Enteroscopy Crohn's disease auxiliary diagnosis system and method based on deep learning

Abstract

The invention discloses an enteroscopy Crohn's disease auxiliary diagnosis system and method based on deep learning. The system comprises an enteroscopy image automatic acquisition subsystem, a database, a client and a server. The enteroscope image automatic acquisition subsystem is used for acquiring an enteroscope image; wherein the database comprises a sample set for training the convolutionalneural network; and the client is used for uploading the enteroscopy image acquired by the enteroscopy image automatic acquisition subsystem to the server, and receiving and displaying an analysis result fed back by the server. According to the method, an image recognition technology is utilized to monitor an endoscope video in real time, images containing key organ parts and suspicious Crohn focus areas are automatically collected, and after global preferences are made according to a weighting algorithm, whether the image is Crohn disease or not is diagnosed. According to the method, after the neural network model is utilized to automatically screen the images, the most valuable image can be extracted from the global video, auxiliary diagnosis is given, and more reliable and efficient support is provided for doctors to diagnose.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and relates to a medical endoscope image recognition system and method, in particular to a system and method for auxiliary diagnosis of Crohn's disease under colonoscopy based on deep learning. Background technique [0002] With the continuous development and maturity of deep learning algorithms, it has been gradually used in the field of medical image analysis. Endoscopic images are an important basis for doctors to analyze patients' digestive tract diseases. In recent years, a variety of methods for screening and diagnosing lesions using deep convolutional neural network models have been developed, which is of great clinical significance in the current colonoscopy diagnosis system. [0003] Crohn's disease is a discontinuous full-thickness inflammation, and its colonoscopy shows segmental or skipping, not continuous; longitudinal or fissure ulcers can be formed; lesions involve the wh...

AI Technical Summary

Problems solved by technology

[0005] The present invention mainly solves the problem that the traditional colonoscopy report system relies on manual image collection, which is prone to missing the blind spot of site inspection and suspicious lesion area. It uses image recognition technology to monitor endoscopic video in real time, and automatically collects key organ sites and suspicious lesions. The image of the lesion area will be selected globally according to the weighted algorithm, and then saved in the colonoscopy reporting system, and the diagnosis of Crohn's disease will be given at the same time

Images