Endoscope report generation device and method, electronic equipment and readable storage medium

Abstract

The invention discloses an endoscope report generation device and method, electronic equipment and a computer readable storage medium, and the device comprises an image obtaining module which is used for obtaining a plurality of endoscope images; a recognition module used for inputting the endoscopic image into the image recognition model to obtain a plurality of target images; an information acquisition module used for extracting corresponding report information from a preset knowledge graph based on the target image; a report generation module used for selecting a representative image in the target image and generating an endoscope report by utilizing the representative image and the report information; the device can automatically generate the endoscopic report corresponding to the endoscopic image, reduces the manual viewing and screening of a huge number of endoscopic images, can reduce the film reading workload and duration required for viewing the endoscopic images, and improves the efficiency.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to an endoscopic report generation device, an endoscopic report generation method, electronic equipment, and a computer-readable storage medium. Background technique [0002] Capsule endoscopy is capsule endoscopy, which is used for digestive tract examination. Its non-invasive and painless features make people get rid of the pain and discomfort caused by traditional gastrointestinal endoscopy. It is a new method of digestive tract examination. During the digestive tract examination with a capsule endoscope, a large amount of image data will be generated, ranging from a few thousand (such as gastric examination) to tens of thousands (such as small intestine examination). A large amount of capsule endoscopic image data needs to be checked manually to determine whether it can represent the situation in the human body, so as to obtain corresponding information ba...

AI Technical Summary

Problems solved by technology

A large amount of capsule endoscopic image data needs to be checked manually to determine whether it can represent the situation in the human body, so as to obtain corresponding information based on it, which makes the reading workload heavy and time-consuming

[0003] Therefore, the problems of large workload and long time-consuming for image reading in related technologies are technical problems that need to be solved by those skilled in the art.

Images