CN109584229A - A kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method - Google Patents
A kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method Download PDFInfo
- Publication number
- CN109584229A CN109584229A CN201811431019.6A CN201811431019A CN109584229A CN 109584229 A CN109584229 A CN 109584229A CN 201811431019 A CN201811431019 A CN 201811431019A CN 109584229 A CN109584229 A CN 109584229A
- Authority
- CN
- China
- Prior art keywords
- image
- ercp
- duodenofiberscope
- client
- server
- 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
Classifications
-
- 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
- G06T2207/10068—Endoscopic 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
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method, system includes client, server-side, database;ERCP image is acquired by client, identification classification is carried out in deep learning model after the ERCP image input training that will acquire, corresponding image information (including duodenofiberscope and nipple opening identification, medical diagnosis on disease) is obtained, and is timely feedbacked to client.The present invention can help doctor to determine duodenofiberscope and nipple aperture position, improve successful intubation;In addition it can also assist doctor to carry out the diagnosis of disease, prevent Misdiagnosis, improve accuracy rate of diagnosis and working efficiency.
Description
Technical field
The invention belongs to image identification technical field, it is related to a kind of assistant diagnosis system and method, and in particular to Yi Zhongji
In the real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method of deep learning.
Background technique
Endoscopic retrograde cholangio-pancreatiography art (ERCP, Endoscopic Retrograde
It Cholangiopancreatography) is to inject contrast agent through Duodenal papilla cannula under scope, thus display of driving in the wrong direction
The shadowgraph technique of pancreatic duct is the gold of the current clinically diseases of pancreaticobiliary duct such as diagnosing and treating choledocholithiasis, obstructive jaundice
Standard.Wherein, completing the precondition that ERCP is checked is to find duodenofiberscope and nipple opening, and successful intubation, so
Recognize that duodenofiberscope and nipple aperture position are particularly significant.But the knowledge figure experience and subjective factor of doctor refer to determining 12
There is large effect at intestines nipple and nipple opening position.In addition, pancreatic duct starts to develop after injection contrast agent, doctor observes disease
Become, the experience and state of doctor also will affect the accuracy rate of medical diagnosis on disease.
Deep learning is the important breakthrough that artificial intelligence field obtains nearly ten years, with powerful learning ability and efficiently
Feature representation ability, can by the study of big data, extract characteristics of image classify to it.We by deep learning with
ERCP inspection combines, and constructs convolutional neural networks model, and auxiliary doctor is special to duodenofiberscope and nipple opening and disease
The differentiation of sign.In addition, we increase target detection technique, picture is divided to come, identifies duodenofiberscope and nipple
After opening, duodenofiberscope is irised out in time and nipple opening, guidance doctor are intubated, improves successful intubation.
Summary of the invention
The technical problem to be solved by the present invention is providing a kind of Endoscopic retrograde cholangio-pancreatiography art based on deep learning
Real-time assistant diagnosis system and method, analyze ERCP image using deep learning, before intubation, auxiliary doctor identification ten
Two duodenum 12 nipples and nipple aperture position;After injecting contrast agent, auxiliary doctor carries out disease to the developed image of the pancreatic duct of shooting
Disease diagnosis.The present invention improves the accuracy rate that doctor is intubated accuracy and medical diagnosis on disease.
Technical solution used by system of the invention is: a kind of real-time auxiliary diagnosis of Endoscopic retrograde cholangio-pancreatiography art
System, it is characterised in that: including client, server-side, database;
The client is connected with ERCP equipment, will by network for obtaining current ERCP equipment acquired image
Image uploads to the server-side, and receives and show the analysis result that server-side is fed back;
The server-side judges whether contain ten in image according to the image for the ERCP equipment acquisition that client is sent
Two duodenum 12 nipples and nipple are open, if it exists the position, and the duodenofiberscope and nipple opening position in image are positioned,
Iris out the range of duodenofiberscope and nipple opening;It identifies image lesion characteristics, assists diagnosis;Result is fed back into visitor
Family end;
The database, the analysis result for storing the ERCP equipment acquired image, server-side is fed back.
Technical solution used by method of the invention is: a kind of real-time auxiliary diagnosis of Endoscopic retrograde cholangio-pancreatiography art
Method, which comprises the following steps:
Step 1: client obtains current ERCP equipment acquired image, and is uploaded to server-side;
Step 2: server-side receives ERCP image, and using image as parameter, calls trained convolutional neural networks mould
Type is identified: identification duodenofiberscope and nipple opening, if it exists the position, to the duodenofiberscope and cream in picture
Head opening position is positioned, and the range of duodenofiberscope and nipple opening is irised out;Identify ERCP image lesion characteristics, auxiliary
Diagnosis;
Step 3: client receives and shows analysis result;
Step 4: operator carries out next step operation according to the analysis result that client is shown.
The invention has the benefit that the Endoscopic retrograde cholangio-pancreatiography art of the invention based on deep learning is auxiliary in real time
Auxiliary diagnosis method and system can assist doctor accurately to find the position of duodenofiberscope and nipple opening before doctor's intubation
It sets, improves successful intubation;After injecting contrast agent, pancreatic duct develops, and doctor can be assisted to diagnose disease, improves
The accuracy and validity of inspection.The present invention both provided safeguard for patient health, avoided Misdiagnosis;Also save doctor's
Time energy.
Detailed description of the invention
Fig. 1 is the system construction drawing of the embodiment of the present invention;
Fig. 2 is the method flow diagram of the embodiment of the present invention;
Fig. 3 is the convolutional neural networks model training flow chart of the embodiment of the present invention.
Specific embodiment
Understand for the ease of those of ordinary skill in the art and implement the present invention, with reference to the accompanying drawings and embodiments to this hair
It is bright to be described in further detail, it should be understood that implementation example described herein is merely to illustrate and explain the present invention, not
For limiting the present invention.
Referring to Fig.1, a kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art provided by the invention, including visitor
Family end, server-side, database, communication module;
Client is provided at least one, is connected with ERCP equipment, for obtaining current ERCP equipment acquired image,
Image is uploaded into server-side by network, and receives and show the analysis result that server-side is fed back;
Server-side, according to the image for the ERCP equipment acquisition that client is sent, judges image for using J2EE framework
In whether be open containing duodenofiberscope and nipple, the position if it exists, duodenofiberscope and nipple opening in image
Position is positioned, and the range of duodenofiberscope and nipple opening is irised out;It identifies image lesion characteristics, assists diagnosis;
Result is fed back into client.
Client and server-side are connected with communication module, divide for transmiting a request to server-side, and from server-side acquisition
Analysis is as a result, be implemented as http communication mode.
Database, the analysis result for storing ERCP equipment acquired image, server-side is fed back.Database is
It helps machine to be learnt, enables it to judge whether it is duodenofiberscope and cream according to given photo in application
Head opening and lesion characteristics.What is learnt is more, and it is more accurate to judge, so in the application, the picture obtained when will also check
Database, enlarged sample amount is added by the qualified picture of screening.
The server-side of the present embodiment includes sample database, convolutional neural networks model and web service module;
Sample database, including duodenofiberscope and nipple opening image library, ERCP lesion image data base are used respectively
In storage duodenofiberscope and nipple opening image and ERCP lesion image;Lesion ERCP image include calculus lesion image,
Cancer lesion image and other lesion images, are stored by Array for structural body.
Convolutional neural networks model, including according to duodenofiberscope and nipple opening image library, ERCP lesion picture number
According to two models that library training obtains, it is respectively used to identification duodenofiberscope and nipple opening and ERCP lesion characteristics;
Web service unit, using the ERCP image received as input parameter, is called for receiving the request of client
Convolutional neural networks model carries out duodenofiberscope and the identification of nipple opening and ERCP lesion characteristics is classified, and will obtain
Analysis result feeds back to client.
See Fig. 2, a kind of real-time aided diagnosis method of Endoscopic retrograde cholangio-pancreatiography art provided by the invention, including with
Lower step:
Step 1: client obtains current ERCP equipment acquired image, and is uploaded to server-side;
Step 2: server-side receives ERCP image, and using image as parameter, calls trained convolutional neural networks mould
Type is identified;
Then call trained convolutional neural networks model to be identified: identification duodenofiberscope and nipple are opened first
Mouthful, the position if it exists, for convenience of the subsequent intubation of doctor, in picture duodenofiberscope and nipple be open position into
The range of duodenofiberscope and nipple opening is irised out in row positioning;After injecting contrast agent, pancreatic duct development identifies ERCP image
Lesion characteristics assist diagnosis;
Trained convolutional neural networks model in the present embodiment is using training subset, training convolutional neural networks mould
Type obtains trained convolutional neural networks model;Training subset belongs to ERCP training set of images, and (training centrally stored is existing
Some doctors carry out the mark patient check image of disease or duodenofiberscope), each training subset includes ERCP image
And corresponding lesion characteristics.
The convolutional neural networks model that the present embodiment uses is the image library that is open according to duodenofiberscope and nipple,
Obtained two models of ERCP lesion image data base training, be respectively used to ERCP image duodenofiberscope position judgement and
The identification of lesion characteristics is classified;VGG-16, Resnet-50, DenseNet. may be selected in model, is developed using Python, envelope
It is called after dressing up RESTful API (network interface of REST style) by other modules.In the present embodiment, to convolutional neural networks
Model selects without limitation, and when concrete application can constantly adjust selection best model according to test result.Convolutional neural networks mould
The training process of type is as shown in Figure 3.
In the present embodiment, ERCP image lesion characteristics include cancer lesion, calculus lesion, other lesions.Here, needing strong
It adjusts, " cancer lesion, calculus lesion, other lesions " mentioned in the present embodiment are not the diagnosis to disease, are only made
For the feature in picture, it can be understood as a parameter, and be aspect ratio pair to picture to their judgement and identification.
In the present embodiment, after identifying duodenofiberscope and nipple opening position, using target detection technique, iris out
Duodenofiberscope and nipple opening position.The object detection and recognition algorithm suggested based on region can be used in target detection technique
It is realized with based on the object detection and recognition algorithm of recurrence.It is irised out using the object detection and recognition algorithm suggested based on region
The step of duodenofiberscope and nipple beginning position includes: that treated that image carries out figure to described by convolutional neural networks
As feature extraction;Candidate region is generated according to described image feature;Duodenofiberscope and cream are carried out according to the candidate region
Head beginning target detection and zone location.Duodenofiberscope and cream are irised out using the object detection and recognition algorithm based on recurrence
The step of head beginning position includes: to carry out image characteristics extraction to treated the image using convolutional layer, by connecting entirely
Layer carries out target detection and zone location to duodenofiberscope and nipple beginning.In the present embodiment, specific limit is not done to algorithm
It is fixed.
Step 3: client receives and shows analysis result;
Step 4: operator carries out next step operation according to the analysis result that client is shown.
It should be understood that the part that this specification does not elaborate belongs to the prior art.
It should be understood that the above-mentioned description for preferred embodiment is more detailed, can not therefore be considered to this
The limitation of invention patent protection range, those skilled in the art under the inspiration of the present invention, are not departing from power of the present invention
Benefit requires to make replacement or deformation under protected ambit, fall within the scope of protection of the present invention, this hair
It is bright range is claimed to be determined by the appended claims.
Claims (8)
1. a kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art, it is characterised in that: including client, service
End, database;
The client is connected with ERCP equipment, for obtaining current ERCP equipment acquired image, by network by image
The server-side is uploaded to, and receives and show the analysis result that server-side is fed back;
The server-side judges whether refer to containing 12 in image according to the image for the ERCP equipment acquisition that client is sent
Intestines nipple and nipple are open, if it exists the position, and the duodenofiberscope and nipple opening position in image are positioned, and iris out
The range of duodenofiberscope and nipple opening;It identifies image lesion characteristics, assists diagnosis;Result is fed back into client
End;
The database, the analysis result for storing the ERCP equipment acquired image, server-side is fed back.
2. the real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art according to claim 1, it is characterised in that: institute
Stating server-side includes sample database, convolutional neural networks model and web service module;
The sample database, including duodenofiberscope and nipple opening image library, ERCP lesion image data base are used respectively
In storage duodenofiberscope and nipple opening image and ERCP lesion image;
The convolutional neural networks model, including according to duodenofiberscope and nipple opening image library, ERCP lesion picture number
According to two models that library training obtains, it is respectively used to identification duodenofiberscope and nipple opening and ERCP lesion characteristics;
The Web service unit, using the ERCP image received as input parameter, is called for receiving the request of client
Convolutional neural networks model carries out duodenofiberscope and the identification of nipple opening and ERCP lesion characteristics is classified, and will obtain
Analysis result feeds back to client.
3. the real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art described in -2 any one according to claim 1,
Be characterized in that: the system also includes communication module, the client and server-side are connected with communication module, and communication module is used
It is requested in realizing that client is sent to server-side, and obtains analysis result from server-side.
4. a kind of real-time aided diagnosis method of Endoscopic retrograde cholangio-pancreatiography art, which comprises the following steps:
Step 1: client obtains current ERCP equipment acquired image, and is uploaded to server-side;
Step 2: server-side receives ERCP image, and using image as parameter, call trained convolutional neural networks model into
Row identification: identification duodenofiberscope and nipple opening, the position if it exists, in picture duodenofiberscope and nipple open
Oral area position is positioned, and the range of duodenofiberscope and nipple opening is irised out;It identifies ERCP image lesion characteristics, assists doctor
Diagnosis;
Step 3: client receives and shows analysis result;
Step 4: operator carries out next step operation according to the analysis result that client is shown.
5. the real-time aided diagnosis method of Endoscopic retrograde cholangio-pancreatiography art according to claim 4, it is characterised in that: step
Trained convolutional neural networks model described in rapid 2 is using training subset, and training convolutional neural networks model is instructed
The convolutional neural networks model perfected;The training subset belongs to ERCP training set of images, and each training subset includes ERCP figure
Picture and corresponding lesion characteristics;The training it is centrally stored be that existing doctor carries out disease or duodenofiberscope
Mark patient's check image.
6. the real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art according to claim 4, it is characterised in that: step
ERCP image lesion characteristics described in rapid 2 includes cancer lesion, calculus lesion and other lesions.
7. the real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art according to claim 4, it is characterised in that: step
In rapid 2, after identifying duodenofiberscope and nipple opening position, using target detection technique, duodenofiberscope is irised out
And nipple opening position.
8. the real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art according to claim 4, it is characterised in that: step
In rapid 2, first after injection contrast agent, so that pancreatic duct is developed, then identify ERCP image lesion characteristics, assist diagnosis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811431019.6A CN109584229A (en) | 2018-11-28 | 2018-11-28 | A kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811431019.6A CN109584229A (en) | 2018-11-28 | 2018-11-28 | A kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109584229A true CN109584229A (en) | 2019-04-05 |
Family
ID=65925222
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811431019.6A Pending CN109584229A (en) | 2018-11-28 | 2018-11-28 | A kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109584229A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110214747A (en) * | 2019-06-17 | 2019-09-10 | 郑州大学第一附属医院 | A kind of novel mouse original position cholangiocarcinoma model and its method for building up |
CN110570407A (en) * | 2019-08-29 | 2019-12-13 | 上海联影智能医疗科技有限公司 | image processing method, storage medium and computer device |
CN111415564A (en) * | 2020-03-02 | 2020-07-14 | 武汉大学 | Pancreatic ultrasonic endoscopy navigation method and system based on artificial intelligence |
CN111666998A (en) * | 2020-06-03 | 2020-09-15 | 电子科技大学 | Endoscope intelligent intubation decision-making method based on target point detection |
CN112652393A (en) * | 2020-12-31 | 2021-04-13 | 山东大学齐鲁医院 | ERCP quality control method, system, storage medium and equipment based on deep learning |
CN114176775A (en) * | 2022-02-16 | 2022-03-15 | 武汉大学 | Calibration method, device, equipment and medium for ERCP selective bile duct intubation |
CN114209289A (en) * | 2022-02-22 | 2022-03-22 | 武汉大学 | Automatic evaluation method, automatic evaluation device, electronic equipment and storage medium |
CN114612475A (en) * | 2022-05-12 | 2022-06-10 | 青岛美迪康数字工程有限公司 | Bile duct support specification selection method and device |
CN115944276A (en) * | 2023-02-22 | 2023-04-11 | 武汉大学人民医院(湖北省人民医院) | Common bile duct fibrosis grade determining method and device and related equipment |
WO2024095673A1 (en) * | 2022-11-04 | 2024-05-10 | 富士フイルム株式会社 | Medical assistance device, endoscope, medical assistance method, and program |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9378551B2 (en) * | 2013-01-03 | 2016-06-28 | Siemens Aktiengesellschaft | Method and system for lesion candidate detection |
CN107610773A (en) * | 2017-09-12 | 2018-01-19 | 北京即刻叁维数据科技股份有限公司 | A kind of vascular dissection aided diagnosis method based on sustainer medical image |
CN108257129A (en) * | 2018-01-30 | 2018-07-06 | 浙江大学 | The recognition methods of cervical biopsy region aids and device based on multi-modal detection network |
CN108510482A (en) * | 2018-03-22 | 2018-09-07 | 姚书忠 | Cervical carcinoma detection method, device, equipment and medium based on gynecatoptron image |
CN108695001A (en) * | 2018-07-16 | 2018-10-23 | 武汉大学人民医院(湖北省人民医院) | A kind of cancer lesion horizon prediction auxiliary system and method based on deep learning |
-
2018
- 2018-11-28 CN CN201811431019.6A patent/CN109584229A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9378551B2 (en) * | 2013-01-03 | 2016-06-28 | Siemens Aktiengesellschaft | Method and system for lesion candidate detection |
CN107610773A (en) * | 2017-09-12 | 2018-01-19 | 北京即刻叁维数据科技股份有限公司 | A kind of vascular dissection aided diagnosis method based on sustainer medical image |
CN108257129A (en) * | 2018-01-30 | 2018-07-06 | 浙江大学 | The recognition methods of cervical biopsy region aids and device based on multi-modal detection network |
CN108510482A (en) * | 2018-03-22 | 2018-09-07 | 姚书忠 | Cervical carcinoma detection method, device, equipment and medium based on gynecatoptron image |
CN108695001A (en) * | 2018-07-16 | 2018-10-23 | 武汉大学人民医院(湖北省人民医院) | A kind of cancer lesion horizon prediction auxiliary system and method based on deep learning |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110214747A (en) * | 2019-06-17 | 2019-09-10 | 郑州大学第一附属医院 | A kind of novel mouse original position cholangiocarcinoma model and its method for building up |
CN110570407A (en) * | 2019-08-29 | 2019-12-13 | 上海联影智能医疗科技有限公司 | image processing method, storage medium and computer device |
CN111415564B (en) * | 2020-03-02 | 2022-03-18 | 武汉大学 | Pancreatic ultrasonic endoscopy navigation method and system based on artificial intelligence |
CN111415564A (en) * | 2020-03-02 | 2020-07-14 | 武汉大学 | Pancreatic ultrasonic endoscopy navigation method and system based on artificial intelligence |
CN111666998A (en) * | 2020-06-03 | 2020-09-15 | 电子科技大学 | Endoscope intelligent intubation decision-making method based on target point detection |
CN111666998B (en) * | 2020-06-03 | 2022-04-22 | 电子科技大学 | Endoscope intelligent intubation decision-making method based on target point detection |
CN112652393A (en) * | 2020-12-31 | 2021-04-13 | 山东大学齐鲁医院 | ERCP quality control method, system, storage medium and equipment based on deep learning |
CN114176775A (en) * | 2022-02-16 | 2022-03-15 | 武汉大学 | Calibration method, device, equipment and medium for ERCP selective bile duct intubation |
CN114176775B (en) * | 2022-02-16 | 2022-05-10 | 武汉大学 | Calibration method, device, equipment and medium for ERCP selective bile duct intubation |
CN114209289A (en) * | 2022-02-22 | 2022-03-22 | 武汉大学 | Automatic evaluation method, automatic evaluation device, electronic equipment and storage medium |
CN114612475A (en) * | 2022-05-12 | 2022-06-10 | 青岛美迪康数字工程有限公司 | Bile duct support specification selection method and device |
CN114612475B (en) * | 2022-05-12 | 2022-09-23 | 青岛美迪康数字工程有限公司 | Bile duct support specification selection method and device |
WO2024095673A1 (en) * | 2022-11-04 | 2024-05-10 | 富士フイルム株式会社 | Medical assistance device, endoscope, medical assistance method, and program |
CN115944276A (en) * | 2023-02-22 | 2023-04-11 | 武汉大学人民医院(湖北省人民医院) | Common bile duct fibrosis grade determining method and device and related equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109584229A (en) | A kind of real-time assistant diagnosis system of Endoscopic retrograde cholangio-pancreatiography art and method | |
CN109190540B (en) | Biopsy region prediction method, image recognition device, and storage medium | |
KR102243830B1 (en) | System for providing integrated medical diagnostic service and method thereof | |
CN108553081B (en) | Diagnosis system based on tongue fur image | |
CN108695001A (en) | A kind of cancer lesion horizon prediction auxiliary system and method based on deep learning | |
CN109117890B (en) | Image classification method and device and storage medium | |
CN107368859A (en) | Training method, verification method and the lesion pattern recognition device of lesion identification model | |
CN111214255B (en) | Medical ultrasonic image computer-aided method | |
CN109447987A (en) | Ulcerative colitis assistant diagnosis system and method under colonoscopy based on deep learning | |
CN109859827A (en) | Gastrointestinal Endoscopes operation horizontal points-scoring system and method in real time | |
US20210059758A1 (en) | System and Method for Identification, Labeling, and Tracking of a Medical Instrument | |
CN109614995A (en) | The system and method for pancreatic duct and pancreas structure is identified under a kind of endoscopic ultrasonography | |
CN110742690A (en) | Method for configuring endoscope and terminal equipment | |
CN117322865B (en) | Temporal-mandibular joint disc shift MRI (magnetic resonance imaging) examination and diagnosis system based on deep learning | |
CN116188466B (en) | Method and device for determining in-vivo residence time of medical instrument | |
CN109493340A (en) | Esophagus fundus ventricularis varication assistant diagnosis system and method under a kind of gastroscope | |
CN117524402A (en) | Method for analyzing endoscope image and automatically generating diagnostic report | |
CN117011892A (en) | Ultrasonic image automatic analysis and diagnosis system based on deep learning | |
WO2023095208A1 (en) | Endoscope insertion guide device, endoscope insertion guide method, endoscope information acquisition method, guide server device, and image inference model learning method | |
CN114240934B (en) | Image data analysis method and system based on acromegaly | |
CN115035086A (en) | Intelligent tuberculosis skin test screening and analyzing method and device based on deep learning | |
KR20220122312A (en) | Artificial intelligence-based gastroscopy diagnosis supporting system and method | |
CN112614103A (en) | Bronchoscope image feature comparison marking system and method based on deep learning | |
CN111035403A (en) | Scanning opportunity determination method, device, equipment and storage medium | |
CN116364265B (en) | Medical endoscope image optimization system and method |
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 |
Application publication date: 20190405 |
|
RJ01 | Rejection of invention patent application after publication |