Method for increasing adenomatous polyp detection rate of colonoscope based on deep learning

Abstract

The invention discloses a method for increasing the adenomatous polyp detection rate of a colonoscope based on deep learning. The method comprises the following steps: dividing a video stream transmitted by an enteroscope lens in an operating table into two parts, transmitting one part of the video stream to an operation platform of a doctor, preprocessing the other part of the video stream, and sending the preprocessed video stream to a polyp detection model embedded into an enteroscope operating system for identification; allowing the polyp detection model to detect whether polyps appear ineach frame of image and the appearing probability of polyps; and returning a detection result of the polyp detection model to the operation platform of the doctor for displaying, and if polyps appearin the video stream, framing the polyps for prompting. By means of an artificial intelligence deep neural network, polyps appearing in a lens in the operation process of colonoscopy can be automatically detected, a polyp recognition rate in colonoscopy examination process is increased, and therefore, the adenomatous polyp detection rate is indirectly increased.

Description

technical field [0001] The invention relates to the technical field of colonoscopy adenomatous polyps detection, in particular to a method for improving the detection rate of colonoscopy adenomatous polyps based on deep learning. Background technique [0002] Polyp refers to the diseased tissue that protrudes or protrudes on the surface of the intestinal cavity mucosa. With the help of colonoscopy, the size and number of polyps can be detected. According to pathological classification, polyps are divided into inflammatory polyps, hyperplastic polyps, hamartoma, adenomatous polyps, etc. Among them, adenomatous polyps are the most common, accounting for about 70%-80%, and the size is generally about 0.5-2cm. The canceration of adenomatous polyps is not only related to its pathological type, but it is generally believed that the size and number of adenomas have a great influence on the possibility of canceration. The canceration rate of adenomatous polyps less than 1cm is al...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to address the technical defects existing in the prior art, and provide a method based on deep learning to improve the detection rate of adenomatous polyps in colonoscopy, which is used to solve the problem of relying on manual detection of polyps in the traditional colonoscopy process , it is easy to miss the problem due to the negligence of doctors or the small size of polyps

Images