CN111863234A - Intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning - Google Patents
Intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning Download PDFInfo
- Publication number
- CN111863234A CN111863234A CN201910339426.2A CN201910339426A CN111863234A CN 111863234 A CN111863234 A CN 111863234A CN 201910339426 A CN201910339426 A CN 201910339426A CN 111863234 A CN111863234 A CN 111863234A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- lesion
- treatment
- intestinal
- image
- 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 47
- 230000003902 lesion Effects 0.000 title claims abstract description 47
- 238000013135 deep learning Methods 0.000 title claims abstract description 19
- 210000001035 gastrointestinal tract Anatomy 0.000 title claims abstract description 9
- 230000036285 pathological change Effects 0.000 claims abstract description 23
- 231100000915 pathological change Toxicity 0.000 claims abstract description 23
- 230000003903 intestinal lesions Effects 0.000 claims abstract description 14
- 230000000968 intestinal effect Effects 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims abstract description 9
- 238000002372 labelling Methods 0.000 claims abstract description 5
- 238000010827 pathological analysis Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007781 pre-processing Methods 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
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Endoscopes (AREA)
Abstract
The invention discloses an intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning, which comprises the following units: the system comprises an image acquisition unit, a lesion diagnosis and treatment calibration unit and an intelligent auxiliary processing unit, wherein the image acquisition unit is used for acquiring an intestinal image of a patient with intestinal lesion, the intestinal original image is directly input into the intelligent auxiliary processing unit, and the intelligent auxiliary unit displays the image in real time; when the pathological change diagnosis and treatment is labeled, a labeling picture is presented, the pathological change diagnosis and treatment calibration unit comprises a training set and a YOLO model, a large number of pathological change pictures are obtained under enteroscope equipment, and a pathological change training set is generated; and inputting the generated lesion training set into a YOLO model, and finally training the YOLO model to generate a lesion diagnosis and treatment calibration unit with a lesion recognition function. The method and the system can provide real-time pathological change diagnosis and treatment calibration for an endoscopist during diagnosis, and improve the accuracy of diagnosis.
Description
Technical Field
The invention relates to the field of deep learning and intelligent medical treatment, in particular to an intestinal lesion diagnosis and treatment calibration auxiliary system based on deep learning.
Background
Intestinal lesions have various forms and extremely similar appearances, so that missed identification often occurs in diagnosis and treatment of the intestinal lesions. In this case, young endoscopists need to learn many years to get well-mastered skills, which brings great challenges to the clinical diagnosis of endoscopists. For patients, intestinal lesions cannot be self-detected.
A deep learning algorithm is introduced, and a high-efficiency enteroscopy lesion calibration auxiliary technology is created by combining medical enteroscopy lesion data and medical knowledge, so that effective assistance is provided for doctors, and lesion missing of doctors is reduced, namely the intestinal lesion diagnosis and treatment calibration auxiliary technology based on deep learning.
Intestinal lesions are various in types and different in forms, the common method is to artificially summarize lesion features and formulate rules, and the features of the intestinal lesions are identified and calibrated according to the rules through the traditional image processing technology, but the features of the intestinal lesions are extremely complex, and the manually summarized features cannot cover all the lesions. Most of the existing markets adopt the traditional image processing technology to identify and label lesions, and the identification precision is low and the time delay is high.
In view of this, this application provides an intestinal pathological change diagnoses demarcation auxiliary system based on deep learning.
Disclosure of Invention
The invention aims to provide an intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning.
In order to achieve the purpose of the invention, the invention provides an intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning, which comprises the following units:
an image acquisition unit, a lesion diagnosis and treatment calibration unit and an intelligent auxiliary processing unit,
the image acquisition unit is used for acquiring an intestinal image of a patient with intestinal lesion, the intestinal original image is directly input into the intelligent auxiliary processing unit, and the intelligent auxiliary unit displays the image in real time; when the pathological diagnosis and treatment are labeled, a labeling picture is presented,
the pathological change diagnosis and treatment calibration unit comprises a training set and a YOLO model, and a large number of pathological change pictures are obtained under enteroscope equipment to generate a pathological change training set; and inputting the generated lesion training set into a YOLO model, and finally training the YOLO model to generate a lesion diagnosis and treatment calibration unit with a lesion recognition function.
The intelligent auxiliary processing unit comprises screenshot, video recording, pathological change diagnosis and treatment calibration and diagnosis and treatment report functions, and a doctor can perform screenshot and video recording on an enteroscope image and generate a corresponding diagnosis and treatment report after diagnosis and treatment are finished.
Compared with the prior art, the invention has the advantages that,
1. the auxiliary technology for diagnosing and treating the pathological changes identifies and classifies the intestinal pathological changes by applying deep learning, calibrates the corresponding pathological changes, and provides a calibrated result for a doctor to refer, so that pathological change missing of the doctor is reduced, and the accuracy of diagnosing and treating the intestinal pathological changes is greatly improved.
2. The auxiliary technology for diagnosing and treating the pathological changes introduces a deep learning algorithm, takes data as drive, and autonomously learns the characteristics of the pathological changes, so that the technology can more accurately identify the pathological changes, greatly improve the identification precision and reduce the time delay. Meanwhile, the deep learning algorithm can be quickly positioned, identified and calibrated under the high-frequency lesion target, missing recognition is greatly reduced, and when doctors examine intestinal lesions, effective lesion auxiliary prompt is provided, missing recognition of the doctors is effectively reduced, and the health of patients is also protected.
Drawings
Fig. 1 is a schematic diagram of the intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It should be noted that "connected" and words used in this application to express "connected," such as "connected," "connected," and the like, include both direct connection of one element to another element and connection of one element to another element through another element.
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 example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when used in this specification the singular forms "a", "an" and/or "the" include "specify the presence of stated features, steps, operations, elements, or modules, components, and/or combinations thereof, unless the context clearly indicates otherwise.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Spatially relative terms, such as "above … …", "above … …", "above … …", "above", and the like, may be used herein for ease of description to describe the spatial relationship of one component or module or feature to another component or module or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations of the component or module in use or operation in addition to the orientation depicted in the figures. For example, if a component or module in the figures is turned over, components or modules described as "above" or "above" other components or modules or configurations would then be oriented "below" or "beneath" the other components or modules or configurations. Thus, the exemplary term "above … …" can include both an orientation of "above … …" and "below … …". The components or modules may also be oriented in other different ways (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Fig. 1 is a schematic diagram of the intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning according to the present invention.
The system comprises an image acquisition unit, a pathological change diagnosis and treatment calibration unit and an intelligent auxiliary processing unit.
The image acquisition unit is used for acquiring an intestinal image of a patient with intestinal pathological changes, and when the diagnosis and treatment calibration function is not started, the intestinal original image is directly input into the intelligent auxiliary processing unit, and the image is presented in real time by the intelligent auxiliary processing unit; after the diagnosis and treatment calibration function is started, the intestinal tract images are preprocessed and enter the lesion diagnosis and treatment calibration unit, and the images after lesion diagnosis and treatment calibration are input into the intelligent auxiliary processing unit to be displayed in real time.
The pathological diagnosis and treatment calibration unit comprises a training set and a YOLO model. Acquiring a large number of pathological change pictures under enteroscope equipment, carrying out preprocessing such as rotation and picture enhancement to improve the diversity of data sets, and carrying out diagnosis and labeling by an authoritative doctor to generate a pathological change training set; and inputting the generated lesion training set into a YOLO model, extracting the features of the lesions by learning the lesions and the labels through the YOLO model, updating the weight parameters through iteration, and finally training to generate a lesion diagnosis and treatment calibration unit with a lesion recognition function.
The intelligent auxiliary processing unit comprises screenshot, video recording, lesion diagnosis and treatment calibration and diagnosis and treatment report functions, and when the lesion diagnosis and treatment calibration is not started, a doctor can perform screenshot and video recording on an original image of the enteroscope; when the lesion diagnosis and treatment calibration is started, a doctor can capture a screenshot of a lesion diagnosis and treatment calibration image and record a video of the lesion diagnosis and treatment calibration image, and a corresponding diagnosis and treatment report is generated after diagnosis and treatment are finished.
The lesion recognition is mainly realized by a deep learning YOLO algorithm, the algorithm is mainly used for carrying out probability estimation on lesion targets through learning on lesion features during recognition, the class with higher probability is a model calibration class, and a calibration result is provided for doctors to refer.
In the actual use process, classification and labeling are carried out on the obtained intestinal lesion data through a front-line expert of a mainstream hospital, the obtained data can be strictly examined, privacy of patients is removed, and a new training set is used for retraining the YOLO algorithm, so that the identification accuracy of the YOLO model is improved. With the continuous expansion of data sets, the deep learning parameters are continuously updated, which is equivalent to that all hospitals jointly perfect the auxiliary technology for diagnosing, diagnosing and calibrating intestinal lesions, and finally the auxiliary technology reaches the expert level.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (3)
1. The utility model provides an intestinal pathological change diagnoses marks auxiliary system based on deep learning which characterized in that, the system includes following unit:
an image acquisition unit, a lesion diagnosis and treatment calibration unit and an intelligent auxiliary processing unit,
the image acquisition unit is used for acquiring an intestinal image of a patient with intestinal lesion, the intestinal original image is directly input into the intelligent auxiliary processing unit, and the intelligent auxiliary unit displays the image in real time; when the pathological diagnosis and treatment are labeled, a labeling picture is presented,
the lesion diagnosis and treatment calibration unit comprises a training set and a training model, and a large number of lesion pictures are acquired under enteroscope equipment to generate a lesion training set; and inputting the generated lesion training set into a training model, and finally training the training model to generate a lesion diagnosis and treatment calibration unit with a lesion recognition function.
2. The system of claim 1, wherein the training model is a YOLO model.
3. The intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning of claim 1, wherein the intelligent auxiliary processing unit comprises functions of screenshot, video recording, lesion diagnosis and treatment calibration and diagnosis and treatment report, and a doctor can perform screenshot and video recording on an enteroscope image and generate a corresponding diagnosis and treatment report after diagnosis and treatment are finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910339426.2A CN111863234A (en) | 2019-04-25 | 2019-04-25 | Intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910339426.2A CN111863234A (en) | 2019-04-25 | 2019-04-25 | Intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111863234A true CN111863234A (en) | 2020-10-30 |
Family
ID=72951278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910339426.2A Pending CN111863234A (en) | 2019-04-25 | 2019-04-25 | Intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111863234A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112802010A (en) * | 2021-02-25 | 2021-05-14 | 吉林大学珠海学院 | Cancer cell detection method, system and medium based on deep learning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107369151A (en) * | 2017-06-07 | 2017-11-21 | 万香波 | System and method are supported in GISTs pathological diagnosis based on big data deep learning |
| CN108288506A (en) * | 2018-01-23 | 2018-07-17 | 雨声智能科技（上海）有限公司 | A kind of cancer pathology aided diagnosis method based on artificial intelligence technology |
| CN109411084A (en) * | 2018-11-28 | 2019-03-01 | 武汉大学人民医院（湖北省人民医院） | A kind of intestinal tuberculosis assistant diagnosis system and method based on deep learning |
| CN109447987A (en) * | 2018-11-28 | 2019-03-08 | 武汉大学人民医院（湖北省人民医院） | Ulcerative colitis assistant diagnosis system and method under colonoscopy based on deep learning |
| CN109615633A (en) * | 2018-11-28 | 2019-04-12 | 武汉大学人民医院（湖北省人民医院） | Crohn disease assistant diagnosis system and method under a kind of colonoscopy based on deep learning |
-
2019
- 2019-04-25 CN CN201910339426.2A patent/CN111863234A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107369151A (en) * | 2017-06-07 | 2017-11-21 | 万香波 | System and method are supported in GISTs pathological diagnosis based on big data deep learning |
| CN108288506A (en) * | 2018-01-23 | 2018-07-17 | 雨声智能科技（上海）有限公司 | A kind of cancer pathology aided diagnosis method based on artificial intelligence technology |
| CN109411084A (en) * | 2018-11-28 | 2019-03-01 | 武汉大学人民医院（湖北省人民医院） | A kind of intestinal tuberculosis assistant diagnosis system and method based on deep learning |
| CN109447987A (en) * | 2018-11-28 | 2019-03-08 | 武汉大学人民医院（湖北省人民医院） | Ulcerative colitis assistant diagnosis system and method under colonoscopy based on deep learning |
| CN109615633A (en) * | 2018-11-28 | 2019-04-12 | 武汉大学人民医院（湖北省人民医院） | Crohn disease assistant diagnosis system and method under a kind of colonoscopy based on deep learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112802010A (en) * | 2021-02-25 | 2021-05-14 | 吉林大学珠海学院 | Cancer cell detection method, system and medium based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6947759B2 (en) | Systems and methods for automatically detecting, locating, and semantic segmenting anatomical objects | |
| US20220172828A1 (en) | Endoscopic image display method, apparatus, computer device, and storage medium | |
| Zhang et al. | Surgical tools detection based on modulated anchoring network in laparoscopic videos | |
| CN112614128B (en) | System and method for assisting biopsy under endoscope based on machine learning | |
| CN108171738B (en) | Multi-modal medical image registration method based on brain function template | |
| WO2017030747A1 (en) | Reconstruction with object detection for images captured from a capsule camera | |
| TWI569764B (en) | Method and system for recognizing multiple instruments during minimally invasive surgery | |
| Nurmaini et al. | Accurate detection of septal defects with fetal ultrasonography images using deep learning-based multiclass instance segmentation | |
| CN111091559A (en) | Depth learning-based auxiliary diagnosis system for small intestine sub-scope lymphoma | |
| CN111950388B (en) | Vulnerable plaque tracking and identifying system and method | |
| CN110742690A (en) | Method for configuring endoscope and terminal equipment | |
| CN110427994A (en) | Digestive endoscope image processing method, device, storage medium, equipment and system | |
| CN108814717A (en) | surgical robot system | |
| CN112801958A (en) | Ultrasonic endoscope, artificial intelligence auxiliary identification method, system, terminal and medium | |
| CN112614571A (en) | Neural network model training method and device, image classification method and medium | |
| CN115082448A (en) | Method and device for scoring cleanliness of intestinal tract and computer equipment | |
| CN111863234A (en) | Intestinal tract lesion diagnosis and treatment calibration auxiliary system based on deep learning | |
| CN116797889B (en) | Updating method and device of medical image recognition model and computer equipment | |
| Song et al. | Combining deep learning with geometric features for image-based localization in the Gastrointestinal tract | |
| US20210182568A1 (en) | Methods for improved operative surgical report generation using machine learning and devices thereof | |
| Ali et al. | Pneumonia Detection Using Chest Radiographs With Novel EfficientNetV2L Model | |
| CN110197722B (en) | AI-CPU system platform | |
| Liu et al. | Towards surgical tools detection and operative skill assessment based on deep learning | |
| CN111047582A (en) | Crohn's disease auxiliary diagnosis system under enteroscope based on degree of depth learning | |
| Kyrollos et al. | Transfer learning approaches for neonate head localization from pressure images |
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 | ||
| CB02 | Change of applicant information |
Address after: 300457 s1405, s1404, s1414, s1415 and s1424, experimental building 14, Tianjin International Joint Research Institute of biomedicine, 220 Dongting Road, Binhai New Area Economic and Technological Development Zone, Tianjin Applicant after: Tianjin Yujin artificial intelligence Medical Technology Co.,Ltd. Address before: Unit 80, room n212, experimental building, Tianjin International Joint Research Institute of biomedicine, 220 Dongting Road, Tianjin Economic and Technological Development Zone, Binhai New Area, Tianjin Applicant before: Tianjin Yujin artificial intelligence Medical Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240131 Address after: No. 402, Gate 2, Building 1, Shunning Lane, Hongqi South Road, Nankai District, Tianjin, 300000 Applicant after: Yang Guozhen Country or region after: China Address before: 300457 s1405, s1404, s1414, s1415 and s1424, experimental building 14, Tianjin International Joint Research Institute of biomedicine, 220 Dongting Road, Binhai New Area Economic and Technological Development Zone, Tianjin Applicant before: Tianjin Yujin artificial intelligence Medical Technology Co.,Ltd. Country or region before: China |
|
| TA01 | Transfer of patent application right |