CN117974556A - Amniotic fluid region calibration method and system based on ultrasonic image - Google Patents
Amniotic fluid region calibration method and system based on ultrasonic image Download PDFInfo
- Publication number
- CN117974556A CN117974556A CN202311789847.8A CN202311789847A CN117974556A CN 117974556 A CN117974556 A CN 117974556A CN 202311789847 A CN202311789847 A CN 202311789847A CN 117974556 A CN117974556 A CN 117974556A
- Authority
- CN
- China
- Prior art keywords
- amniotic fluid
- fluid region
- image
- ultrasonic image
- training
- 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.)
- Pending
Links
- 210000004381 amniotic fluid Anatomy 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012549 training Methods 0.000 claims abstract description 65
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000002604 ultrasonography Methods 0.000 claims description 19
- 238000012937 correction Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 abstract description 4
- 230000035935 pregnancy Effects 0.000 description 8
- 230000004044 response Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 210000001161 mammalian embryo Anatomy 0.000 description 4
- 238000002592 echocardiography Methods 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 3
- 210000001519 tissue Anatomy 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001605 fetal effect Effects 0.000 description 2
- 210000003754 fetus Anatomy 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 208000026350 Inborn Genetic disease Diseases 0.000 description 1
- 238000002669 amniocentesis Methods 0.000 description 1
- 210000001691 amnion Anatomy 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 210000002219 extraembryonic membrane Anatomy 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 230000004578 fetal growth Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 208000016361 genetic disease Diseases 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000008774 maternal effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 210000003954 umbilical cord Anatomy 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
- 210000004291 uterus Anatomy 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Abstract
The invention discloses an amniotic fluid region calibration method and system based on an ultrasonic image, and relates to the technical field of image processing. Acquiring an ultrasonic image, preprocessing the ultrasonic image, and taking the preprocessed image as a training sample; calibrating the amniotic fluid region of the training sample; constructing a discrimination network, and training the discrimination network by using the calibrated training sample to obtain a trained amniotic fluid region calibration model, wherein in the process of training the discrimination network, a DPM method is used for extracting features, and an SVM method is used for classifying ultrasonic images; and processing the ultrasonic image to be discriminated by using the amniotic fluid region calibration model to obtain an ultrasonic image marked with the amniotic fluid region. The method can indicate through the difference of the image gray values in the ultrasonic image, so that automatic labeling is realized, and the method is used for analyzing amniotic fluid areas.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an amniotic fluid region calibration method and system based on an ultrasonic image.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Amniotic fluid is fluid within the amniotic cavity of an embryo at an early stage. The source, amount and composition of amniotic fluid varies from pregnancy to pregnancy. Early gestation is mainly the leakage of maternal plasma through the fetal membrane into the amniotic membrane, and mid-term may be the main source of fetal urine. Amniotic fluid has the effects of protecting fetus and protecting mother during gestation period. Amniotic fluid examination may reflect fetal growth, maturity, sex within the uterus and aid in diagnosis of certain genetic diseases. Amniotic fluid specimens are typically obtained by a general practitioner via amniocentesis.
With the development of ultrasonic technology, ultrasonic imaging is gradually applied to embryo inspection due to its non-invasive nature, and B-ultrasound is a well-known technique. Ultrasound examination is an examination method that uses differences in the physical properties of ultrasound and the acoustic properties of human organ tissue to display and record in the form of waveforms, curves or images, thereby performing diagnosis of a disease. Various organs and tissues of the human body have specific acoustic impedance and attenuation characteristics, thus constituting differences in acoustic impedance and attenuation. Ultrasound is injected into the body from the surface to the deep, and is subjected to organs and tissues with different acoustic impedance and different attenuation characteristics, so that different reflections and attenuations are generated. This different reflection and attenuation is the basis for constructing an ultrasound image. The received echoes are sequentially displayed on the shadow screen by light spots with different brightness according to the intensity of the echoes, so that the section ultrasonic image of the human body can be displayed.
Traditional segmentation of amniotic fluid region in ultrasonic image is carried out manually by doctor according to experience and ultrasonic image, and has the following problems: the artificial calibration is influenced by more subjective factors, and the defined areas are different due to different eyesight and different discriminant standards and experiences of different people; the workload is large, and the time consumption is long; the calibration range lacks accuracy and cannot be accurately handled for image distortion. Because the contrast of an ultrasonic image is low and a large amount of speckle noise exists, the object segmentation in the ultrasonic image is more difficult than that in a natural image, and the calibration method in the existing image segmentation process is not suitable for marking the ultrasonic image of the amniotic fluid region, so that the accurate calibration of the amniotic fluid region of the ultrasonic image is realized, and the technical problem to be solved in the prior art is urgent.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide the amniotic fluid region calibration method and the amniotic fluid region calibration system based on the ultrasonic image, which can realize automatic labeling by indicating the difference of the gray values of the images in the ultrasonic image, thereby being used for analyzing the amniotic fluid region.
In order to achieve the above object, the present invention is realized by the following technical scheme:
The invention provides an amniotic fluid region calibration method based on an ultrasonic image, which comprises the following steps:
Acquiring an ultrasonic image, preprocessing the ultrasonic image, and taking the preprocessed image as a training sample;
calibrating the amniotic fluid region of the training sample;
Constructing a discrimination network, and training the discrimination network by using the calibrated training sample to obtain a trained amniotic fluid region calibration model, wherein in the process of training the discrimination network, a DPM method is used for extracting features, and an SVM method is used for classifying ultrasonic images;
and processing the ultrasonic image to be discriminated by using the amniotic fluid region calibration model to obtain an ultrasonic image marked with the amniotic fluid region.
Further, pre-processing the ultrasound image includes graying the ultrasound image, denoising the image, enhancing contrast, or any combination of the three.
Further, the specific steps of training the discrimination network by using the calibrated training samples are as follows:
dividing the training sample into a training set and a correction set;
extracting features of the training set by utilizing a discrimination network, and marking out a corresponding amniotic fluid region;
And correcting the mark by utilizing the ultrasonic images in the correction set, thereby obtaining a trained amniotic fluid region calibration model.
Furthermore, the correction set is an ultrasonic image of the training sample after amniotic fluid region labeling.
Further, the image features extracted by the feature extraction process are image texture features.
Further, the image texture features are gray level difference statistics.
Further, the training ending criteria are: outputting the marked amniotic fluid region in the ultrasonic image and performing error calculation on the marked amniotic fluid region; if the error is smaller than the set threshold, finishing training to obtain a trained amniotic fluid region calibration model; if the error is greater than or equal to the set threshold, updating the training sample, and continuing training until the error is less than the set threshold.
The second aspect of the invention provides an amniotic fluid region calibration system based on an ultrasonic image, which comprises:
The image acquisition module is configured to acquire an ultrasonic image, preprocess the ultrasonic image and take the preprocessed image as a training sample;
the sample calibration module is configured to calibrate the amniotic fluid region of the training sample;
the model training module is configured to construct a discrimination network, train the discrimination network by using the calibrated training sample to obtain a trained amniotic fluid region calibration model, wherein in the process of training the discrimination network, the DPM method is used for extracting features, and the SVM method is used for classifying ultrasonic images;
The image calibration module is configured to process the ultrasonic image to be distinguished by using the amniotic fluid region calibration model to obtain an ultrasonic image marked with the amniotic fluid region.
A third aspect of the present invention provides a medium having stored thereon a program which when executed by a processor performs the steps of the ultrasound image based amniotic fluid region calibration method according to the first aspect of the present invention.
A fourth aspect of the invention provides an apparatus comprising a memory, a processor and a program stored on the memory and executable on the processor, the processor implementing the steps in the ultrasound image based amniotic fluid region calibration method according to the first aspect of the invention when the program is executed.
The one or more of the above technical solutions have the following beneficial effects:
the invention discloses an amniotic fluid region calibration method and an amniotic fluid region calibration system based on an ultrasonic image, and provides an amniotic fluid region analysis method based on a DPM (digital pulse width modulation) feature extraction method aiming at the problem of calibration of the amniotic fluid region of the ultrasonic image. By the method, the deformable component model (Deformable Parts Model, DPM) characteristic extraction is carried out, and the amniotic fluid region calibration model with good accuracy can be obtained.
The amniotic fluid region calibration model provided by the invention has a good effect when applied to clinical amniotic fluid region calibration. According to the amniotic fluid region calibration model, a doctor can save a large amount of manual time, shorten the learning period, reduce the probability of occurrence of amniotic fluid region calibration errors, assist in diagnosing the amniotic fluid region, and improve the accuracy and the safety.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
Fig. 1 is a flowchart of an amniotic fluid region calibration method based on an ultrasonic image according to a first embodiment of the present invention.
Fig. 2 is a schematic diagram of a DPM feature extraction method according to a first embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It should be noted that, in the embodiments of the present invention, related data such as ultrasound images are related, when the above embodiments of the present invention are applied to specific products or technologies, user permission or consent is required to be obtained, and the collection, use and processing of related data is required to comply with related laws and regulations and standards of related countries and regions.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof;
embodiment one:
The first embodiment of the invention provides an amniotic fluid region calibration method based on an ultrasonic image, as shown in fig. 1, comprising the following steps:
S1: and acquiring an ultrasonic image, preprocessing the ultrasonic image, and taking the preprocessed image as a training sample.
S2: and calibrating the amniotic fluid region of the training sample.
S3: constructing a discrimination network, training the discrimination network by using the calibrated training sample to obtain a trained amniotic fluid region calibration model, wherein in the process of training the discrimination network, a DPM method is used for extracting features, and an SVM method is used for classifying ultrasonic images.
S4: and processing the ultrasonic image to be discriminated by using the amniotic fluid region calibration model to obtain an ultrasonic image marked with the amniotic fluid region.
In S1, preprocessing the ultrasound image includes graying the ultrasound image, denoising the image, enhancing contrast, or any combination of the three. And a bilateral filtering method is adopted for denoising the image.
S3, training the discrimination network by using the calibrated training sample comprises the following specific steps:
s301: the training samples are divided into training sets and correction sets.
The correction set is an ultrasonic image of a training sample after amniotic fluid region labeling.
S302: and extracting the characteristics of the training set by utilizing a discrimination network, and marking out the corresponding amniotic fluid region.
The amniotic fluid region typically appears as a clean anechoic zone on B-ultrasound, where the embryo or fetus and umbilical cord appear very clearly. In the early gestation period, the amniotic fluid is pure in area, the embryo is smaller, and the area calibration is easier. As gestation time increases, fetal volume increases to late gestation, possibly resulting in the amniotic fluid region becoming a non-singly connected region, and at the same time, punctiform echoes inside the amniotic fluid region during late gestation gradually increase, which can affect the determination of the amniotic fluid region. Compared with other image features, the boundary of the amniotic fluid region is more fuzzy, and the tiny target region is easily ignored, so that the problem of inaccurate calibration is caused. Therefore, for amniotic fluid region calibration, the root model is used for overall region judgment, and the component model judges a tiny target region, so that the region is finer.
More specifically, the discriminant model is composed of two components, each of which is composed of a root model and a plurality of component models. And extracting a DPM characteristic image of any one input image, and then carrying out Gaussian pyramid up-sampling on the original image to extract the DPM characteristic image with 2 times of resolution. And carrying out convolution operation on the DPM characteristic graph of the original image and the trained root filter operator, thereby obtaining a response graph of the root filter model. And carrying out convolution operation on the DPM characteristic diagram with the resolution of 2 times and the trained component filter operator, thereby obtaining a response diagram of the component filter model. And carrying out Gaussian pyramid downsampling operation on the response diagram of the component filter model. And then carrying out weighted average on the obtained images to obtain a final response chart. The larger the luminance is, the larger the response value is, thereby obtaining a final detection area.
DPM feature extraction process, as shown in fig. 2:
1. Gamma correction is carried out on the original image;
2. Setting an 8×8 cell unit, normalizing the cell unit with 4 cell units in its diagonal neighborhood, and cutting off in four directions;
3. Respectively calculating gradient histograms of four truncated areas, wherein 18 gradient vectors are generated by signed (0-360 DEG) gradients and 9 unsigned (0-180 DEG) gradients;
4. Accumulating histograms in different neighborhood directions to obtain 27-dimensional characteristics;
5. accumulating the signed gradient direction histogram and the unsigned gradient direction histogram in the same neighborhood direction to obtain a 4-dimensional characteristic;
6. And finally, all the features are spliced together to obtain the 31-dimensional feature.
The image features extracted in the feature extraction process are image texture features, and the image texture features are gray level difference statistics.
S303: and correcting the mark by utilizing the ultrasonic images in the correction set, thereby obtaining a trained amniotic fluid region calibration model for amniotic fluid region matching.
In this embodiment, the standard for ending training is: outputting the marked amniotic fluid region in the ultrasonic image and performing error calculation on the marked amniotic fluid region; if the error is smaller than the set threshold, finishing training to obtain a trained amniotic fluid region calibration model; if the error is greater than or equal to the set threshold, updating the training sample, and continuing training until the error is less than the set threshold.
Embodiment two:
The second embodiment of the invention provides an amniotic fluid region calibration system based on an ultrasonic image, which comprises:
The image acquisition module is configured to acquire an ultrasonic image, preprocess the ultrasonic image and take the preprocessed image as a training sample;
the sample calibration module is configured to calibrate the amniotic fluid region of the training sample;
the model training module is configured to construct a discrimination network, train the discrimination network by using the calibrated training sample to obtain a trained amniotic fluid region calibration model, wherein in the process of training the discrimination network, the DPM method is used for extracting features, and the SVM method is used for classifying ultrasonic images;
The image calibration module is configured to process the ultrasonic image to be distinguished by using the amniotic fluid region calibration model to obtain an ultrasonic image marked with the amniotic fluid region.
Embodiment III:
The third embodiment of the present invention provides a medium, on which a program is stored, which when executed by a processor, implements the steps in the amniotic fluid region calibration method based on an ultrasound image according to the first embodiment of the present invention.
Embodiment four:
The fourth embodiment of the invention provides a device, which comprises a memory, a processor and a program stored on the memory and capable of running on the processor, wherein the processor realizes the steps in the amniotic fluid region calibration method based on the ultrasonic image according to the first embodiment of the invention when executing the program.
The steps involved in the second, third and fourth embodiments correspond to the first embodiment of the method, and the detailed description of the second embodiment refers to the relevant description of the first embodiment.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented by general-purpose computer means, alternatively they may be implemented by program code executable by computing means, whereby they may be stored in storage means for execution by computing means, or they may be made into individual integrated circuit modules separately, or a plurality of modules or steps in them may be made into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (10)
1. An amniotic fluid region calibration method based on an ultrasonic image is characterized by comprising the following steps:
Acquiring an ultrasonic image, preprocessing the ultrasonic image, and taking the preprocessed image as a training sample;
calibrating the amniotic fluid region of the training sample;
Constructing a discrimination network, and training the discrimination network by using the calibrated training sample to obtain a trained amniotic fluid region calibration model, wherein in the process of training the discrimination network, a DPM method is used for extracting features, and an SVM method is used for classifying ultrasonic images;
and processing the ultrasonic image to be discriminated by using the amniotic fluid region calibration model to obtain an ultrasonic image marked with the amniotic fluid region.
2. The ultrasound image-based amniotic fluid region calibration method according to claim 1, wherein preprocessing the ultrasound image includes graying the ultrasound image, denoising the image, enhancing contrast, or any combination thereof.
3. The method for calibrating an amniotic fluid region based on an ultrasonic image according to claim 1, wherein the specific steps of training the discrimination network by using the calibrated training samples are as follows:
dividing the training sample into a training set and a correction set;
extracting features of the training set by utilizing a discrimination network, and marking out a corresponding amniotic fluid region;
And correcting the mark by utilizing the ultrasonic images in the correction set, thereby obtaining a trained amniotic fluid region calibration model.
4. The method for calibrating an amniotic fluid region based on an ultrasonic image according to claim 3, wherein the correction set is an ultrasonic image after the amniotic fluid region is marked in a training sample.
5. The method of calibrating an amniotic fluid region based on an ultrasonic image according to claim 3, wherein the image features extracted by the feature extraction process are image texture features.
6. The method for calibrating an amniotic fluid region based on an ultrasonic image according to claim 5, wherein the image texture feature is gray level difference statistics.
7. The method for calibrating an amniotic fluid region based on an ultrasonic image according to claim 1, wherein the training ending criteria are: outputting the marked amniotic fluid region in the ultrasonic image and performing error calculation on the marked amniotic fluid region; if the error is smaller than the set threshold, finishing training to obtain a trained amniotic fluid region calibration model; if the error is greater than or equal to the set threshold, updating the training sample, and continuing training until the error is less than the set threshold.
8. Amniotic fluid region calibration system based on ultrasonic image, characterized by comprising:
The image acquisition module is configured to acquire an ultrasonic image, preprocess the ultrasonic image and take the preprocessed image as a training sample;
the sample calibration module is configured to calibrate the amniotic fluid region of the training sample;
the model training module is configured to construct a discrimination network, train the discrimination network by using the calibrated training sample to obtain a trained amniotic fluid region calibration model, wherein in the process of training the discrimination network, the DPM method is used for extracting features, and the SVM method is used for classifying ultrasonic images;
The image calibration module is configured to process the ultrasonic image to be distinguished by using the amniotic fluid region calibration model to obtain an ultrasonic image marked with the amniotic fluid region.
9. A computer readable storage medium, characterized in that a plurality of instructions are stored, which instructions are adapted to be loaded by a processor of a terminal device and to perform the ultrasound image based amniotic fluid region calibration method according to any of claims 1-7.
10. A terminal device comprising a processor and a computer readable storage medium, the processor configured to implement instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the ultrasound image based amniotic fluid region calibration method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311789847.8A CN117974556A (en) | 2023-12-22 | 2023-12-22 | Amniotic fluid region calibration method and system based on ultrasonic image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311789847.8A CN117974556A (en) | 2023-12-22 | 2023-12-22 | Amniotic fluid region calibration method and system based on ultrasonic image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117974556A true CN117974556A (en) | 2024-05-03 |
Family
ID=90846713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311789847.8A Pending CN117974556A (en) | 2023-12-22 | 2023-12-22 | Amniotic fluid region calibration method and system based on ultrasonic image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117974556A (en) |
-
2023
- 2023-12-22 CN CN202311789847.8A patent/CN117974556A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108573490B (en) | Intelligent film reading system for tumor image data | |
| CN112529894B (en) | Thyroid nodule diagnosis method based on deep learning network | |
| CN109949271B (en) | Detection method based on medical image, model training method and device | |
| JP2016531709A (en) | Image analysis technology for diagnosing disease | |
| CN112070119A (en) | Ultrasonic tangent plane image quality control method and device and computer equipment | |
| CN111986211A (en) | Deep learning-based ophthalmic ultrasonic automatic screening method and system | |
| CN116503392B (en) | Follicular region segmentation method for ovarian tissue analysis | |
| Bai et al. | Automatic segmentation of cervical region in colposcopic images using K-means | |
| CN110910404B (en) | Anti-noise data breast ultrasonic nodule segmentation method | |
| CN113576508A (en) | Cerebral hemorrhage auxiliary diagnosis system based on neural network | |
| CN113017687A (en) | Automatic identification method for B-ultrasonic image of abdominal dropsy | |
| CN111820948B (en) | Fetal growth parameter measuring method and system and ultrasonic equipment | |
| CN116523802B (en) | Enhancement optimization method for liver ultrasonic image | |
| CN117974556A (en) | Amniotic fluid region calibration method and system based on ultrasonic image | |
| CN111325758A (en) | Lung image segmentation method and device and training method of image segmentation model | |
| CN116563224A (en) | Image histology placenta implantation prediction method and device based on depth semantic features | |
| CN116452523A (en) | Ultrasonic image quality quantitative evaluation method | |
| CN115035086A (en) | Intelligent tuberculosis skin test screening and analyzing method and device based on deep learning | |
| Chakkarwar et al. | Automated analysis of gestational sac in medical image processing | |
| CN114332139A (en) | Fetal ultrasound image brain segmentation method based on prior interaction reinforcement learning | |
| CN114938971A (en) | Ultrasonic image quality control method and system | |
| CN114947957A (en) | Carotid plaque analysis method and system based on ultrasonic image | |
| CN113689424A (en) | Ultrasonic inspection system capable of automatically identifying image characteristics and identification method | |
| CN117593192B (en) | Gynecological cervical image enhancement analysis method | |
| CN115147378B (en) | CT image analysis and extraction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |