Improve the efficiency and accuracy of ultrasound scanning.

Abstract

本发明公开了一种超声图像处理方法，在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；根据扫查指令获取目标对象的标准切面，并将标准切面作为目标对象的超声图像；保存超声图像。还公开了一种超声图像处理装置和超声诊断设备。本发明在超声实时扫查状态下，根据扫查指令获取目标对象的标准切面，并将获取的标准切面作为目标对象的超声图像，实现了直接快速识别和获取标准切面，无需手动冻结和解冻操作，提高扫查的准确度和效率。

Description

超声图像处理方法及系统、超声诊断设备
本申请要求于2017年9月29日提交中国专利局、申请号为201710909446.X、发明名称为“超声图像处理方法及系统、超声诊断设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及超声诊断设备技术领域，尤其涉及一种超声图像处理方法及系统、超声诊断设备。
背景技术
目前优势的医疗资源高度集中于大城市及医学院校附属医院，超声图像扫查需要操作者有规范的操作手法，临床经验丰富，技术门槛较高。然而基层医院资源短缺，另外操作者还存在着手法不规范、临床经验少等诸多问题。
而且现有的扫查流程大致为：在扫查一系列的超声图像后，先冻结图像，然后通过滑动轨迹球等回放电影，人工查找需要的标准切面，之后解冻图像，再进行实时扫查，获取下一个标准切面。重复执行上述步骤，直至所有的标准切面都检查完。操作步骤繁琐，效率低。
发明内容
为了解决上述技术问题，本发明的目的是提供一种超声图像处理方法及系统、超声诊断设备。本发明实现了在超声实时扫查状态下直接快速识别和获取标准切面，无需手动冻结和解冻操作，提高超声扫查的准确度和效率。
本发明所采用的技术方案是：一种超声图像处理方法，包括以下步骤：
在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；
根据所述扫查指令获取所述目标对象的标准切面，并将所述标准切面作为所述目标对象的超声图像；
保存所述超声图像。
进一步地，所述根据所述扫查指令获取所述目标对象的标准切面的步骤包括：
根据所述扫查指令获取所述目标对象的至少一幅图像；
将所述至少一幅图像与预先存储的标准切面数据库中的标准切面进行匹配，获取匹配度；
将最大匹配度对应的图像作为所述目标对象的标准切面。
进一步地，将所述至少一幅图像与标准切面数据库中的标准切面进行匹配，获取匹配度的步骤包括：
对每幅所述图像进行特征提取以获取图像特征信息；
根据所述图像特征信息与标准切面数据库中的预设图像特征信息进行匹配，计算所述匹配度，所述标准切面数据库存储有多种标准切面信息及其对应的预设图像特征信息。
进一步地，所述计算所述匹配度的步骤包括：
计算所述图像特征信息与标准切面数据库中的预设图像特征信息的距离；
计算所述距离与预设阈值的比值，并将所述比值作为匹配度。
进一步地，所述标准切面数据库的建立方法为：
获取多数据中心存储的不同组织器官的标准切面数据；
根据所述标准切面数据利用机器学习方法建立标准切面数据库。
进一步地，所述方法还包括：
根据预设测量需求对所述标准切面进行测量，获取测量结果。
本发明所采用的另一技术方案是：一种超声图像处理装置，包括：
指令接收单元，用于在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；
图像获取单元，用于根据所述扫查指令获取所述目标对象的标准切面，并将所述标准切面作为所述目标对象的超声图像；
存储单元，用于保存所述超声图像。
进一步地，所述根据所述扫查指令获取所述目标对象的标准切面的步骤包括：
根据所述扫查指令获取所述目标对象的至少一幅图像；
将所述至少一幅图像与预先存储的标准切面数据库中的标准切面进行匹配，获取匹配度；
将最大匹配度对应的图像作为所述目标对象的标准切面。
进一步地，所述超声图像处理装置还包括：
测量单元，用于根据预设测量需求对所述标准切面进行测量，获取测量结果。
本发明所采用的另一技术方案是：一种超声诊断设备，包括：
用户输入组件，用于在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；
处理器，用于根据所述扫查指令获取所述目标对象的标准切面，并将所述标准切面作为所述目标对象的超声图像；
存储器，用于保存所述超声图像。
本发明的有益效果是：
本发明在超声实时扫查状态下，根据扫查指令获取目标对象的标准切面，并将获取的标准切面作为目标对象的超声图像，实现了直接快速识别和获取标准切面，无需手动冻结和解冻操作，提高扫查的准确度和效率。
附图说明
下面结合附图对本发明的具体实施方式作进一步说明：
图1是本发明第一实施例所述超声图像处理方法流程图；
图2是本发明第一实施例所述根据扫查指令获取目标对象的标准切面的方法流程图；
图3是本发明第一实施例所述步骤202的方法流程图；
图4是本发明第一实施例所述计算匹配度的方法流程图；
图5是本发明第二实施例所述超声图像处理方法流程图；
图6是本发明第三实施例所述超声图像处理装置的结构示意图；
图7是本发明第四实施例所述超声图像处理装置的结构示意图；
图8是本发明第五实施例所述超声诊断设备的结构示意图。
具体实施方式
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。
实施例一
本发明第一实施例将对一种超声图像处理方法进行详细说明，本实施例所述超声图像处理方法包括以下步骤，如图1所示，图1是本发明第一实施例所述超声图像处理方法流程图，一种超声图像处理方法，包括以下步骤：
101、在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；
在超声实时扫查状态下，接收用户输入的获取目标对象的超声图像的扫查指令。在本实施例中，目标对象可以是待检查的组织器官，如胎儿、甲状腺、乳腺、肝脏等。扫查指令可以是不同孕期的扫查项目，如宫颈管矢状切面、丘脑水平横切面、小脑水平横切面扫查等。还可以是其他组织器官的扫查项目，这里不作具体限定。
102、根据扫查指令获取目标对象的标准切面，并将标准切面作为目标对象的超声图像；
根据接收到的扫查指令获取目标对象的至少一幅图像，并对所获取的至少一幅图像进行处理以获取目标对象的标准切面，并将该标准切面作为目标对象的超声图像。
103、保存超声图像。
根据上述步骤获取的目标对象的超声图像(标准切面)，保存目标对象的超声图像，即目标对象的标准切面。存储时，可以按照被检查者信息、目标对象、扫查指令及其超声图像的对应关系进行存储，建立完整的被检查者档案以便后续调用查询。被检查者信息包括用户的基本信息，如姓名、年龄等。
本发明在超声实时扫查状态下，根据扫查指令获取目标对象的标准切面， 并将获取的标准切面作为目标对象的超声图像，实现了直接快速识别和获取标准切面，无需冻结和解冻操作，提高超声扫查的效率和准确度。
进一步地，参考图2，图2是本发明第一实施例所述根据扫查指令获取目标对象的标准切面的方法流程图，根据扫查指令获取目标对象的标准切面的步骤包括：
201、根据扫查指令获取目标对象的至少一幅图像；
在本实施例方法中，获取实时超声扫查状态下，根据扫查指令获取目标对象的至少一幅超声图像，本实施例中，超声图像的获取数量可以自由设置，本实施例中，图像的数量可以为10幅。
202、将至少一幅图像与预先存储的标准切面数据库中的标准切面进行匹配，获取匹配度；
将上述获取到的至少一幅超声图像进行处理，并与预先存储的标准切面数据库中的标准切面进行匹配以获取匹配度。具体地，以获取10幅目标对象的超声图像为例，对每幅超声图像与预先存储的标准切面数据库中的标准切面进行匹配，获取相应的匹配度。
203、将最大匹配度对应的图像作为目标对象的标准切面。
将上述的匹配度进行排序获取最大的匹配度，并将匹配度最大的超声图像作为目标对象的标准切面。
进一步地，参考图3，图3是本发明第一实施例所述步骤202的方法流程图，步骤202包括：
301、对每幅图像进行特征提取以获取图像特征信息；
本实施例中，特征提取选用HOG特征提取，方向梯度直方图(Histogram of Oriented Gradient,HOG)特征是一种在计算机视觉和图像处理中用来进行物体检测的特征描述子。它通过计算和统计图像局部区域的梯度方向直方图来构成特征。具体的实现方法如下：
首先，将超声图像分成小的连通区域，这种小的连通区域称为细胞单元， 对每个细胞单元计算图像梯度；
计算超声图像横坐标和纵坐标方向的梯度，并据此计算每个像素位置的梯度方向值；求导操作不仅能够捕获轮廓，人影和一些纹理信息，还能进一步弱化光照的影响。超声图像中像素点(x,y)的梯度为：
G y(x，y)＝H(x，y+1)-H(x，y-1)
G X(x，y)＝H(x+1，y)-H(x-1，y)
其中，G X(x，y)、G y(x，y)、H(x，y)分别表示超声图像中像素点(x，y)处的水平方向梯度、垂直方向梯度和像素值。
则像素点(x，y)处的梯度幅值和梯度方向分别为：
Figure PCTCN2018108262-appb-000001
Figure PCTCN2018108262-appb-000002
第二步，为每个细胞单元构建梯度方向直方图，目的是为局部图像区域提供一个编码，同时能够保持对图像中人体对象的姿势和外观的弱敏感性。
第三步，把细胞单元组合成大的块(block)，块内归一化梯度直方图；
由于局部光照的变化以及背景和前景对比度的变化，使得梯度幅值的变化范围非常大。由此需要对梯度幅值做归一化，具体地，把各个细胞单元组合成大的、空间上连通的区间(块)。归一化能够进一步地对光照、阴影和边缘进行压缩。
第四步，根据归一化处理后的梯度直方图收集HOG特征；
将检测窗口中所有重叠的块进行HOG特征的收集，并将它们结合成最终的图像特征向量，即超声图像的图像特征信息。
302、根据图像特征信息与标准切面数据库中的预设图像特征信息进行匹配，计算匹配度，标准切面数据库存储有多种标准切面信息及其对应的预设图像特征信息。
具体地，通过获取多个数据中心存储的不同组织器官的标准切面数据；
根据标准切面数据利用机器学习方法建立标准切面数据库，标准切面数据库中存储有不同组织器官的标准切面信息及其对应的预设图像特征信息。
利用上述获取超声图像的图像特征信息的方法，获取上述不同组织器官的标准切面的图像特征信息，即标准切面数据库中的预设图像特征信息，也即预设图像特征向量。另外，标准切面数据库中的标准切面信息包括标准切面的名称。例如，产科超声标准切面的名称包括宫颈管矢状切面、丘脑水平横切面、小脑水平横切面、脊柱矢状切面、四腔心切面、胎心率图(多普勒)、上腹部横切面(AC)、脐带腹壁入口腹部横切面、膀胱水平横切面、双肾横切面、股骨长轴(FL)切面。进一步地，按照现有的国际标准的规定，一些产科超声标准切面需要进行测量，而一些不需要，例如宫颈管矢状切面不需要对切面进行测量，而丘脑水平横切面需要进行测量。
本实施例中，通过对超声图像进行特征提取以得到图像特征信息，并结合标准切面数据库中的预设图像特征信息，进而判断超声图像是否为标准切面；实现超声实时扫查状态下标准切面的快速识别，提高超声标准切面识别速度和准确度，十分方便快捷。
进一步地，参考图4，图4是本发明第一实施例所述计算匹配度的方法流程图，计算匹配度的步骤包括：
401、计算图像特征信息与标准切面数据库中的预设图像特征信息的距离；
本实施例中，计算图像特征信息与标准切面数据库中的预设图像特征信息的距离的方法包括但不限于计算两者之间的欧氏距离、直方图相交距离或夹角余弦距离；本实施例中，选用计算图像特征向量与标准切面数据库中的预设图像特征向量之间的欧氏距离来进行数据处理。在n维空间中，对于点集x和Y，它们的欧氏距离计算公式如下所示：
Figure PCTCN2018108262-appb-000003
其中，d(A,B)为A点、B点之间的欧氏距离(A点和B点分别是点集X和Y中的一点)，X i、Y i分别为A点、B点在i位置处的值，N为点集X和Y中元素的个数。
本实施例中，超声图像的图像特征向量即三维空间中的一个点；则相应地，标准切面数据库中的预设图像特征向量为三维空间中的一个预设点。利用欧氏距离的计算公式计算超声图像的图像特征向量和预设图像特征向量之间的欧氏距离。当然也可选用其他距离计算方式，例如直方图相交距离或夹角余弦距离，这里不再赘述。
402、计算距离与预设阈值的比值，并将比值作为匹配度。
本实施例中，可以将上述步骤计算得到的距离与预设值的比值作为匹配度。
实施例二
本发明第二实施例阐述了一种超声图像处理方法。本实施例所述超声图像处理方法包括以下步骤，如图5所示，图5是本发明第二实施例所述超声图像处理方法流程图：
501、在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；
502、根据扫查指令获取目标对象的标准切面，并将标准切面作为目标对象的超声图像；
503、保存超声图像；
504、根据预设测量需求对标准切面进行测量，获取测量结果。
本实施例是在本发明第一实施例的基础上进一步得到的，根据本发明第一实施例所描述的超声图像处理方法得到标准切面之后，根据预设测量需求对标准切面进行测量以获取测量结果。具体地，根据国际标准的规定判断标准切面是否需要测量；若判断结果为是，则对标准切面进行测量并存储测量结果。超声图像的测量方法是利用超声图像测量的常规方法，此处不再赘述。以产科超声标准切面为例，以丘脑水平横切面为例，此标准切面需要测量，测量结果包 括双顶径和头围大小。对需要测量的标准切面进行测量，以辅助用户对超声图像进行处理分析。
经过上述处理之后，本发明还将标准切面(超声图像)和/或对应的标准切面信息和/或存储结果提示信息和/或测量结果输出，以帮助用户直接获取相关信息，存储结果提示信息用于提示用户标准切面是否存储成功。具体地，将上述信息进行显示输出，也可以通过语音播报的方式将上述信息输出给用户得知。
实施例三
本发明第三实施例将对一种超声图像处理装置进行详细说明，所述超声图像处理装置的具体结构请参见图6，图6是本发明第三实施例所述超声图像处理装置的结构示意图，超声图像处理装置包括指令接收单元601、图像获取单元602和存储单元603。
指令接收单元601，用于在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令。
图像获取单元602，用于根据扫查指令获取目标对象的标准切面，并将标准切面作为目标对象的超声图像。
存储单元603，用于保存超声图像。
本发明在超声实时扫查状态下，根据扫查指令获取目标对象的标准切面，并将获取的标准切面作为目标对象的超声图像，实现了直接快速识别和获取标准切面，无需冻结和解冻操作，提高超声扫查的效率和准确度。
进一步地，图像获取单元602包括超声图像获取模块、匹配度获取模块和标准切面获取模块。
超声图像获取模块，用于根据扫查指令获取目标对象的至少一幅图像。
匹配度获取模块，用于将至少一幅图像与预先存储的标准切面数据库中的标准切面进行匹配，获取匹配度。
标准切面获取模块，用于将最大匹配度对应的图像作为目标对象的标准切 面。
标准切面获取模块将上述的匹配度进行比较获取最大的匹配度，并将匹配度最大的超声图像作为目标对象的标准切面。
进一步地，所述匹配度获取模块包括图像特征信息获取模块和匹配度计算模块。
图像特征信息获取模块，用于对每幅图像进行特征提取以获取图像特征信息。
匹配度计算模块，用于根据图像特征信息与标准切面数据库中的预设图像特征信息进行匹配，计算匹配度，标准切面数据库存储有多种标准切面信息及其对应的预设图像特征信息。
进一步地，所述匹配度计算模块包括距离计算子模块和匹配度计算子模块。
距离计算子模块，用于计算图像特征信息与标准切面数据库中的预设图像特征信息的距离；
匹配度计算子模块，用于计算距离与预设阈值的比值，并将比值作为匹配度。
本实施例中，可以将上述计算得到的距离与预设值的比值作为匹配度。
实施例四
本发明第三实施例将对一种超声图像处理装置进行详细说明，所述超声图像处理装置的具体结构请参见图7，图7是本发明第四实施例所述超声图像处理装置的结构示意图，超声图像处理装置包括指令接收单元701、图像获取单元702、存储单元703和测量单元704。
指令接收单元701，用于在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；
图像获取单元702，用于根据扫查指令获取目标对象的标准切面，并将标准切面作为目标对象的超声图像；
存储单元703，用于保存超声图像；
测量单元704，用于根据预设测量需求对标准切面进行测量，获取测量结果。
本实施例是在本发明第三实施例的基础上进一步得到的，参考第三实施例中对超声图像处理装置的描述，在得到标准切面后，测量单元704根据现有的国际标准的规定判断标准切面是否需要测量；若判断结果为是，则对标准切面进行测量并存储测量结果。超声图像的测量方法是利用超声图像测量的常规方法，此处不再赘述。以产科超声标准切面为例，以丘脑水平横切面为例，此标准切面需要测量，测量结果包括双顶径和头围大小。对需要测量的标准切面进行测量，以辅助用户对超声图像进行处理分析。
经过上述处理之后，本发明还包括输出单元，用于将标准切面(超声图像)和/或对应的标准切面信息和/或存储结果提示信息和/或测量结果输出以帮助用户直接获取相关信息；存储结果提示信息用于提示用户标准切面是否成功存储。具体地，输出单元可以是将上述信息进行显示输出，也可以通过语音播报的方式将上述信息输出给用户得知。
实施例五
本发明第五实施例将对一种超声诊断设备进行详细说明，所述超声诊断设备的具体结构请参见图8，图8是本发明第五实施例所述超声诊断设备的结构示意图，超声诊断设备包括用户输入组件801、处理器802和存储器803。
用户输入组件801，用于在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令。
用户输入组件包括如触摸显示屏，轨迹球，键盘等的可供用户输入的部件。在超声实时扫查状态下时，接收用户输入的获取目标对象的超声图像的扫查指令。目标对象包括胎儿、甲状腺、乳腺、肝脏等的组织器官。扫查指令可以是不同孕期的扫查项目，如宫颈管矢状切面、丘脑水平横切面、小脑水平横切面扫查等。还可以是其他组织器官的扫查项目，这里不作具体限定。
处理器802，用于根据扫查指令获取目标对象的标准切面，并将标准切面作为目标对象的超声图像。
处理器802根据用户输入组件801接收到的扫查指令获取目标对象的超声图像，并对所获取的超声图像进行处理以获取目标对象的标准切面，并将标准切面作为目标对象的超声图像。
存储器803，用于保存超声图像。
存储器803保存目标对象的超声图像，即目标对象的标准切面。存储时，可以按照被检查者信息、目标对象、扫查指令及其超声图像的对应关系进行存储，建立完整的被检查者档案以便后续调用查询。被检查者信息包括用户的基本信息，如姓名、年龄等。
处理器802得到目标对象的标准切面之后，还根据预设测量需求对标准切面进行测量以获取测量结果。具体地，根据现有的国际标准的规定判断标准切面是否需要测量；若判断结果为是，则对标准切面进行测量并存储测量结果。超声图像的测量方法是利用超声图像测量的常规方法，此处不再赘述。以产科超声标准切面为例，以丘脑水平横切面为例，此标准切面需要测量，测量结果包括双顶径和头围大小。对需要测量的标准切面进行测量，以辅助用户对超声图像进行处理分析。
经过上述处理之后，本发明还将标准切面(超声图像)和/或对应的标准切面信息和/或存储结果提示信息和/或测量结果输出以帮助用户直接获取相关信息，存储结果提示信息用于提示用户标准切面是否成功存储。具体地，将上述信息进行显示输出，也可以通过语音播报的方式将上述信息输出给用户得知。
具体地，用户输入组件801可以采用按键用于输入获取目标对象的超声图像的扫查指令；处理器802可以是计算机等具有计算处理能力的终端；存储器803可以是存储芯片。另外，超声诊断设备还包括用于获取超声图像的超声探头以及显示屏，显示屏用于输出标准切面(超声图像)和/或对应的标准切面 信息和/或存储结果提示信息和/或测量结果，其中，对应的标准切面信息和/或存储结果提示信息和/或测量结果可以使用语音输出例如喇叭进行输出。
实际使用时，以产科II级检查为例，产科中晚孕II级检查时，需要顺序获取多个切面图像，具体包括：宫颈管矢状切面、丘脑水平横切面、小脑水平横切面、脊柱矢状切面、四腔心切面、胎心率图(多普勒)、上腹部横切面(AC)、脐带腹壁入口腹部横切面、膀胱水平横切面、双肾横切面、股骨长轴(FL)切面。下面具体说明本发明的使用过程：用户可以选择凸阵探头，进入二维模式实时扫查。先扫查宫颈管矢状切面，在扫查的过程中，通过移动凸阵探头的位置和凸阵探头的旋转角度，寻找标准的宫颈管矢状切面的二维图像，在用户手动操作实时打图的过程中，若系统识别到当前扫查的图像中包含了标准的宫颈管矢状切面，则自动将这一帧标准图像进行后台存储，并伴随存储成功的提示(该切面上不需要做测量，直接存储)。这个提示可以是一个提示音，也可以是在超声主界面的提示字符或者提示图片。
在用户收到提示之后，开始转动探头，寻找下一个切面，也就是丘脑水平横切面的扫查(不再需要像现有技术一样，先冻结图像，滑动轨迹球，寻找标准切面，按下存储键，解冻该帧图像，然后进行下一个切面的扫查)，若系统识别到当前扫查的图像中包含了标准的丘脑水平横切面，则自动将这一帧图像进行存储，同时系统自动对该图像进行自动测量，测量结果包括双顶径和头围大小。
之后进行下一个切面的实时扫查，直到11个切面图像及部分切面上的测量数据全部获取。则提示用户产科II级检查的多个切面获取成功。
本发明在超声实时扫查状态下，根据扫查指令获取目标对象的标准切面，并将获取的标准切面作为目标对象的超声图像，实现了直接快速识别和获取标准切面，无需冻结和解冻操作，提高超声扫查的效率和准确度。
以上是对本发明的较佳实施进行了具体说明，但本发明创造并不限于所述实施例，熟悉本领域的技术人员在不违背本发明精神的前提下还可做出种种的 等同变形或替换，这些等同的变形或替换均包含在本申请权利要求所限定的范围内。

Claims (10)

  1. 一种超声图像处理方法，其特征在于，包括以下步骤：
    在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；
    根据所述扫查指令获取所述目标对象的标准切面，并将所述标准切面作为所述目标对象的超声图像；
    保存所述超声图像。
  2. 根据权利要求1所述的超声图像处理方法，其特征在于，所述根据所述扫查指令获取所述目标对象的标准切面的步骤包括：
    根据所述扫查指令获取所述目标对象的至少一幅图像；
    将所述至少一幅图像与预先存储的标准切面数据库中的标准切面进行匹配，获取匹配度；
    将最大匹配度对应的图像作为所述目标对象的标准切面。
  3. 根据权利要求2所述的超声图像处理方法，其特征在于，将所述至少一幅图像与标准切面数据库中的标准切面进行匹配，获取匹配度的步骤包括：
    对每幅所述图像进行特征提取以获取图像特征信息；
    根据所述图像特征信息与标准切面数据库中的预设图像特征信息进行匹配，计算所述匹配度，所述标准切面数据库存储有多种标准切面信息及其对应的预设图像特征信息。
  4. 根据权利要求3所述的超声图像处理方法，其特征在于，所述计算所述匹配度的步骤包括：
    计算所述图像特征信息与标准切面数据库中的预设图像特征信息的距离；
    计算所述距离与预设阈值的比值，并将所述比值作为匹配度。
  5. 根据权利要求2至4任一项所述的超声图像处理方法，其特征在于，所述标准切面数据库的建立方法为：
    获取多数据中心存储的不同组织器官的标准切面数据；
    根据所述标准切面数据利用机器学习方法建立标准切面数据库。
  6. 根据权利要求1至4任一项所述的超声图像处理方法，其特征在于，所述方法还包括：
    根据预设测量需求对所述标准切面进行测量，获取测量结果。
  7. 一种超声图像处理装置，其特征在于，包括：
    指令接收单元，用于在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；
    图像获取单元，用于根据所述扫查指令获取所述目标对象的标准切面，并将所述标准切面作为所述目标对象的超声图像；
    存储单元，用于保存所述超声图像。
  8. 根据权利要求7所述的超声图像处理装置，其特征在于，所述根据所述扫查指令获取所述目标对象的标准切面的步骤包括：
    根据所述扫查指令获取所述目标对象的至少一幅图像；
    将所述至少一幅图像与预先存储的标准切面数据库中的标准切面进行匹配，获取匹配度；
    将最大匹配度对应的图像作为所述目标对象的标准切面。
  9. 根据权利要求7或8所述的超声图像处理装置，其特征在于，所述超声图像处理装置还包括：
    测量单元，用于根据预设测量需求对所述标准切面进行测量，获取测量结果。
  10. 一种超声诊断设备，其特征在于，包括：
    用户输入组件，用于在超声实时扫查状态下，接收获取目标对象的超声图像的扫查指令；
    处理器，用于根据所述扫查指令获取所述目标对象的标准切面，并将所述标准切面作为所述目标对象的超声图像；
    存储器，用于保存所述超声图像。
PCT/CN2018/108262 2017-09-29 2018-09-28 超声图像处理方法及系统、超声诊断设备 WO2019062835A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710909446.X 2017-09-29
CN201710909446.XA CN107569257A (zh) 2017-09-29 2017-09-29 超声图像处理方法及系统、超声诊断设备

Publications (1)

Publication Number Publication Date
WO2019062835A1 true WO2019062835A1 (zh) 2019-04-04

Family

ID=61039534

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/108262 WO2019062835A1 (zh) 2017-09-29 2018-09-28 超声图像处理方法及系统、超声诊断设备

Country Status (2)

Country Link
CN (1) CN107569257A (zh)
WO (1) WO2019062835A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110604596A (zh) * 2019-07-30 2019-12-24 深圳迈瑞生物医疗电子股份有限公司 一种髋关节的超声成像方法以及髋关节成像系统
CN112057107A (zh) * 2020-09-14 2020-12-11 无锡祥生医疗科技股份有限公司 超声扫查方法、超声设备及系统

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107569257A (zh) * 2017-09-29 2018-01-12 深圳开立生物医疗科技股份有限公司 超声图像处理方法及系统、超声诊断设备
CN108804547A (zh) * 2018-05-18 2018-11-13 深圳华声医疗技术股份有限公司 超声图像教学方法、装置及计算机可读存储介质
CN108648164A (zh) * 2018-05-18 2018-10-12 深圳华声医疗技术股份有限公司 超声图像优化方法、装置及计算机可读存储介质
CN110507358B (zh) * 2018-05-21 2022-01-11 珠海艾博罗生物技术股份有限公司 一种从超声图像上测量胎儿颈背透明物厚度的图像处理方法及系统
CN109044398B (zh) * 2018-06-07 2021-10-19 深圳华声医疗技术股份有限公司 超声系统成像方法、装置及计算机可读存储介质
CN109223034B (zh) * 2018-08-07 2021-10-26 深圳迈瑞生物医疗电子股份有限公司 超声成像方法及超声成像设备
CN109567860B (zh) * 2018-10-19 2022-03-04 深圳迈瑞生物医疗电子股份有限公司 超声成像方法、设备和存储介质
CN111096765B (zh) * 2018-10-25 2023-06-20 深圳迈瑞生物医疗电子股份有限公司 超声诊断设备及其快速查找未完成切面的方法、存储介质
CN109276275A (zh) * 2018-10-26 2019-01-29 深圳开立生物医疗科技股份有限公司 一种超声图像标准切面提取及测量方法和超声诊断设备
CN109276274A (zh) * 2018-10-26 2019-01-29 深圳开立生物医疗科技股份有限公司 一种超声图像标准切面识别及测量方法和超声诊断设备
CN109464162A (zh) * 2018-12-14 2019-03-15 深圳开立生物医疗科技股份有限公司 一种负荷超声心动图的处理方法及装置
CN109589141A (zh) * 2018-12-28 2019-04-09 深圳开立生物医疗科技股份有限公司 一种超声诊断辅助方法、系统和超声诊断设备
CN109646046A (zh) * 2018-12-29 2019-04-19 深圳开立生物医疗科技股份有限公司 应用于超声医疗设备的智能分析方法及相关设备
CN117618021A (zh) * 2018-12-29 2024-03-01 深圳迈瑞生物医疗电子股份有限公司 超声成像系统及相关的工作流系统和方法
CN110613483B (zh) * 2019-09-09 2022-05-20 南方医科大学 一种基于机器学习检测胎儿颅脑异常的系统
CN110652317B (zh) * 2019-09-24 2020-12-29 深圳度影医疗科技有限公司 一种产前胎儿超声容积图像中标准切面的自动定位方法
CN110675398B (zh) * 2019-10-22 2022-05-17 深圳瀚维智能医疗科技有限公司 乳腺超声筛查方法、装置及计算机设备
CN112773402A (zh) * 2019-11-09 2021-05-11 无锡祥生医疗科技股份有限公司 智能辅助引导方法、超声诊断设备及存储介质
WO2021128310A1 (zh) * 2019-12-27 2021-07-01 深圳迈瑞生物医疗电子股份有限公司 一种超声成像设备以及快速设置超声自动工作流的方法
CN111462059B (zh) * 2020-03-24 2023-09-29 湖南大学 胎儿超声图像智能目标检测的并行处理方法和装置
CN114521914A (zh) * 2020-11-23 2022-05-24 深圳迈瑞生物医疗电子股份有限公司 超声参数测量方法和超声参数测量系统
CN113274056A (zh) * 2021-06-30 2021-08-20 深圳开立生物医疗科技股份有限公司 一种超声扫查方法及相关装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2570081A1 (en) * 2011-09-19 2013-03-20 Samsung Medison Co., Ltd. Method and apparatus for processing image, ultrasound diagnosis apparatus, and medical imaging system
CN104680481A (zh) * 2013-11-28 2015-06-03 深圳迈瑞生物医疗电子股份有限公司 一种超声辅助扫查方法和系统
WO2016131185A1 (zh) * 2015-02-16 2016-08-25 深圳迈瑞生物医疗电子股份有限公司 三维成像数据的显示处理方法和三维超声成像方法及系统
CN106580368A (zh) * 2016-11-26 2017-04-26 汕头市超声仪器研究所有限公司 一种全自动超声波诊断方法
CN107569257A (zh) * 2017-09-29 2018-01-12 深圳开立生物医疗科技股份有限公司 超声图像处理方法及系统、超声诊断设备

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106388865A (zh) * 2016-11-26 2017-02-15 汕头市超声仪器研究所有限公司 一种引导人工采集超声波切面图像的方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2570081A1 (en) * 2011-09-19 2013-03-20 Samsung Medison Co., Ltd. Method and apparatus for processing image, ultrasound diagnosis apparatus, and medical imaging system
CN104680481A (zh) * 2013-11-28 2015-06-03 深圳迈瑞生物医疗电子股份有限公司 一种超声辅助扫查方法和系统
WO2016131185A1 (zh) * 2015-02-16 2016-08-25 深圳迈瑞生物医疗电子股份有限公司 三维成像数据的显示处理方法和三维超声成像方法及系统
CN106580368A (zh) * 2016-11-26 2017-04-26 汕头市超声仪器研究所有限公司 一种全自动超声波诊断方法
CN107569257A (zh) * 2017-09-29 2018-01-12 深圳开立生物医疗科技股份有限公司 超声图像处理方法及系统、超声诊断设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110604596A (zh) * 2019-07-30 2019-12-24 深圳迈瑞生物医疗电子股份有限公司 一种髋关节的超声成像方法以及髋关节成像系统
CN112057107A (zh) * 2020-09-14 2020-12-11 无锡祥生医疗科技股份有限公司 超声扫查方法、超声设备及系统

Also Published As

Publication number Publication date
CN107569257A (zh) 2018-01-12

Similar Documents

Publication Publication Date Title
WO2019062835A1 (zh) 超声图像处理方法及系统、超声诊断设备
US11101033B2 (en) Medical image aided diagnosis method and system combining image recognition and report editing
CN110338844B (zh) 三维成像数据的显示处理方法和三维超声成像方法及系统
US11450003B2 (en) Medical imaging apparatus, image processing apparatus, and image processing method
CN111227864B (zh) 使用超声图像利用计算机视觉进行病灶检测的装置
US11341634B2 (en) Fetal ultrasound image processing
US20110201935A1 (en) 3-d ultrasound imaging
US20060034513A1 (en) View assistance in three-dimensional ultrasound imaging
CN112086197B (zh) 基于超声医学的乳腺结节检测方法及系统
WO2019062843A1 (zh) 超声图像处理方法及系统
Rahmatullah et al. Quality control of fetal ultrasound images: Detection of abdomen anatomical landmarks using adaboost
US20210267570A1 (en) Identifying an optimal image from a number of ultrasound images
WO2018195946A1 (zh) 一种超声图像显示方法、设备及存储介质
WO2018205274A1 (zh) 一种超声设备及其三维超声图像的显示变换方法、系统
US20210077062A1 (en) Device and method for obtaining anatomical measurements from an ultrasound image
CN111462049A (zh) 一种乳腺超声造影视频中病灶区形态自动标注方法
WO2020215485A1 (zh) 胎儿生长参数测量方法、系统及超声设备
Liu et al. Learning-based scan plane identification from fetal head ultrasound images
KR101496198B1 (ko) 3차원 초음파 촬영장치 및 그 운영방법
WO2022099704A1 (zh) 中晚孕期胎儿的超声成像方法和超声成像系统
CN113469942B (zh) 一种ct图像病变检测方法
Shiney et al. A Review on techniques for computer aided diagnosis of soft markers for detection of down syndrome in ultrasound fetal images
JP7299100B2 (ja) 超音波診断装置及び超音波画像処理方法
WO2022134049A1 (zh) 胎儿颅骨的超声成像方法和超声成像系统
CN112991166A (zh) 智能辅助导引方法、超声设备及存储介质

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: 18863001

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16/09/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18863001

Country of ref document: EP

Kind code of ref document: A1