CN110378888B - Physiological period monitoring method and device, ultrasonic equipment and storage medium - Google Patents
Physiological period monitoring method and device, ultrasonic equipment and storage medium Download PDFInfo
- Publication number
- CN110378888B CN110378888B CN201910662447.8A CN201910662447A CN110378888B CN 110378888 B CN110378888 B CN 110378888B CN 201910662447 A CN201910662447 A CN 201910662447A CN 110378888 B CN110378888 B CN 110378888B
- Authority
- CN
- China
- Prior art keywords
- image set
- follicle
- physiological
- historical
- ultrasonic
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Radiology & Medical Imaging (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Physiology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The embodiment of the invention discloses a physiological period monitoring method, a physiological period monitoring device, ultrasonic equipment and a storage medium, wherein the method comprises the following steps: acquiring a current ultrasonic image set of a measured object; wherein the current ultrasound image set comprises ultrasound images of the left and right ovaries and ultrasound images of the uterus; and inputting the current ultrasonic image set into an image classification model trained in advance, and determining the physiological period stage of the measured object. According to the embodiment of the invention, the ultrasound image is input into the image classification model, so that the problem that the physiological period stage needs to be artificially judged is solved, the intelligent monitoring of the physiological period stage is realized, and the accuracy of the monitoring of the physiological period stage is improved.
Description
Technical Field
The embodiment of the invention relates to the field of ultrasonic medical treatment, in particular to a physiological period monitoring method and device, ultrasonic equipment and a storage medium.
Background
Ultrasonic imaging is an imaging method in which a human body is detected by ultrasonic waves emitted from an electroacoustic transducer and an image is formed using ultrasonic reflection echoes. The ultrasonic imaging method is commonly used for judging the position, size and shape of organs, determining the range and physical properties of lesions, and is suitable for diagnosing various organ diseases such as liver, kidney, bladder, uterus, ovary and the like.
The follicle is the basic functional unit of oocyte development and can be broadly divided into primordial, growing and mature follicles. In the prior art, people observe the development condition of follicles in female ovaries in an ultrasonic imaging mode, diagnose the development condition of the follicles, and further predict the ovulation date of women.
The above prior art solutions require an experienced physician to make a diagnosis based on the ultrasound imaging results and determine the current stage of the follicle in the physiological phase. However, the monitoring of the physiological period by the doctor requires the monitored person to go to the hospital regularly to be examined, which causes waste of manpower and material resources, and the subjective factor of the diagnosis result is large, and a large error is easy to exist.
Disclosure of Invention
The embodiment of the invention provides a physiological period monitoring method and device, ultrasonic equipment and a storage medium, so as to realize intelligent monitoring of a physiological period stage and improve the accuracy of the monitoring of the physiological period stage.
In a first aspect, an embodiment of the present invention provides a method for monitoring a physiological period, the method including:
acquiring a current ultrasonic image set of a measured object; wherein the current ultrasound image set comprises ultrasound images of the left and right ovaries and ultrasound images of the uterus;
and inputting the current ultrasonic image set into an image classification model trained in advance, and determining the physiological period stage of the measured object.
In a second aspect, an embodiment of the present invention further provides a device for monitoring a physiological period, the device including:
the ultrasonic image set acquisition module is used for acquiring a current ultrasonic image set of the measured object; wherein the current ultrasound image set comprises ultrasound images of the left and right ovaries and ultrasound images of the uterus;
and the physiological period stage determining module is used for inputting the current ultrasonic image set into an image classification model which is trained in advance and determining the physiological period stage of the measured object.
In a third aspect, an embodiment of the present invention further provides an ultrasound apparatus, where the ultrasound apparatus includes:
one or more processors;
a memory for storing one or more programs;
an ultrasonic transducer for energy conversion;
when executed by the one or more processors, cause the one or more processors to implement any of the physiological period monitoring methods described above.
In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions for performing any of the above-mentioned methods of monitoring a physiological period when executed by a computer processor.
According to the embodiment of the invention, the ultrasound image is input into the image classification model, so that the problem that the physiological period stage needs to be artificially judged is solved, the intelligent monitoring of the physiological period stage is realized, and the accuracy of the monitoring of the physiological period stage is improved.
Drawings
Fig. 1 is a flowchart of a physiological period monitoring method according to an embodiment of the present invention.
Fig. 2 is a flowchart of a physiological period monitoring method according to a second embodiment of the present invention.
Fig. 3 is a schematic diagram of a physiological period monitoring device according to a third embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an ultrasound apparatus according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a physiological period monitoring method according to an embodiment of the present invention, where the present embodiment is applicable to a case where an ultrasound device performs physiological period monitoring, and the method may be executed by an ultrasound imaging device, and specifically includes the following steps:
s110, acquiring a current ultrasonic image set of the measured object; wherein the current ultrasound image set includes ultrasound images of the left and right ovaries and ultrasound images of the uterus.
Medical ultrasound imaging is to scan a human body with ultrasound waves, and then to receive and process ultrasound waves reflected or projected from tissues of the human body to obtain an acoustic image reflecting tissues of organs in the body. Currently, a type a ultrasonic diagnostic apparatus, a type M ultrasonic diagnostic apparatus, a type B ultrasonic diagnostic apparatus, a doppler ultrasonic diagnostic apparatus, and the like are mainly used as ultrasonic apparatuses for medical diagnosis. Correspondingly, in one embodiment, the acquired ultrasound image may be one or more of an a-mode ultrasound image, an M-mode ultrasound image, a B-mode ultrasound image, and a doppler ultrasound image, and the type of the ultrasound image is not limited herein. Among them, B-ultrasonic is the most widely used ultrasonic diagnostic equipment in clinical practice at present, and it uses the principle of brightness modulation to display echo signals in gray scale according to the intensity of signals, so as to obtain tomographic images of tissues, and is mainly used in abdominal examination, thyroid examination, fetal examination and gynecological examination. Specifically, the user can obtain the series of images of the cross section in the body of the tested object by moving the ultrasonic transducer vertically to the body surface and sequentially, and the scanning range covers the uterus and ovary of the tested object. The acquisition mode of the ultrasound image is not limited here.
And S120, inputting the current ultrasonic image set into an image classification model which is trained in advance, and determining the physiological period stage of the object to be tested.
In an embodiment, optionally, a historical ultrasound image set of the historical measured object is obtained, labeling is performed according to a physiological phase stage where the historical ultrasound image set is located, where the historical ultrasound image set includes ultrasound images of the left ovary and the right ovary and ultrasound images of the uterus, the labeled historical ultrasound image set is input into the initial classification model as a training sample, and model parameters of the initial classification model are adjusted according to an output result to obtain the image classification model. The image classification model may adopt one or more classification models of a typical CNN (Convolutional Neural Networks) model, a VGG network model, a ResNet network model, an inclusion network model, and an AlexNet network model.
In one embodiment, optionally, the physiological phase of the historical ultrasound image set is labeled according to the stage and thickness of the endometrium in the uterine ultrasound image, the size of the follicle in the left and right ovarian ultrasound images, the endometrium image, and other information. Specifically, the correspondence relationship between the labeled parameters of the physiological phase is described with reference to table 1, where table 1 is labeled parameter information of the physiological phase provided in the first embodiment of the present invention.
Here, the period from the first day of a physiological period to the day before the next physiological period is referred to as a physiological cycle, and is generally about 28 days. Depending on the tissue changes of the uterus and ovary, the physiological cycle can be divided into three phases: (1) the physiological period corresponds to the 1 st to 5 th days of the physiological cycle. The endometrium is exfoliated by ischemic necrosis, the blood vessel is ruptured and bleeds, and the blood and exfoliated endometrial fragments are discharged through the vagina. At this time, the endometrium is thinned, the thickness is generally less than 3mm, and the follicle develops from the primordial follicle to the growing follicle, and the size is less than 5 mm; (2) after the physiological period (before ovulation), this corresponds to the 5 th to 14 th day of the physiological cycle. Repairing and thickening endometrium, wherein the thickness of endometrium is 3-5 mm. At this time, the follicles developed from growing follicles to mature follicles, and were about 5-22mm in size. Cumulus images can be observed on the intima of the ovary the day before ovulation; (3) before the physiological phase (post-ovulation), this corresponds to day 15-28 of the physiological cycle. The endometrium and gland continue to grow and secrete mucus, which prepares the condition for the planting and development of fertilized eggs, and the thickness of the endometrium is increased to 5-10 mm. At this time, a laceration left after the follicular discharge was observed on the ovarian intima.
The number of follicles in the left and right ovarian ultrasound images is usually more than one. In one embodiment, the follicle may be a main follicle having the largest contour data after comparing contour data of all follicles in the left and right ovaries, and determining whether the contour data of the main follicle satisfies the above condition. Illustratively, the contour data of the follicle includes the major axis dimension, the minor axis dimension, the area, and the volume of the follicle. The selection of the main follicle may be performed by comparing one or more contour data of all follicles. The selection criteria for the primary follicle are not limited herein.
It should be noted that, when performing the physiological phase stage labeling, all parameter information in the left and right ovarian ultrasound images and the uterine ultrasound images need to be considered comprehensively, and the physiological phase stage represented by the historical ultrasound image set needs to be labeled. Table 1 in this embodiment only provides parameter information referred to when labeling a physiological phase, and all embodiments of labeling a physiological phase according to the left and right ovarian ultrasound images and the uterine ultrasound image are within the scope of protection of the embodiments of the present invention.
According to the technical scheme, the ultrasound image is input into the image classification model, so that the problem that the physiological period stage needs to be judged manually is solved, the intelligent monitoring of the physiological period stage is realized, and the accuracy of the monitoring of the physiological period stage is improved.
Example two
Fig. 2 is a flowchart of a physiological period monitoring method according to a second embodiment of the present invention, where the technical solution of this embodiment is further detailed on the basis of the foregoing embodiment, and optionally, after determining the physiological period phase of the subject, the method further includes:
if the physiological period stage is in the post-physiological period (preovulation) stage, carrying out follicle identification on the current ultrasound image set, and determining contour data of at least one follicle, wherein the contour data comprises the major axis size and the minor axis size of the follicle;
and determining ovulation information of the tested object according to the profile data.
The method of the embodiment specifically comprises the following steps:
s210, acquiring a current ultrasonic image set of the measured object; wherein the current ultrasound image set includes ultrasound images of the left and right ovaries and ultrasound images of the uterus.
And S220, inputting the current ultrasonic image set into an image classification model which is trained in advance, and determining the physiological period stage of the object to be tested.
And S230, if the physiological period stage is in the post-physiological period (preovulatory) stage, carrying out follicle identification on the current ultrasound image set, and determining contour data of at least one follicle, wherein the contour data comprises the major axis size and the minor axis size of the follicle.
In one embodiment, the identification of the follicle may be performed by identifying the follicle in the current ultrasound image set, or may be performed by identifying the ultrasound images of the left ovary and the right ovary in the current ultrasound image set. Specifically, after the follicle has developed to a mature follicle, it is expelled from the ovary into the fallopian tube to become an ovum. In the oviduct, the egg combines with the sperm to form a fertilized egg, which migrates from the oviduct to the uterus for implantation. Thus, during the post-physiologic (pre-ovulatory) phase, no follicles are typically identified in the uterine ultrasound image, and thus only the ultrasound images of the left and right ovaries in the current ultrasound image set can be identified.
In one embodiment, optionally, the current ultrasound image set is input into a pre-trained follicle recognition model, a current contour image of at least one follicle is determined, and contour data of at least one follicle is determined according to the current contour image. The follicle identification model can input the historical ultrasonic image set in the post-physiological period (pre-ovulation) stage into a pre-established deep learning network by acquiring the historical ultrasonic image set in the post-physiological period (pre-ovulation) stage to obtain an output contour image of a historical ultrasonic image, and network parameters of the deep learning network are adjusted according to the output contour image and an expected contour image to obtain the follicle identification model. Illustratively, the deep learning network can be one or more of a U-net image segmentation model, a Ternausnet image segmentation model, a deep Lab image segmentation model and a Linknet image segmentation model. The contour images include, but are not limited to, contour images of the ovary and contour images of the follicle. Illustratively, from the current contour image, contour data of the follicle may be determined using an elliptical contour detection algorithm, which may in particular be a FindContours contour detection function in the OpenCV computer vision library.
And S240, determining ovulation information of the tested object according to the contour data.
In one embodiment, the ovulation information includes, but is not limited to, the day of ovulation and the growth rate of the follicle.
In this regard, the number of growing follicles in the left and right ovaries of a female is generally more than one during the post-physiologic (pre-ovulatory) phase. Therefore, when determining the ovulation information, one of the main follicle or the dominant follicle in the left and right ovaries can be determined by comparing one or more of the data of the long axis size, the short axis size, the area and the volume of the detected follicle as the determination condition, and the ovulation information of the subject can be determined based on the contour data of the main follicle. The contour data of the main follicle comprises the major axis size, the minor axis size, the area and the volume of the main follicle, and one or more parameters are used as judgment conditions for determining ovulation information of the tested object. Of course, the outline data parameters of all follicles may be considered together as a judgment condition for determining ovulation information of the subject.
In one embodiment, different criteria may be selected based on different ovulation information. Specifically, when predicting the ovulation day of the subject, the contour data of the main follicle can be selected as the judgment condition. When determining the growth rate of the follicles, the contour data parameters of all follicles can be considered together. Optionally, at least one contour data of at least one follicle is recorded and saved, and the growth rate of the at least one follicle is determined from the contour data. Specifically, profile data of at least one follicle monitored by the subject in each physiological period is recorded and stored, and the growth rate of at least one follicle is calculated by combining the stored multiple pieces of profile data.
According to the technical scheme, the follicle at the post-ovulation (pre-ovulation) stage is identified, the problem that the ovulation day needs to be artificially predicted is solved, the accuracy of ovulation day prediction is improved, and intelligent monitoring of ovulation information is achieved.
On the basis of the above embodiment, optionally, the determining ovulation information of the measured object according to the profile data further includes:
performing maturity assessment and/or tonicity assessment according to the contour data of the main follicle;
and determining ovulation information of the tested object according to the result of the maturity evaluation and/or the result of the tension evaluation.
The contour data of follicles at different stages of physiology vary, as well as the maturity and surface tension of follicles. Surface tension refers to the tension between any two adjacent portions of the follicle surface that interact perpendicular to their boundary line per unit length. Illustratively, an evaluation scale, such as a scale of 1-10, is set for the maturity evaluation and the tonicity evaluation of the follicles. For example, when the long axis dimension of the follicle is 5-6mm, the follicle has a maturity of 1 and a tonicity of 1. When the size of the long axis of the follicle is 6-7mm, the maturity of the follicle is 2, and the tension is 2, etc. The criteria for maturity assessment and tonicity assessment are not limited herein.
The advantage of this arrangement is that by correlating the outline data of the follicle with the parameter assessment, the criteria for ovulation information are unified, making the results of the ovulation information determined more accurate. The acquired various ovulation information is convenient for the user to more comprehensively know the physiological period condition of the user.
On the basis of the above embodiment, optionally, the method further comprises displaying the result of the physiological period monitoring. The results of the physiologic phase monitoring include, but are not limited to, an ultrasound image set, a physiologic phase, a day of ovulation, a growth rate of at least one follicle, a maturity assessment result, and a tonicity assessment result. Illustratively, the display device may be a terminal display device communicatively connected to the ultrasound device, and of course, may also be a display device on the ultrasound device. Display devices include, but are not limited to, display screens and indicator lights. Specifically, when the display device includes an indicator light, a plurality of different indicator lights or one indicator light with different colors corresponding to different physiological periods may be set according to different physiological periods, and the manner of displaying the physiological period monitoring result is not limited herein.
EXAMPLE III
Fig. 3 is a schematic diagram of a physiological period monitoring device according to a third embodiment of the present invention, where the physiological period monitoring device according to the third embodiment of the present invention can execute the physiological period monitoring method according to any embodiment of the present invention, and this embodiment is applicable to a condition where an ultrasound device performs physiological period monitoring and can be executed by an ultrasound imaging device. The physiological phase monitoring device comprises: an ultrasound image set acquisition module 310 and a physiological phase stage determination module 320.
The ultrasound image set acquisition module 310 is configured to acquire a current ultrasound image set of the measured object; wherein the current ultrasound image set includes ultrasound images of the left and right ovaries and ultrasound images of the uterus.
And a physiological period stage determining module 320, configured to input the current ultrasound image set into a pre-trained image classification model, and determine a physiological period stage in which the object is located.
According to the technical scheme, the ultrasound image is input into the image classification model, so that the problem that the physiological period stage needs to be judged manually is solved, the intelligent monitoring of the physiological period stage is realized, and the accuracy of the monitoring of the physiological period stage is improved.
Optionally, the physiological period phase determining module 320 includes:
and the historical image set acquisition unit is used for acquiring a historical ultrasonic image set of the historical measured object and labeling according to the physiological period stage of the historical ultrasonic image set, wherein the historical ultrasonic image set comprises the ultrasonic images of the left ovary and the right ovary and the ultrasonic image of the uterus.
And the image classification model acquisition unit is used for inputting the labeled historical ultrasonic image set into the initial classification model as a training sample, and adjusting the model parameters of the initial classification model according to the output result to obtain the image classification model.
Optionally, the apparatus further comprises:
and the contour data determining module is used for performing follicle identification on the current ultrasonic image set if the physiological period stage is in a post-physiological period (preovulatory) stage, and determining contour data of at least one follicle, wherein the contour data comprises a long axis size and a short axis size of the follicle.
And the ovulation information determining module is used for determining the ovulation information of the tested object according to the contour data.
Optionally, the contour data determining module includes:
the contour data determining unit is used for inputting the current ultrasonic image set into a follicle identification model which is trained in advance, and determining a current contour image of at least one follicle;
a contour data determination unit for determining contour data of at least one follicle from the current contour image.
Optionally, the contour data determining module includes:
a historical ultrasound image set acquisition unit for acquiring a historical ultrasound image set at a post-physiological (pre-ovulation) stage;
the profile image output unit is used for inputting the historical ultrasonic image set in the post-physiological (pre-ovulation) stage into a pre-established deep learning network to obtain an output profile image of the historical ultrasonic image;
and the follicle identification model acquisition unit is used for adjusting the network parameters of the deep learning network according to the output contour image and the expected contour image to obtain a follicle identification model.
Optionally, the ovulation information determining module includes:
the evaluation unit is used for evaluating the maturity and/or the tension according to the contour data;
and the ovulation information determining unit is used for determining the ovulation information of the tested object according to the result of the maturity evaluation and/or the result of the tension evaluation.
Optionally, the apparatus further comprises:
the contour data storage module is used for recording and storing at least one contour data of at least one follicle;
a growth rate determining module for determining a growth rate of the at least one follicle based on the contour data.
The physiological period monitoring device provided by the embodiment of the invention can be used for executing the physiological period monitoring method provided by the embodiment of the invention, and has corresponding functions and beneficial effects of the executing method.
Example four
Fig. 4 is a schematic structural diagram of an ultrasound apparatus according to a fourth embodiment of the present invention, where the fourth embodiment of the present invention provides a service for implementing the physiological period monitoring method according to any of the above embodiments of the present invention, and the physiological period monitoring device according to the third embodiment of the present invention may be configured.
The components of the ultrasound device include, but are not limited to: a processor 40, a memory 41, an input device 42, an output device 43, and an ultrasound transducer 44; the number of processors 40 in the ultrasound apparatus may be one or more, and one processor 40 is taken as an example in fig. 4; the processor 40, the memory 41, the input device 42, the output device 43 and the ultrasound transducer 44 in the ultrasound apparatus may be connected by a bus or other means, as exemplified by the bus connection in fig. 4.
The memory 41, which is a computer-readable storage medium, may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules (e.g., the ultrasound image set acquisition module 310 and the physiological phase stage determination module 320) corresponding to the physiological phase monitoring method in embodiments of the present invention. The processor 40 executes various functional applications of the ultrasound apparatus and data processing by executing software programs, instructions and modules stored in the memory 41, namely, implements the above-described physiological period monitoring method.
The memory 41 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 41 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 41 may further include memory located remotely from processor 40, which may be connected to the ultrasound device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 42 is operable to receive entered numerical or character information and to generate key signal inputs relating to user settings and function controls of the ultrasound apparatus. The output device 43 may include a display device such as a display screen.
The ultrasonic transducer 44 is a key component in an ultrasonic imaging apparatus and is made of a set of special crystals having a piezoelectric effect. The piezoelectric crystal has special properties, namely, when voltage is applied to the specific direction of the crystal, the crystal can deform, and conversely, when the crystal deforms, voltage can be generated in the corresponding direction, so that conversion of electric signals and ultrasonic waves is realized, and the piezoelectric crystal has double functions of ultrasonic transmission and ultrasonic receiving.
According to the technical scheme, the ultrasound image is input into the image classification model, so that the problem that the physiological period stage needs to be judged manually is solved, the intelligent monitoring of the physiological period stage is realized, and the accuracy of the monitoring of the physiological period stage is improved.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method of monitoring a physiological phase, the method comprising:
acquiring a current ultrasonic image set of a measured object; wherein the current ultrasound image set comprises ultrasound images of the left and right ovaries and ultrasound images of the uterus;
and inputting the current ultrasonic image set into an image classification model trained in advance, and determining the physiological period stage of the object to be tested.
Of course, the embodiment of the present invention provides a storage medium containing computer-executable instructions, which are not limited to the method operations described above, but can also perform related operations in the method for monitoring a physiological period provided in any embodiment of the present invention.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (9)
1. A method of monitoring a physiological phase, comprising:
acquiring a current ultrasonic image set of a measured object; wherein the current ultrasound image set comprises ultrasound images of the left and right ovaries and ultrasound images of the uterus;
inputting the current ultrasonic image set into an image classification model trained in advance, and determining the physiological period stage of the tested object;
the method further comprises the following steps: acquiring a historical ultrasonic image set of a historical measured object, and labeling according to the physiological period stage of the historical ultrasonic image set, wherein the historical ultrasonic image set comprises ultrasonic images of a left ovary and a right ovary and ultrasonic images of a uterus;
inputting the marked historical ultrasonic image set as a training sample into an initial classification model, and adjusting model parameters of the initial classification model according to an output result to obtain an image classification model;
the labeling according to the physiological period stage of the historical ultrasound image set comprises: and marking the physiological period stage of the historical ultrasonic image set according to the stage and the thickness of the endometrium in the ultrasonic image of the uterus, the size of the follicle in the ultrasonic images of the left ovary and the right ovary and the endometrial image.
2. The method of claim 1, further comprising:
performing follicle identification on the current ultrasound image set if the phase of the physiological period is in a post-physiological (preovulatory) phase, and determining contour data of at least one follicle, wherein the contour data comprises a major axis dimension and a minor axis dimension of the follicle;
and determining ovulation information of the tested object according to the profile data.
3. The method of claim 2, wherein identifying the follicle in the current ultrasound image set and determining at least one follicle contour data comprises:
inputting the current ultrasonic image set into a follicle identification model which is trained in advance, and determining a current contour image of at least one follicle;
determining contour data of at least one follicle from the current contour image.
4. The method of claim 3, further comprising:
acquiring a historical ultrasonic image set in a post-physiological (pre-ovulation) stage;
inputting a historical ultrasonic image set in a post-physiological (pre-ovulation) stage into a pre-established deep learning network to obtain an output profile image of the historical ultrasonic image;
and adjusting network parameters of the deep learning network according to the output contour image and the expected contour image to obtain a follicle identification model.
5. The method of claim 2, wherein determining ovulation information for the subject from the profile data further comprises:
performing maturity assessment and/or tension assessment according to the profile data;
and determining ovulation information of the tested object according to the result of the maturity evaluation and/or the result of the tension evaluation.
6. The method of claim 2, further comprising:
recording and storing at least one profile data of at least one follicle;
determining a growth rate of the at least one follicle from the contour data.
7. A device for physiological session monitoring, the device comprising:
the ultrasonic image set acquisition module is used for acquiring a current ultrasonic image set of the measured object; wherein the current ultrasound image set comprises ultrasound images of the left and right ovaries and ultrasound images of the uterus;
a physiological period stage determining module, configured to input the current ultrasound image set into a pre-trained image classification model, and determine a physiological period stage in which the object is located;
the physiological phase stage determination module includes:
the historical image set acquisition unit is used for acquiring a historical ultrasonic image set of a historical measured object and labeling according to the physiological period stage of the historical ultrasonic image set, wherein the historical ultrasonic image set comprises ultrasonic images of the left ovary and the right ovary and ultrasonic images of the uterus;
the image classification model obtaining unit is used for inputting the marked historical ultrasonic image set into an initial classification model as a training sample, and adjusting model parameters of the initial classification model according to an output result to obtain an image classification model;
the historical image set obtaining unit is specifically configured to: and marking the physiological period stage of the historical ultrasonic image set according to the stage and the thickness of the endometrium in the ultrasonic image of the uterus, the size of the follicle in the ultrasonic images of the left ovary and the right ovary and the endometrial image.
8. An ultrasound apparatus, characterized in that the apparatus comprises:
one or more processors;
a memory for storing one or more programs;
an ultrasonic transducer for energy conversion;
when executed by the one or more processors, cause the one or more processors to implement the physiological period monitoring method of any one of claims 1-6.
9. A storage medium containing computer-executable instructions for performing the physiological session monitoring method of any one of claims 1-6 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910662447.8A CN110378888B (en) | 2019-07-22 | 2019-07-22 | Physiological period monitoring method and device, ultrasonic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910662447.8A CN110378888B (en) | 2019-07-22 | 2019-07-22 | Physiological period monitoring method and device, ultrasonic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110378888A CN110378888A (en) | 2019-10-25 |
| CN110378888B true CN110378888B (en) | 2022-01-25 |
Family
ID=68254813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910662447.8A Active CN110378888B (en) | 2019-07-22 | 2019-07-22 | Physiological period monitoring method and device, ultrasonic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110378888B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673453A (en) * | 2021-08-25 | 2021-11-19 | 天津大学 | M-type ultrasound-based movement intention prediction method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1875881A (en) * | 2005-06-07 | 2006-12-13 | 西门子公司 | Method for acquisition, analysis and representation of a medical image data set |
| CN105137093A (en) * | 2015-07-24 | 2015-12-09 | 天津起跑线生物信息技术有限公司 | Method for early warning of ovulation period |
| CN105232091A (en) * | 2015-09-30 | 2016-01-13 | 龙国亮 | Women's ovulation detecting system and method |
| CN105943086A (en) * | 2015-06-10 | 2016-09-21 | 湖南润泽医疗影像科技有限公司 | Ultrasonic follicle inspection tester and automatic analysis method thereof |
| CN106175826A (en) * | 2014-08-29 | 2016-12-07 | 三星麦迪森株式会社 | Ultrasonographic display device and the method for display ultrasonoscopy |
| CN108985366A (en) * | 2018-07-06 | 2018-12-11 | 武汉兰丁医学高科技有限公司 | B ultrasound image recognition algorithm and system based on convolution depth network |
| CN109671062A (en) * | 2018-12-11 | 2019-04-23 | 成都智能迭迦科技合伙企业(有限合伙) | Ultrasound image detection method, device, electronic equipment and readable storage medium storing program for executing |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004290335A (en) * | 2003-03-26 | 2004-10-21 | Tanita Corp | Physical condition managing device for women |
| CN102525685A (en) * | 2012-02-07 | 2012-07-04 | 青岛德瑞骏发生物科技有限公司 | Control method for synchronization of menstrual cycles of donor mare and receptor mare |
| US11154196B2 (en) * | 2017-06-20 | 2021-10-26 | Siemens Healthcare Gmbh | Deep-learnt tissue deformation for medical imaging |
-
2019
- 2019-07-22 CN CN201910662447.8A patent/CN110378888B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1875881A (en) * | 2005-06-07 | 2006-12-13 | 西门子公司 | Method for acquisition, analysis and representation of a medical image data set |
| CN106175826A (en) * | 2014-08-29 | 2016-12-07 | 三星麦迪森株式会社 | Ultrasonographic display device and the method for display ultrasonoscopy |
| CN105943086A (en) * | 2015-06-10 | 2016-09-21 | 湖南润泽医疗影像科技有限公司 | Ultrasonic follicle inspection tester and automatic analysis method thereof |
| CN105137093A (en) * | 2015-07-24 | 2015-12-09 | 天津起跑线生物信息技术有限公司 | Method for early warning of ovulation period |
| CN105232091A (en) * | 2015-09-30 | 2016-01-13 | 龙国亮 | Women's ovulation detecting system and method |
| CN108985366A (en) * | 2018-07-06 | 2018-12-11 | 武汉兰丁医学高科技有限公司 | B ultrasound image recognition algorithm and system based on convolution depth network |
| CN109671062A (en) * | 2018-12-11 | 2019-04-23 | 成都智能迭迦科技合伙企业(有限合伙) | Ultrasound image detection method, device, electronic equipment and readable storage medium storing program for executing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110378888A (en) | 2019-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7044796B2 (en) | Determining the number and size of follicles | |
| RU2607510C2 (en) | Automated measurement of doppler velocity using cheap converter | |
| US9687212B2 (en) | Ultrasonic diagnosis apparatus, ultrasonic image processing apparatus, ultrasonic image processing method, and ultrasonic image processing program | |
| Jones et al. | Benefits of ultrasound scanning during gestation in the small ruminant | |
| CN110415248B (en) | Blood vessel monitoring method, device, equipment and storage medium based on ultrasound | |
| US10709416B2 (en) | Obstetrical imaging at the point of care for untrained or minimally trained operators | |
| Coelho Neto et al. | True Reproducibility of UltraSound Techniques (TRUST): systematic review of reliability studies in obstetrics and gynecology | |
| CN110246135B (en) | Follicle monitoring method, device, system and storage medium | |
| CN108451543A (en) | Automatic ultrasonic imaging system and method | |
| CN110378888B (en) | Physiological period monitoring method and device, ultrasonic equipment and storage medium | |
| CN113274056A (en) | Ultrasonic scanning method and related device | |
| CN114246611A (en) | System and method for adaptive interface for ultrasound imaging system | |
| Luque et al. | Modification of the hand-held Vscan ultrasound and verification of its performance for transvaginal applications | |
| Singh et al. | Three-dimensional sonography-based automated volume calculation (SonoAVC) versus two-dimensional manual follicular tracking in in vitro fertilization | |
| CN111481233B (en) | Thickness measuring method for transparent layer of fetal cervical item | |
| WO2020103098A1 (en) | Ultrasonic imaging method and apparatus, storage medium, processor and computer device | |
| Racewicz et al. | Ultrasonographic diagnosis of early pregnancy in cattle using different ultrasound systems | |
| CN115813433A (en) | Follicle measuring method based on two-dimensional ultrasonic imaging and ultrasonic imaging system | |
| CN113729775A (en) | Ultrasonic examination diagnosis method and device | |
| Di Naro et al. | Ultrasound and probe setting | |
| CN113729774A (en) | Medical ultrasonic diagnosis method and device | |
| Murtinger et al. | Basics of Three-Dimensional Ultrasound and Applications in Reproductive Medicine | |
| Borghi et al. | The role of three-dimensional ultrasound in pregnancies submitted to cerclage | |
| Wladimiroff | Ultrasound Scanning in the First Trimester of Pregnancy | |
| RU2013989C1 (en) | Method for determining ovulation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |