Auxiliary diagnosis system and method for esophageal and gastric varicosity under a gastroscope

Abstract

The invention discloses an auxiliary diagnosis system and method for esophageal and gastric varices under a gastroscope. The system comprises a video receiving module, a convolutional neural network module, a result reporting module and a database module, the video receiving module is used for receiving the image acquired by the gastroscope equipment and calling the convolutional neural network module to identify; the convolutional neural network module is used for judging the image qualification and grading and judging the focus; the result reporting module is used for recording each judgmentresult of the convolutional neural network module, after the gastroscopy is completed at this time, sorting is carried out according to the confidence degree and the image quality, and N images containing suspicious focuses and corresponding varicosity grading results are output; and the database module is used for storing images acquired by the gastroscope equipment, and the convolutional neuralnetwork module is used for identifying results. According to the method, the most valuable image can be extracted from the global video, varicosity classification is carried out on the focus image, 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 system and method for auxiliary diagnosis of esophageal and gastric varices under gastroscope, in particular to a system and method for auxiliary diagnosis of esophageal and gastric varices under gastroscope based on deep learning. Background technique [0002] Acute gastrointestinal bleeding is a common complication in digestive system diseases. Among them, rupture and bleeding of esophageal or gastric varices caused by decompensated liver cirrhosis is particularly troublesome and often life-threatening. Therefore, accurate diagnosis and judgment of treatment efficacy very important. At present, gastroscopy is the most convenient and effective method for diagnosing esophageal and gastric varices, and the grading of esophageal and gastric varices is helpful to understand the critical condition. During the endoscopic operation, the clinician judges the suspicious lesion...

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problem of manually collecting images of gastric varices and manually judging the inaccurate classification of esophageal and gastric varices, the present invention provides a system and method based on deep learning for the auxiliary diagnosis of esophageal and gastric varices under gastroscope

Images