Endoscope image processing method and device, electronic equipment and storage medium

Abstract

The invention discloses an endoscopic image processing method and device, electronic equipment and storage medium. The method comprises the steps of obtaining an endoscopic image sent by an endoscopic terminal by a cloud; performing anomaly identification processing on the endoscopic image by using an image identification network to obtain an identification result; sending the identification result to an endoscope terminal. According to the method, the endoscope terminal does not need to process the endoscope image, so that the hardware requirement on the endoscope terminal can be reduced, the cost of the endoscope terminal is reduced, and the endoscope terminal can be widely applied; through the cooperation of the cloud and the plurality of endoscope terminals, the endoscope terminals can be widely applied, the film reading workload is effectively reduced, the efficiency is improved, and the auxiliary diagnosis and treatment of an artificial intelligence system in primary hospitals can be effectively promoted.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to an endoscopic image processing method, an endoscopic image processing device, electronic equipment, and a computer-readable storage medium. Background technique [0002] The incidence of digestive tract diseases is relatively high in the world, especially with the weakening of various body functions, middle-aged and elderly people have become a group with a higher incidence of digestive tract diseases. In my country, most of the inspections for digestive tract diseases are completed in primary hospitals. Capsule endoscopy is convenient and has low physical requirements for middle-aged and elderly people. It is suitable for the examination of any gastrointestinal symptoms. It has no side effects and is non-invasive. However, in the process of digestive tract examination with capsule endoscopy, a large amount of image data will be generated, ranging from a f...

AI Technical Summary

Problems solved by technology

However, medical artificial intelligence systems often require the cooperation of strong GPU (Graphics Processing Unit, graphics processing unit) hardware or professional high-performance computing chips and other hardware, and the equipment procurement costs of these hardware are relatively high, and grassroots hospitals seldom purchase them. It has caused great resistance to promoting the auxiliary diagnosis and treatment of artificial intelligence systems in grassroots hospitals

Images