Colon image recognition method and device and related equipment

Abstract

The invention discloses a colon image recognition method. The method comprises the steps of obtaining a to-be-detected colon image; detecting the colon image to be detected through a single-target detector to obtain a first detection result; wherein the detection target of the single-target detector is polyp tissue; detecting the colon image to be detected through a multi-target detector to obtaina second detection result; wherein the detection target of the multi-target detector comprises polyp tissue and interference tissue; determining polyp information in the colon image to be detected according to the first detection result and the second detection result. The colon image recognition method can effectively improve the accuracy of colon polyp recognition. The invention further discloses a colon image recognition device, colon image recognition equipment and a computer readable storage medium, which all have the above beneficial effects.

Description

technical field [0001] The present application relates to the field of image processing, in particular to a colon image recognition method, and also relates to a colon image recognition device, equipment, and computer-readable storage medium. Background technique [0002] At present, colon cancer has become a major killer of human beings. According to clinical experience, more than 90% of colon cancers are transformed from colon polyps. Early diagnosis and removal of colon polyps are the most effective way to prevent colon cancer. Colonoscopy is the most effective way to prevent colon cancer. It is considered to be the most effective method for detecting colon polyps, because it can examine the intact colon and can effectively remove the polyps found. Therefore, it is of great practical significance to study colonic polyp detection methods based on colonoscopy video. [0003] At present, researchers have proposed a variety of traditional methods to detect colon polyps, such...

AI Technical Summary

Problems solved by technology

[0003] At present, researchers have proposed a variety of traditional methods to detect colon polyps, such as using color information or texture information or geometric information as features, and using traditional machine learning methods to distinguish normal areas from colon polyp areas. However, the morphology of colon polyps different, and are interfered by other non-polyp areas in the colon, such as air bubbles, impurities, etc. Therefore, it is often difficult to accurately detect colon polyps based on the above-mentioned traditional features, and the false detection rate is high

Images