CN112002407A - Breast cancer diagnosis device and method based on ultrasonic video - Google Patents
Breast cancer diagnosis device and method based on ultrasonic video Download PDFInfo
- Publication number
- CN112002407A CN112002407A CN202010689889.4A CN202010689889A CN112002407A CN 112002407 A CN112002407 A CN 112002407A CN 202010689889 A CN202010689889 A CN 202010689889A CN 112002407 A CN112002407 A CN 112002407A
- Authority
- CN
- China
- Prior art keywords
- network
- breast
- frame image
- module
- breast cancer
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 33
- 206010006187 Breast cancer Diseases 0.000 title claims abstract description 32
- 208000026310 Breast neoplasm Diseases 0.000 title claims abstract description 32
- 238000002604 ultrasonography Methods 0.000 claims abstract description 65
- 210000000481 breast Anatomy 0.000 claims abstract description 57
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims description 41
- 238000000605 extraction Methods 0.000 claims description 18
- 230000003902 lesion Effects 0.000 claims description 16
- 210000005075 mammary gland Anatomy 0.000 claims description 11
- 238000011176 pooling Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000007636 ensemble learning method Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- ZOKXTWBITQBERF-UHFFFAOYSA-N Molybdenum Chemical compound [Mo] ZOKXTWBITQBERF-UHFFFAOYSA-N 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 229910052750 molybdenum Inorganic materials 0.000 description 2
- 239000011733 molybdenum Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000004195 computer-aided diagnosis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 201000010759 hypertrophy of breast Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 210000000779 thoracic wall Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0825—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the breast, e.g. mammography
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30068—Mammography; Breast
Abstract
The invention discloses a breast cancer diagnosis method based on breast ultrasound video sequence data, which is characterized in that a breast ultrasound single-frame image sequence is obtained by preprocessing the ultrasound video sequence data, compared with the traditional ultrasound image, the breast cancer diagnosis method has more information content, and the breast cancer diagnosis method is combined with a computer technology and a deep learning method to realize end-to-end positioning diagnosis of breast cancer, so that the information of ultrasound video data is utilized to the maximum extent, effective second opinions are provided for the diagnosis of doctors, and the working efficiency of the doctors is improved.
Description
Technical Field
The invention relates to the field of ultrasonic video diagnosis, in particular to a breast cancer diagnosis device and method based on ultrasonic video.
Background
There are currently three major screening methods for breast cancer: digital mammary gland molybdenum target X-ray, clinical mammary gland examination and mammary gland B-ultrasonic examination. The digital mammary gland molybdenum target X-ray examination has the advantages of high resolution, accurate detection of the mass which can not be touched by hands, good diagnosis effect on fat type breasts and large breasts of obese patients, and easy neglect of compact mammary glands and focus attached to the chest wall. Clinical breast examination has the advantages of low detection cost, no damage, convenience and the like, but misdiagnosis and missed diagnosis are easily caused, and further regular reexamination is often needed. The breast B-ultrasonic examination is an important tool for clinically detecting and diagnosing breast cancer, and has the advantages of strong authenticity, good intuition, easy mastering, convenient diagnosis and the like, wherein the breast ultrasonic video sequence contains larger information amount compared with an ultrasonic image.
The computer-aided diagnosis based on the medical image utilizes the computer technology and the deep learning method to analyze the medical image, can provide effective second opinion for the clinical diagnosis of doctors and assist the disease diagnosis of the doctors. With the increasing maturity of deep learning technology, the deep learning technology is widely used in various fields, and detection and classification technology based on the deep learning method is being applied to the field of medical images. The traditional target detection and classification is mainly applied to natural images, while the background noise of medical images is complex, and the gray level images make the traditional target detection and classification method difficult to obtain good results. The invention is mainly based on breast ultrasound video sequence data, and combines computer technology and deep learning method to automatically position and diagnose the focus area in the breast ultrasound video sequence.
Accordingly, those skilled in the art have made efforts to develop an apparatus for diagnosing breast cancer based on an ultrasonic video and a method thereof.
Disclosure of Invention
In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is how to automatically locate and diagnose a lesion region in a breast ultrasound video sequence based on the breast ultrasound video sequence data by combining a computer technology and a deep learning method.
In order to achieve the above object, the present invention provides a breast cancer diagnosis method based on an ultrasound video, which is characterized by comprising the following steps:
(1) acquiring mammary gland ultrasonic video sequence data from a B ultrasonic equipment terminal;
(2) preprocessing the breast ultrasound video sequence data into breast ultrasound single-frame image sequence data according to a given frame rate;
(3) respectively extracting a characteristic diagram from the breast ultrasound single-frame image sequence by using a characteristic extraction network and a focus detection network, and detecting a focus area;
(4) and adopting an ensemble learning method to carry out ensemble learning on all breast ultrasound single-frame images of the detected focus region to make a judgment diagnosis and obtain an auxiliary diagnosis result.
Furthermore, a rectangular frame is marked on the breast ultrasound single-frame image sequence label, and a breast tumor focus is in the rectangular frame.
Further, the specific process of step (3) includes:
(a) extracting the characteristics of the breast ultrasound single-frame image sequence by using a characteristic extraction network to obtain a characteristic diagram of the breast ultrasound single-frame image sequence;
(b) and (3) using a focus detection network to carry out focus region positioning on the characteristic image of the breast ultrasound single-frame image sequence, and detecting the focus region of the breast ultrasound single-frame image sequence.
Further, the feature extraction network is a pre-training VGG16 network, the pre-training VGG16 network performs layer-by-layer feature mapping on the input breast ultrasound single-frame image sequence data, and the feature map required by the focus detection network is output after multilayer convolution and pooling processing.
Further, the feature extraction network adopts a pre-trained VGG16 network, the original VGG16 network is used for a natural image classification task, the last maximum pooling layer and three full-connection layers for classification are removed on the basis of the original network, the rest convolution layers are reserved for feature extraction, and a feature map for inputting the lesion detection network is obtained.
Furthermore, the focus detection network is a Faster R-CNN network, and the Faster R-CNN network generates a target region for a feature map of the input single-frame image sequence data so as to detect the focus region of the breast ultrasound single-frame image sequence.
Further, the step of detecting the focus area by the focus detection network is to firstly generate the category of the network judgment anchor by using the candidate area and calculate the predicted value of the frame, and then detect the focus area of the single frame image by combining the information of the feature map and the region of interest
Further, in the step (4), a voling, Adaboost or other ensemble learning algorithm is specifically adopted to carry out ensemble learning on all breast ultrasound single-frame images of the identified lesion area to make a judgment diagnosis, so as to obtain an auxiliary diagnosis result.
The invention also provides a breast cancer diagnosis device based on ultrasonic video, which is characterized by comprising an ultrasonic video acquisition module, a video sequence input module, a focus detection module and a diagnosis distinguishing module, wherein the ultrasonic video acquisition module is connected with the video sequence input module, the video sequence input module is connected with the focus detection module, the focus detection module is connected with the diagnosis distinguishing module,
wherein, the ultrasonic video acquisition module acquires mammary gland ultrasonic video sequence data from a B ultrasonic equipment terminal,
the video sequence input module preprocesses the breast ultrasound video sequence data into breast ultrasound single-frame image sequence data according to a given frame rate,
the focus detection module uses the pre-trained feature extraction network and the focus detection network to respectively extract feature maps of the breast ultrasound single-frame image sequence and detect focus areas,
the judgment and diagnosis module adopts an ensemble learning method to carry out ensemble learning on all breast ultrasonic single-frame images of the detected focus region to make judgment and diagnosis so as to obtain an auxiliary diagnosis result.
Furthermore, the ultrasonic video acquisition module, the video sequence input module, the lesion detection module and the judgment and diagnosis module all comprise a processor and a storage medium, and the processor runs computer program codes in the storage medium to execute the steps.
Technical effects
Compared with the prior art, the breast cancer diagnosis method based on the breast ultrasound video sequence data has the advantages that the breast cancer is diagnosed based on the breast ultrasound video sequence data, the breast ultrasound single-frame image sequence is obtained by preprocessing the ultrasound video sequence data, compared with the traditional ultrasound image, the breast cancer diagnosis method based on the breast ultrasound video sequence data contains more information, the end-to-end positioning diagnosis of the breast cancer is realized by combining the computer technology and the deep learning method, the information of the ultrasound video data is utilized to the maximum extent, the effective second opinion is provided for the diagnosis of doctors, and the working efficiency of the doctors is improved.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 is a flow chart of a method for diagnosing breast cancer based on ultrasound video according to a preferred embodiment of the present invention;
fig. 2 is a system block diagram of an ultrasound video-based breast cancer diagnosis apparatus.
Detailed Description
The technical contents of the preferred embodiments of the present invention will be more clearly and easily understood by referring to the drawings attached to the specification. The present invention may be embodied in many different forms of embodiments and the scope of the invention is not limited to the embodiments set forth herein.
As shown in fig. 1, the method for diagnosing breast cancer based on ultrasound video of this embodiment includes the following steps:
step (1), collecting mammary gland ultrasonic video sequence data from a B ultrasonic equipment end;
step (2), reading in breast ultrasound video sequence data in a video form, and then preprocessing according to a given framing frequency to obtain a breast ultrasound single-frame image sequence;
step (3), adopting a pre-training feature extraction network to extract the features of the single-frame image sequence, sending the feature map obtained after multilayer convolution and pooling into a focus detection network, and detecting the focus area of the single-frame image sequence;
and (4) performing ensemble learning on all breast ultrasonic single-frame images of the identified focus region by using Voting, Adaboost or other ensemble learning algorithms to make a judgment diagnosis, and obtaining an auxiliary diagnosis result.
The breast ultrasound video sequence data of the invention is acquired by experienced clinicians from the side of the B-mode ultrasound equipment. After breast ultrasound video sequence data are input, preprocessing the video sequence data according to the framing frequency of a given single-frame image to obtain a single-frame image sequence. Then, according to the clinical prior knowledge of a doctor, a rectangular frame label is marked on the focus region of the single-frame image sequence.
The invention uses two networks in the focus area detection process of the breast ultrasound video sequence, which are respectively a feature extraction network and a focus detection network, and the input breast ultrasound single-frame image sequence is processed by the feature extraction network and the focus detection network in sequence. The feature extraction network adopts a pre-trained VGG16 network, the original VGG16 network is used for a natural image classification task, the last maximum pooling layer and three full-connection layers used for classification are removed on the basis of the original network, the rest convolutional layers are reserved for feature extraction, and a feature map used for inputting a lesion detection network is obtained. The focus detection network adopts an Faster R-CNN network, firstly uses a candidate region generation network to judge the category of an anchor and calculates the predicted value of a frame, and then detects the focus region of a single-frame image by combining a feature map and the information of an interested region.
As shown in fig. 2, the breast cancer diagnosis apparatus of the present invention includes an ultrasound video acquisition module 1, a video sequence input module 2, a lesion detection module 3 and a diagnosis discrimination module 4. The ultrasonic video acquisition module 1 is connected with the video sequence input module 2, the video sequence input module 2 is connected with the focus detection module 3, and the focus detection module 3 is connected with the judgment and diagnosis module 4. The ultrasonic video acquisition module 1 acquires mammary gland ultrasonic video sequence data from a B ultrasonic equipment terminal. The video sequence input module 2 preprocesses the breast ultrasound video sequence data into breast ultrasound single-frame image sequence data according to a given frame rate. The focus detection module 3 uses a pre-trained feature extraction network and a focus detection network to respectively extract feature maps of the breast ultrasound single-frame image sequence and detect a focus area. The discrimination diagnosis module 4 performs ensemble learning on all breast ultrasound single-frame images of the detected focus region to make discrimination diagnosis and obtain an auxiliary diagnosis result.
The ultrasound video acquisition module 1, the video sequence input module 2, the lesion detection module 3 and the diagnosis discriminating module 4 each include a processor and a storage medium, and the processor runs computer program codes in the storage medium to execute the steps of the breast cancer diagnosis method based on the ultrasound video.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. A breast cancer diagnosis method based on ultrasonic video is characterized by comprising the following steps:
(1) acquiring mammary gland ultrasonic video sequence data from a B ultrasonic equipment terminal;
(2) preprocessing the breast ultrasound video sequence data into breast ultrasound single-frame image sequence data according to a given frame rate;
(3) respectively extracting a feature map from the breast ultrasound single-frame image sequence by using a feature extraction network and a focus detection network, and detecting a focus area;
(4) and adopting an ensemble learning method to carry out ensemble learning on all breast ultrasound single-frame images of the detected focus region to make a judgment diagnosis and obtain an auxiliary diagnosis result.
2. The method of claim 1, wherein the breast ultrasound single-frame image sequence label is labeled with a rectangular frame, and a breast tumor focus is located in the rectangular frame.
3. The method for diagnosing breast cancer according to claim 1, wherein the specific process of step (3) comprises:
(a) extracting the characteristics of the breast ultrasound single-frame image sequence by using a characteristic extraction network to obtain a characteristic diagram of the breast ultrasound single-frame image sequence;
(b) and (3) using a focus detection network to carry out focus region positioning on the feature map of the breast ultrasound single-frame image sequence, and detecting the focus region of the breast ultrasound single-frame image sequence.
4. The breast cancer diagnosis method according to claim 3, wherein the feature extraction network is a pre-trained VGG16 network, the pre-trained VGG16 network performs layer-by-layer feature mapping on the input breast ultrasound single frame image sequence data, and outputs a feature map required by the lesion detection network after multilayer convolution and pooling.
5. The breast cancer diagnosis method according to claim 4, wherein the feature extraction network adopts a pre-trained VGG16 network, the original VGG16 network is used for a natural image classification task, the last maximum pooling layer and three full-link layers for classification are removed on the basis of the original network, the rest convolution layers are reserved for feature extraction, and a feature map for inputting a lesion detection network is obtained.
6. The breast cancer diagnosis method according to claim 3, wherein the lesion detection network is a Faster R-CNN network, and the Faster R-CNN network generates a target region for a feature map of the input single frame image sequence data, thereby detecting a lesion region of the breast ultrasound single frame image sequence.
7. The breast cancer diagnosis method as claimed in claim 6, wherein the lesion detection network detects a lesion region by first generating a network judgment anchor class using the candidate region and calculating a predicted value of a frame, and then detecting the lesion region of the single frame image by combining the feature map and information of the region of interest.
8. The breast cancer diagnosis method according to claim 1, wherein in the step (4), the voing, Adaboost or other ensemble learning algorithm is specifically adopted to perform ensemble learning on all breast ultrasound single-frame images of the identified lesion region to make a judgment diagnosis, so as to obtain an auxiliary diagnosis result.
9. A breast cancer diagnosis device based on ultrasonic video is characterized by comprising an ultrasonic video acquisition module, a video sequence input module, a focus detection module and a diagnosis distinguishing module, wherein the ultrasonic video acquisition module is connected with the video sequence input module, the video sequence input module is connected with the focus detection module, the focus detection module is connected with the diagnosis distinguishing module,
wherein the ultrasonic video acquisition module acquires mammary gland ultrasonic video sequence data from a B ultrasonic equipment terminal,
the video sequence input module preprocesses the breast ultrasound video sequence data into breast ultrasound single-frame image sequence data according to a given frame rate,
the focus detection module respectively extracts a feature map from the breast ultrasound single-frame image sequence by using a pre-trained feature extraction network and a focus detection network to detect a focus area,
the judging and diagnosing module adopts an integrated learning method to carry out integrated learning on all breast ultrasonic single-frame images of detected focus regions to carry out judging and diagnosing so as to obtain an auxiliary diagnosis result.
10. The breast cancer diagnostic apparatus according to claim 9, wherein the ultrasound video acquisition module, the video sequence input module, the lesion detection module and the discriminant diagnosis module each comprise a processor and a storage medium, and the processor executes computer program code in the storage medium to perform the steps of claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010689889.4A CN112002407A (en) | 2020-07-17 | 2020-07-17 | Breast cancer diagnosis device and method based on ultrasonic video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010689889.4A CN112002407A (en) | 2020-07-17 | 2020-07-17 | Breast cancer diagnosis device and method based on ultrasonic video |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112002407A true CN112002407A (en) | 2020-11-27 |
Family
ID=73467053
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010689889.4A Pending CN112002407A (en) | 2020-07-17 | 2020-07-17 | Breast cancer diagnosis device and method based on ultrasonic video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112002407A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112641466A (en) * | 2020-12-31 | 2021-04-13 | 北京小白世纪网络科技有限公司 | Ultrasonic artificial intelligence auxiliary diagnosis method and device |
CN113536964A (en) * | 2021-06-25 | 2021-10-22 | 合肥合滨智能机器人有限公司 | Classification extraction method of ultrasonic videos |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108961215A (en) * | 2018-06-05 | 2018-12-07 | 上海大学 | Parkinson's disease assistant diagnosis system and method based on Multimodal medical image |
CN109300121A (en) * | 2018-09-13 | 2019-02-01 | 华南理工大学 | A kind of construction method of cardiovascular disease diagnosis model, system and the diagnostic model |
CN110349141A (en) * | 2019-07-04 | 2019-10-18 | 复旦大学附属肿瘤医院 | A kind of breast lesion localization method and system |
CN111291789A (en) * | 2020-01-19 | 2020-06-16 | 华东交通大学 | Breast cancer image identification method and system based on multi-stage multi-feature deep fusion |
-
2020
- 2020-07-17 CN CN202010689889.4A patent/CN112002407A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108961215A (en) * | 2018-06-05 | 2018-12-07 | 上海大学 | Parkinson's disease assistant diagnosis system and method based on Multimodal medical image |
CN109300121A (en) * | 2018-09-13 | 2019-02-01 | 华南理工大学 | A kind of construction method of cardiovascular disease diagnosis model, system and the diagnostic model |
CN110349141A (en) * | 2019-07-04 | 2019-10-18 | 复旦大学附属肿瘤医院 | A kind of breast lesion localization method and system |
CN111291789A (en) * | 2020-01-19 | 2020-06-16 | 华东交通大学 | Breast cancer image identification method and system based on multi-stage multi-feature deep fusion |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112641466A (en) * | 2020-12-31 | 2021-04-13 | 北京小白世纪网络科技有限公司 | Ultrasonic artificial intelligence auxiliary diagnosis method and device |
CN113536964A (en) * | 2021-06-25 | 2021-10-22 | 合肥合滨智能机器人有限公司 | Classification extraction method of ultrasonic videos |
CN113536964B (en) * | 2021-06-25 | 2023-09-26 | 合肥合滨智能机器人有限公司 | Classification extraction method for ultrasonic video |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108898595B (en) | Construction method and application of positioning model of focus region in chest image | |
CN107480677B (en) | Method and device for identifying interest region in three-dimensional CT image | |
AU2004252917B2 (en) | CAD (computer-aided decision) support for medical imaging using machine learning to adapt CAD process with knowledge collected during routine use of CAD system | |
CN109727243A (en) | Breast ultrasound image recognition analysis method and system | |
CN112086197B (en) | Breast nodule detection method and system based on ultrasonic medicine | |
JP2020524018A (en) | System and method for integrating tomographic image reconstruction and radiomics using neural networks | |
CN111553892B (en) | Lung nodule segmentation calculation method, device and system based on deep learning | |
US20120014578A1 (en) | Computer Aided Detection Of Abnormalities In Volumetric Breast Ultrasound Scans And User Interface | |
KR20200133593A (en) | Ai-automatic ultrasound diagnosis apparatus for liver steatosis and remote medical-diagnosis method using the same | |
CN111227864A (en) | Method and apparatus for lesion detection using ultrasound image using computer vision | |
JP2009516551A (en) | Quantitative and qualitative computer-aided analysis method and system for medical images | |
CN111028206A (en) | Prostate cancer automatic detection and classification system based on deep learning | |
CN101103924A (en) | Galactophore cancer computer auxiliary diagnosis method based on galactophore X-ray radiography and system thereof | |
McDermott et al. | Sonographic diagnosis of COVID-19: A review of image processing for lung ultrasound | |
KR102531400B1 (en) | Artificial intelligence-based colonoscopy diagnosis supporting system and method | |
CN114782307A (en) | Enhanced CT image colorectal cancer staging auxiliary diagnosis system based on deep learning | |
WO2022110525A1 (en) | Comprehensive detection apparatus and method for cancerous region | |
CN112002407A (en) | Breast cancer diagnosis device and method based on ultrasonic video | |
CN112071418B (en) | Gastric cancer peritoneal metastasis prediction system and method based on enhanced CT image histology | |
CN112545562A (en) | Multimodal multiparameter breast cancer screening system, device and computer storage medium | |
CN110738633B (en) | Three-dimensional image processing method and related equipment for organism tissues | |
CN114998674A (en) | Device and method for tumor focus boundary identification and grade classification based on contrast enhanced ultrasonic image | |
CN103262070A (en) | Generation of Pictorial Reporting Diagrams of Lesions In Anatomical Structures | |
KR20230097646A (en) | Artificial intelligence-based gastroscopy diagnosis supporting system and method to improve gastro polyp and cancer detection rate | |
CN115409812A (en) | CT image automatic classification method based on fusion time attention mechanism |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201127 |