CN110378888A - A kind of physiology phase monitoring method, device, ultrasonic device and storage medium - Google Patents
A kind of physiology phase monitoring method, device, ultrasonic device and storage medium Download PDFInfo
- Publication number
- CN110378888A CN110378888A CN201910662447.8A CN201910662447A CN110378888A CN 110378888 A CN110378888 A CN 110378888A CN 201910662447 A CN201910662447 A CN 201910662447A CN 110378888 A CN110378888 A CN 110378888A
- Authority
- CN
- China
- Prior art keywords
- physiology phase
- ultrasound image
- ovarian follicle
- measurand
- outline data
- 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.)
- Granted
Links
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 kind of physiology phase monitoring method, device, ultrasonic device and storage mediums, this method comprises: obtaining the current ultrasonic image set of measurand;Wherein, the current ultrasonic image set includes the ultrasound image of left and right ovary and the ultrasound image in uterus;The current ultrasonic image set is input in the image classification model that training is completed in advance, determines the physiology phase stage locating for the measurand.The embodiment of the present invention solves the problems, such as to need artificially to judge the physiology phase stage, realizes the intelligent monitoring to the physiology phase stage, improve the accuracy to the monitoring of physiology phase stage by the way that ultrasound image to be input in image classification model.
Description
Technical field
The present embodiments relate to ultrasonic medical field more particularly to a kind of physiology phase monitoring methods, device, ultrasonic device
And storage medium.
Background technique
Ultrasonic imaging is ultrasonic listening human body to be issued by electroacoustic transducer, and form image using ultrasonic reflection echo
A kind of imaging method.Ultrasonic imaging method is commonly used to judge the position of internal organs, size, form, determines the range and object of lesion
Rationality matter, the diagnosis suitable for a variety of organ diseases such as liver, kidney, bladder, uterus and ovary.
Ovarian follicle be egg mother cell occur with development basic function unit, be broadly divided into primordial follicle, growing follicle and
Graaffian follicle.In the prior art, people observe the developmental state of ovarian follicle in female ovary by way of ultrasonic imaging, to ovarian follicle
Developmental state make diagnosis, the further device for testing ovulation date for predicting women.
Above-mentioned prior art is needed to make diagnosis according to ultrasonic imaging result by experienced doctor, be determined
The physiology phase stage locating for follicles present.But the monitoring needs subjects for relying on doctor's progress physiology phase periodically arrive hospital
It is checked, causes the waste of man power and material, and the result subjective factor diagnosed is larger, be easy that there are biggish errors.
Summary of the invention
The embodiment of the present invention provides a kind of physiology phase monitoring method, device, ultrasonic device and storage medium, to realize to life
The intelligent monitoring in stage reason phase improves the accuracy of physiology phase stage monitoring.
In a first aspect, the embodiment of the invention provides a kind of physiology phase monitoring methods, this method comprises:
Obtain the current ultrasonic image set of measurand;Wherein, the current ultrasonic image set includes the super of left and right ovary
The ultrasound image of acoustic image and uterus;
The current ultrasonic image set is input in the image classification model that training is completed in advance, determines described tested pair
As the locating physiology phase stage.
Second aspect, the embodiment of the invention also provides a kind of device of physiology phase monitoring, which includes:
Ultrasound image collection obtains module, for obtaining the current ultrasonic image set of measurand;Wherein, the current ultrasonic
Image set includes the ultrasound image of left and right ovary and the ultrasound image in uterus;
Physiology phase stage determining module, for the current ultrasonic image set to be input to the image point that training is completed in advance
In class model, the physiology phase stage locating for the measurand is determined.
The third aspect, the embodiment of the invention also provides a kind of ultrasonic device, which includes:
One or more processors;
Memory, for storing one or more programs;
Ultrasonic transducer is converted for energy;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes above-mentioned related any physiology phase monitoring method.
Fourth aspect, it is described the embodiment of the invention also provides a kind of storage medium comprising computer executable instructions
Store instruction can be performed when being executed by computer processor for executing above-mentioned related any physiology in computer
Phase monitoring method.
The embodiment of the present invention solves needs and artificially judges physiology by the way that ultrasound image to be input in image classification model
The problem of stage phase, realizes the intelligent monitoring to the physiology phase stage, improves the accuracy to the monitoring of physiology phase stage.
Detailed description of the invention
Fig. 1 is a kind of flow chart for physiology phase monitoring method that the embodiment of the present invention one provides.
Fig. 2 is a kind of flow chart of physiology phase monitoring method provided by Embodiment 2 of the present invention.
Fig. 3 is a kind of schematic diagram for physiology phase monitoring device that the embodiment of the present invention three provides.
Fig. 4 is a kind of structural schematic diagram for ultrasonic device that the embodiment of the present invention four provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is a kind of flow chart for physiology phase monitoring method that the embodiment of the present invention one provides, and the present embodiment is applicable to
Ultrasonic device carries out the case where physiology phase monitoring, and this method can be executed by supersonic imaging apparatus, be specifically comprised the following steps:
S110, the current ultrasonic image set for obtaining measurand;Wherein, current ultrasonic image set includes left and right ovary
The ultrasound image of ultrasound image and uterus.
Medical ultrasound image is to utilize ultrasonic scanning human body, then pass through the ultrasonic wave of the reflection of reception tissue or projection
And handled, obtain the ultrasonogram of organ-tissue in antimer.Ultrasonic device currently used for medical diagnosis mainly has A type super
Audio clinic equipment, M type ultrasonic diagnostic equipment, Type B ultrasonic diagnostic equipment and ultrasonic doppler diagnostic equipment etc..It is corresponding,
In one embodiment, the ultrasound image of acquisition can be A-mode ultrasonic image, M type ultrasonoscopy, Type B ultrasound image and Doppler
One or more of ultrasound image is herein not construed as limiting the type of ultrasound image.Wherein, B ultrasound is clinically to apply at present
Widest ultrasonic diagnostic equipment, the principle for using luminance to modulate, echo signal is shown according to signal strength or weakness with gray scale
Show, to obtain the faultage image of tissue, is mainly used in abdomen examination, thyroid gland inspection, fetus inspection and gynecologial examination.
Specifically, user can be by the way that by the vertical body surface of ultrasonic transducer, the mobile ultrasonic transducer of sequence be obtained horizontal in measurand body
Section image series, the uterus of the range covering measurand of scanning and ovary.The acquisition modes of ultrasound image are not made herein
It limits.
S120, current ultrasonic image set is input in the image classification model that training is completed in advance, determines measurand
The locating physiology phase stage.
In one embodiment, optionally, the history ultrasound image collection for obtaining history measurand, according to history ultrasound figure
The physiology phase stage locating for image set is labeled, wherein history ultrasound image collection includes ultrasound image and the uterus of left and right ovary
Ultrasound image, the history ultrasound image collection after mark is input in preliminary classification model as training sample, according to output
As a result the model parameter of preliminary classification model is adjusted, to obtain image classification model.Wherein, the model of image classification can
With using typical CNN (Convolutional Neural Networks, convolutional neural networks) model, VGG network model,
One or more of ResNet network model, Inception network model, AlexNet network model disaggregated model.
In one embodiment, optionally, the stage according to locating for endometrium in uterine ultrasound image and thickness and
The information such as the size of ovarian follicle and ovary endometrial image physiology phase described in history ultrasound image collection in left and right ovary ultrasound image
Stage is labeled.Specifically, it is illustrated in conjunction with label parameters corresponding relationship of the table 1 to the physiology phase stage, table 1 is the present invention
A kind of label parameters information in physiology phase stage that embodiment one provides.
Wherein, it is known as a physiological period until the daystart of physiology phase to next physiology phase the previous day, generally exists
28 days or so.According to the tissue change in uterus and ovary, physiological period can be divided into three phases: (1) physiology phase is equivalent to physiology
The 1-5 days of period.Endometrium ischemic necrosis and fall off, angiorrhoxis bleeding, blood and the inner membrance fragment Via vagina to fall off
Discharge.At this point, endometrium is thinning, thickness is generally less than 3mm, and ovarian follicle is developed to growing follicle from primordial follicle, and size is small
In 5mm;(2) after physiology phase (before preovulatory), it is equivalent to the 5-14 days of physiological period.It endometrium reparation and thickens, intrauterine
Film with a thickness of 3-5mm.At this point, ovarian follicle is developed to graaffian follicle from growing follicle, size is in 5-22mm or so.Before ovulation
One day, ovarian cumulus image can be observed on ovary endometrial;(3) before physiology phase (after ovulation), it is equivalent to the 15- of physiological period
28 days.Endometrium and body of gland continue to increase, and secreting mucus, are plantation and the development preparatory condition of fertilized eggs, endometrium
Thickness increase to 5-10mm.At this point, it can be observed that the cut left after ovarian follicle discharge on ovary endometrial.
The usual more than one of ovarian follicle quantity in left and right ovary ultrasound image.In one embodiment, above-mentioned ovarian follicle can
To be to choose the maximum main ovarian follicle of outline data in more left and right ovary after the outline data of all ovarian follicles, judge main ovarian follicle
Whether outline data meets above-mentioned condition.Wherein, illustratively, the outline data of ovarian follicle includes the major axis dimension of ovarian follicle, short axle
Size, area and volume.When carrying out main ovarian follicle and choosing, it can be and one or more of outline datas of all ovarian follicles are carried out pair
Than.The selection standard of main ovarian follicle is not construed as limiting herein.
It should be noted that needing to comprehensively consider left and right ovary ultrasound image and son when carrying out physiology phase stage mark
All parameter informations in the ultrasound image of palace are labeled the physiology phase stage representated by history ultrasound image collection.This implementation
Table 1 in example only provides a kind of pair of physiology phase stage parameter information referenced when being labeled, the with good grounds left and right ovary of institute
The embodiment that ultrasound image and uterine ultrasound image carry out physiology phase stage mark belongs to the range of protection of the embodiment of the present invention.
It is artificial to solve needs by the way that ultrasound image to be input in image classification model for the technical solution of the present embodiment
The problem of judging the physiology phase stage realizes the intelligent monitoring to the physiology phase stage, improves to the monitoring of physiology phase stage
Accuracy.
Embodiment two
Fig. 2 is a kind of flow chart of physiology phase monitoring method provided by Embodiment 2 of the present invention, the technical side of the present embodiment
Case is the further refinement carried out on the basis of the above embodiments, optionally, is determining physiology phase locating for measurand
After stage, further includes:
If the physiology phase stage is in after physiology phase the stage (before preovulatory), ovarian follicle identification is carried out to current ultrasonic image set,
Determine the outline data of at least one ovarian follicle, wherein outline data includes the major axis dimension and minor axis dimension of ovarian follicle;
According to outline data, the ovulation information of measurand is determined.
The method of the present embodiment specifically comprises the following steps:
S210, the current ultrasonic image set for obtaining measurand;Wherein, current ultrasonic image set includes left and right ovary
The ultrasound image of ultrasound image and uterus.
S220, current ultrasonic image set is input in the image classification model that training is completed in advance, determines measurand
The locating physiology phase stage.
If S230, physiology phase stage are in after physiology phase the stage (before preovulatory), ovarian follicle is carried out to current ultrasonic image set
Identification, determines the outline data of at least one ovarian follicle, wherein outline data includes the major axis dimension and minor axis dimension of ovarian follicle.
In one embodiment, carrying out, which can be when ovarian follicle identification, carries out ovarian follicle identification to current ultrasonic image set, certainly,
It is also possible to identify the ultrasound image of left ovary and right ovary in current ultrasonic image set.Specifically, ovarian follicle is being sent out
It educates to graaffian follicle, fallopian tubal is discharged into from ovary as ovum.In fallopian tubal, ovum can generate in conjunction with sperm
Fertilized eggs, fertilized eggs migrate to uterus from fallopian tubal and carry out implantation.Therefore, stage (before preovulatory) after physiology phase, super in uterus
Generally identification is less than ovarian follicle in acoustic image, therefore ultrasound figure that can only to left ovary and right ovary in current ultrasonic image set
As being identified.
In one embodiment, optionally, current ultrasonic image set is inputted into the ovarian follicle identification model that training is completed in advance,
The current outline image for determining at least one ovarian follicle determines the outline data of at least one ovarian follicle according to current outline image.Its
In, ovarian follicle identification model can be in after physiology phase the history ultrasound image collection in stage (before preovulatory) by obtaining, will be in life
The history ultrasound image collection in stage is input in the deep learning network pre-established (before preovulatory) after the reason phase, and it is super to obtain history
The output contour images of acoustic image join the network of the deep learning network according to output contour images and desired contour images
Number is adjusted, to obtain ovarian follicle identification model.Wherein, illustratively, deep learning network can be U-net image segmentation mould
One of type, TernausNet Image Segmentation Model, DeepLab Image Segmentation Model and Linknet Image Segmentation Model or
Several models.Contour images include but is not limited to the contour images of ovary and the contour images of ovarian follicle.Illustratively, according to current
Contour images can determine the outline data of ovarian follicle using elliptic contour detection algorithm, and specifically, elliptic contour detection algorithm can
To be the FindContours contour detecting function in OpenCV computer vision library.
S240, according to the outline data, determine the ovulation information of measurand.
In one embodiment, ovulation information includes but is not limited to the speed of growth of ovulation day and ovarian follicle.
Wherein, the quantity in stage (before preovulatory) after physiology phase, the growing follicle in the left and right ovary of women is generally more than
One.Accordingly, it is determined that when ovulation information, major axis dimension, minor axis dimension, area and the body of the ovarian follicle that can be detected by comparing
One or more of product data determine the main ovarian follicle or perhaps dominant follicle in left and right ovary as Rule of judgment,
According to the outline data of main ovarian follicle, the ovulation information of measurand is determined.Wherein, the outline data of main ovarian follicle includes main ovarian follicle
Major axis dimension, minor axis dimension, area and volume, according to one such or several parameters as determining measurand ovulation information
Rule of judgment.It is of course also possible to by the outline data parameter for comprehensively considering all ovarian follicles, as determining measurand ovulation
The Rule of judgment of information.
In one embodiment, different Rule of judgment can be selected according to different ovulation information.Specifically, work as prediction
When the ovulation day of measurand, the outline data of main ovarian follicle can be chosen as Rule of judgment.When the speed of growth for determining ovarian follicle
When, the outline data parameter of all ovarian follicles can be comprehensively considered.Wherein, optionally, at least one ovarian follicle is recorded and saved extremely
A few outline data determines the speed of growth of at least one ovarian follicle according to the outline data.Specifically, it records simultaneously
The outline data for saving at least one ovarian follicle of each physiology phase monitoring of measurand, in conjunction with multiple multiple number of contours of preservation
According to calculating the speed of growth of at least one ovarian follicle.
The technical solution of the present embodiment is needed by solving to the ovarian follicle in stage identifies (before preovulatory) after physiology phase
The problem of very important person is predicting ovulation day improves the accuracy of ovulation day prediction, realizes the intelligent monitoring to ovulation information.
On the basis of the above embodiments, optionally, described according to the outline data, determine the row of the measurand
Ovum information, further includes:
Maturity assessment and/or tension assessment are carried out according to the outline data of the main ovarian follicle;
According to the result of maturity assessment and/or tension assessment as a result, determining the ovulation letter of the measurand
Breath.
The outline data of the ovarian follicle in different physiology phase stages is different, meanwhile, the maturity and surface tension of ovarian follicle are also different.
Wherein, surface tension refers to and interacts between any two adjacent part in ovarian follicle surface perpendicular to their unit length line of demarcation
Pulling force.Illustratively, it is assessed to the maturity assessment of ovarian follicle and tension and evaluation grade is set, such as 1-10 grades.For example, when
For the major axis dimension of ovarian follicle in 5-6mm, the maturity of ovarian follicle is 1, tension 1.When the major axis dimension of ovarian follicle is in 6-7mm, ovum
The maturity of bubble is 2, and tension is 2 etc..The standard of maturity assessment and tension assessment is not construed as limiting herein.
The advantages of this arrangement are as follows having been unified by the way that the outline data of ovarian follicle is corresponding with parameter evaluation to ovulation
The judgment criteria of information, so that the result of the ovulation information determined is more acurrate.The a variety of ovulation information got, facilitate user couple
The physiology phase situation of itself, which has, more fully to be understood.
On the basis of the above embodiments, optionally, this method further includes showing to the result of physiology phase monitoring.It is raw
The result of reason phase monitoring includes but is not limited to the growth speed of ultrasound image collection, physiology phase stage, ovulation day, at least one ovarian follicle
Degree, maturity assessment result and tension assessment result.Illustratively, display equipment can be the end with ultrasonic device communication connection
End display equipment, it is of course also possible to be the display equipment on ultrasonic device.Show that equipment includes but is not limited to display screen and instruction
Lamp.Specifically, when showing equipment includes indicator light, multiple and different indicator lights can be arranged according to the different physiology phase stages
Or an indicator light of corresponding different physiology phase stage different colours, the mode that physiology phase monitoring result is shown herein
It is not construed as limiting.
Embodiment three
Fig. 3 is a kind of schematic diagram for physiology phase monitoring device that the embodiment of the present invention three provides, and the embodiment of the present invention is mentioned
Physiology phase monitoring method provided by any embodiment of the invention can be performed in the physiology phase monitoring device of confession, and the present embodiment is applicable
In ultrasonic device carry out physiology phase monitoring the case where, can be executed by supersonic imaging apparatus.The physiology phase monitoring device includes:
Ultrasound image collection obtains module 310 and physiology phase stage determining module 320.
Wherein, ultrasound image collection obtains module 310, for obtaining the current ultrasonic image set of measurand;Wherein, currently
Ultrasound image collection includes the ultrasound image of left and right ovary and the ultrasound image in uterus.
Physiology phase stage determining module 320, for current ultrasonic image set to be input to the image point that training is completed in advance
In class model, the physiology phase stage locating for measurand is determined.
It is artificial to solve needs by the way that ultrasound image to be input in image classification model for the technical solution of the present embodiment
The problem of judging the physiology phase stage realizes the intelligent monitoring to the physiology phase stage, improves to the monitoring of physiology phase stage
Accuracy.
Optionally, physiology phase stage determining module 320 includes:
History image collection acquiring unit, for obtaining the history ultrasound image collection of history measurand, according to history ultrasound
The physiology phase stage locating for image set is labeled, wherein history ultrasound image collection includes the ultrasound image and son of left and right ovary
The ultrasound image in palace.
Image classification model acquiring unit, for being input to the history ultrasound image collection after mark as training sample just
In beginning disaggregated model, the model parameter of preliminary classification model is adjusted according to output result, to obtain image classification model.
Optionally, the device further include:
Outline data determining module, if being in after physiology phase the stage (before preovulatory) for the physiology phase stage, to current super
Sound spectrogram image set carries out ovarian follicle identification, determines the outline data of at least one ovarian follicle, wherein outline data includes the length of the ovarian follicle
Shaft size and minor axis dimension.
Ovulation information determination module, for determining the ovulation information of measurand according to outline data.
Optionally, outline data determining module includes:
Outline data determination unit identifies mould for the current ultrasonic image set to be inputted the ovarian follicle that training is completed in advance
Type determines the current outline image of at least one ovarian follicle;
Outline data determination unit, for determining the outline data of at least one ovarian follicle according to the current outline image.
Optionally, outline data determining module includes:
History ultrasound image collection acquiring unit is in after physiology phase the history ultrasound image in stage (before preovulatory) for obtaining
Collection;
Contour images output unit, for by the history ultrasound image collection in stage is input to (before preovulatory) after physiology phase
In the deep learning network pre-established, the output contour images of the history ultrasound image are obtained;
Ovarian follicle identification model acquiring unit is used for according to the output contour images and desired contour images to the depth
The network parameter of learning network is adjusted, to obtain ovarian follicle identification model.
Optionally, ovulation information determination module includes:
Assessment unit, for carrying out maturity assessment and/or tension assessment according to the outline data;
Ovulation information determination unit, it is that result and/or tension for being assessed according to the maturity are assessed as a result, determining
The ovulation information of the measurand.
Optionally, the device further include:
Outline data preserving module, for recording and saving at least one outline data of at least one ovarian follicle;
Speed of growth determining module, for determining the speed of growth of at least one ovarian follicle according to the outline data.
Physiology phase monitoring device provided by the embodiment of the present invention can be used for executing raw provided by the embodiment of the present invention
Reason phase monitoring method has the corresponding function of execution method and beneficial effect.
Example IV
Fig. 4 is a kind of structural schematic diagram for ultrasonic device that the embodiment of the present invention four provides, and the embodiment of the present invention four is this
The realization of any physiology phase monitoring method of invention above-described embodiment provides service, can configure institute in the embodiment of the present invention three
The physiology phase monitoring device stated.
The component of the ultrasonic device includes but is not limited to: processor 40, memory 41, input unit 42, output device 43
With ultrasonic transducer 44;The quantity of processor 40 in ultrasonic device can be one or more, with a processor 40 in Fig. 4
For;Processor 40, memory 41, input unit 42, output device 43 and ultrasonic transducer 44 in ultrasonic device can lead to
It crosses bus or other modes connects, in Fig. 4 for being connected by bus.
Memory 41 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, if the corresponding program instruction/module of physiology phase monitoring method in the embodiment of the present invention is (for example, ultrasound image
Collection obtains module 310 and physiology phase stage determining module 320).The software that processor 40 is stored in memory 41 by operation
Program, instruction and module realize above-mentioned physiology thereby executing the various function application and data processing of ultrasonic device
Phase monitoring method.
Memory 41 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function;Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 41 may include high-speed random access memory, can also include nonvolatile memory, for example, at least a magnetic
Disk storage device, flush memory device or other non-volatile solid state memory parts.In some instances, memory 41 can be further
Including the memory remotely located relative to processor 40, these remote memories can pass through network connection to ultrasonic device.
The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 42 can be used for receiving the number or character information of input, and generate the user setting with ultrasonic device
And the related key signals input of function control.Output device 43 may include that display screen etc. shows equipment.
Ultrasonic transducer 44 is the critical component in supersonic imaging apparatus, it is by one group of crystal with piezoelectric effect
It is made.This piezo-electric crystal has special property, is exactly plus voltage on crystal specific direction, and crystal can deformation occurs,
In turn when deformation occurs for crystal, voltage will be generated on corresponding direction, realize the conversion of electric signal and ultrasonic wave, have
Ultrasound emission and received dual function.
It is artificial to solve needs by the way that ultrasound image to be input in image classification model for the technical solution of the present embodiment
The problem of judging the physiology phase stage realizes the intelligent monitoring to the physiology phase stage, improves to the monitoring of physiology phase stage
Accuracy.
Embodiment five
The embodiment of the present invention five additionally provides a kind of storage medium comprising computer executable instructions, and the computer can
It executes instruction when being executed by computer processor for executing a kind of physiology phase monitoring method, this method comprises:
Obtain the current ultrasonic image set of measurand;Wherein, current ultrasonic image set includes the ultrasound figure of left and right ovary
The ultrasound image of picture and uterus;
Current ultrasonic image set is input in the image classification model that training is completed in advance, is determined locating for measurand
The physiology phase stage.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
Physiology phase prison provided by any embodiment of the invention can also be performed in the method operation that executable instruction is not limited to the described above
Relevant operation in survey method.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium can for example be but not limited to system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or
Any above combination.The more specific example (non exhaustive list) of computer readable storage medium include: with one or
The electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), can
Erasing programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light are deposited
Memory device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including but not limited to without
Line, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
It is related in the situation of remote computer, remote computer can include local area network (LAN) or wide area by the network of any kind
Net (WAN), is connected to subscriber computer, or, it may be connected to outer computer (such as using ISP come
It is connected by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of physiology phase monitoring method characterized by comprising
Obtain the current ultrasonic image set of measurand;Wherein, the current ultrasonic image set includes the ultrasound figure of left and right ovary
The ultrasound image of picture and uterus;
The current ultrasonic image set is input in the image classification model that training is completed in advance, determines the measurand institute
The physiology phase stage at place.
2. the method according to claim 1, wherein further include:
Obtain history measurand history ultrasound image collection, according to the physiology phase stage locating for the history ultrasound image collection into
Rower note, wherein the history ultrasound image collection includes the ultrasound image of left and right ovary and the ultrasound image in uterus;
The history ultrasound image collection after mark is input in preliminary classification model as training sample, according to output result
The model parameter of the preliminary classification model is adjusted, to obtain image classification model.
3. the method according to claim 1, wherein further include:
If the physiology phase stage is in after physiology phase the stage (before preovulatory), ovarian follicle knowledge is carried out to the current ultrasonic image set
Not, the outline data of at least one ovarian follicle is determined, wherein the outline data includes the major axis dimension and short axle ruler of the ovarian follicle
It is very little;
According to the outline data, the ovulation information of the measurand is determined.
4. according to the method described in claim 3, it is characterized in that, described carry out ovarian follicle knowledge to the current ultrasonic image set
Not, the outline data of at least one ovarian follicle is determined, comprising:
The current ultrasonic image set is inputted into the ovarian follicle identification model that training is completed in advance, determines the current of at least one ovarian follicle
Contour images;
According to the current outline image, the outline data of at least one ovarian follicle is determined.
5. according to the method described in claim 4, it is characterized by further comprising:
It obtains and is in after physiology phase the history ultrasound image collection in stage (before preovulatory);
By the history ultrasound image collection in stage is input to the deep learning network pre-established (before preovulatory) after physiology phase
In, obtain the output contour images of the history ultrasound image;
It is adjusted according to the output contour images with network parameter of the desired contour images to the deep learning network, with
Obtain ovarian follicle identification model.
6. according to the method described in claim 3, determining described tested pair it is characterized in that, described according to the outline data
The ovulation information of elephant, further includes:
Maturity assessment and/or tension assessment are carried out according to the outline data;
According to the result of maturity assessment and/or tension assessment as a result, determining the ovulation information of the measurand.
7. according to the method described in claim 3, it is characterized by further comprising:
Record and save at least one outline data of at least one ovarian follicle;
According to the outline data, the speed of growth of at least one ovarian follicle is determined.
8. a kind of device of physiology phase monitoring, which is characterized in that the device includes:
Ultrasound image collection obtains module, for obtaining the current ultrasonic image set of measurand;Wherein, the current ultrasonic image
Collection includes the ultrasound image of left and right ovary and the ultrasound image in uterus;
Physiology phase stage determining module, for the current ultrasonic image set to be input to the image classification mould that training is completed in advance
In type, the physiology phase stage locating for the measurand is determined.
9. a kind of ultrasonic device, which is characterized in that the equipment includes:
One or more processors;
Memory, for storing one or more programs;
Ultrasonic transducer is converted for energy;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now physiology phase monitoring method as described in any in claim 1-7.
10. a kind of storage medium comprising computer executable instructions, which is characterized in that the computer executable instructions by
For executing the physiology phase monitoring method as described in any in claim 1-7 when computer processor executes.
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 true CN110378888A (en) | 2019-10-25 |
CN110378888B 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) |
Cited By (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 (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040193069A1 (en) * | 2003-03-26 | 2004-09-30 | Tanita Corporation | Female physical condition management apparatus |
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 |
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 |
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 |
CN109102532A (en) * | 2017-06-20 | 2018-12-28 | 西门子保健有限责任公司 | The metaplasia of deep learning for medical imaging |
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 |
-
2019
- 2019-07-22 CN CN201910662447.8A patent/CN110378888B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040193069A1 (en) * | 2003-03-26 | 2004-09-30 | Tanita Corporation | Female physical condition management apparatus |
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 |
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 |
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 |
CN109102532A (en) * | 2017-06-20 | 2018-12-28 | 西门子保健有限责任公司 | The metaplasia of deep learning for medical imaging |
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 |
Cited By (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 |
Also Published As
Publication number | Publication date |
---|---|
CN110378888B (en) | 2022-01-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ginther | How ultrasound technologies have expanded and revolutionized research in reproduction in large animals | |
Gonzalez‐Bulnes et al. | Ultrasonographic imaging in small ruminant reproduction | |
Jones et al. | Benefits of ultrasound scanning during gestation in the small ruminant | |
JP2023159340A (en) | Intelligent ultrasound-based fertility monitoring | |
Ganaie et al. | Evaluation of different techniques for pregnancy diagnosis in sheep | |
AU2010269114B2 (en) | Non-invasively measuring physiological process | |
CN110246135A (en) | Monitor Follicles method, apparatus, system and storage medium | |
Rempen et al. | Quality requirements for ultrasound examination in early pregnancy (DEGUM Level I) between 4+ 0 and 13+ 6 weeks of gestation | |
CN110378888A (en) | A kind of physiology phase monitoring method, device, ultrasonic device and storage medium | |
Ivančić et al. | Ultrasonographic findings associated with normal pregnancy and fetal well‐being in the bottlenose dolphin (Tursiops truncatus) | |
Viñoles-Gil et al. | Sheep and goats | |
Ginther et al. | Ultrasonic evaluation of the reproductive tract of the mare; principles, equipment, and techniques | |
Sur et al. | Embryo volume measurement: an intraobserver, intermethod comparative study of semiautomated and manual three‐dimensional ultrasound techniques | |
Revol et al. | Foetal ageing in farmed red deer using real-time ultrasonography | |
WO2020103098A1 (en) | Ultrasonic imaging method and apparatus, storage medium, processor and computer device | |
Zalud et al. | Placental and spiral artery volume and gray‐scale value assessment via 3‐dimensional sonography in the second trimester | |
Racewicz et al. | Ultrasonographic diagnosis of early pregnancy in cattle using different ultrasound systems | |
Shero et al. | Field use of ultrasonography to characterize the reproductive tract and early pregnancy in a phocid, the weddell seal (Leptonychotes weddellii) | |
Lang et al. | A Method to Visualize 3‐Dimensional Anatomic Changes in the Cervix During Pregnancy: A Preliminary Observational Study | |
Thuring et al. | Operator auditory perception and spectral quantification of umbilical artery Doppler ultrasound signals | |
Shih et al. | Three-dimensional ultrasonography in early pregnancy | |
Borghi et al. | The role of three-dimensional ultrasound in pregnancies submitted to cerclage | |
CN203290937U (en) | Four-dimensional probe | |
US20230342917A1 (en) | Method and system for automatic segmentation and phase prediction in ultrasound images depicting anatomical structures that change over a patient menstrual cycle | |
Pestelacci et al. | Comparison of two‐dimensional (2D) and three‐dimensional (3D) ultrasonography for gestational ageing in the early to mid‐pregnant bitch |
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 |