Method for pylorus and ileocecal valve positioning through wireless capsule endoscope images

Abstract

The invention discloses a method for pylorus and ileocecal valve positioning through wireless capsule endoscope images. When a wireless capsule endoscope is used for examination, the starting point and the stopping point of the small intestine are accurately found so that the workload of a doctor for viewing the images can be reduced, and missed diagnosis is reduced. According to the method, a deep learning thought serves as a technical core, a transfer learning strategy is also used, and a convolution neural network algorithm in a deep learning model is used for building an area image classifier; features of the wireless capsule endoscope images are obtained through automatic learning by means of training of the model, and then an area image identification result sequence is analyzed through an area positioning algorithm, so that pylorus and ileocecal valve positioning in the wireless capsule endoscope images is achieved. The method makes up for the blank of an existing capsule endoscope in the field of intelligent identification and accurate positioning, the working intensity of a doctor is greatly reduced, the working efficiency and the diagnosis rate are improved, the practicalvalue of the capsule endoscope in the clinical diagnosis of digestive tract diseases is further promoted, and a more efficient and more standard diagnosis mode is formed.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for locating pylorus and ileocecal valve in a wireless capsule endoscope image. Background technique [0002] At present, conventional hand-held endoscopy in clinical application cannot involve the entire digestive tract. Gastroscopy can examine the upper digestive tract, while colonoscopy can only examine the colon and rectum, so there are still parts of the intestinal tract that conventional endoscopes cannot detect. and arrived. In recent years, with the development of science and technology, Wireless Capsule Endoscopy (WCE) has been widely used clinically, and has gradually become the mainstream technology for doctors to detect intestinal lesions. Usually, the patient swallows the capsule endoscope from the mouth, and through the peristalsis of the gastrointestinal tract, the capsule endoscope stays in the body for about 8 hours and takes images...

AI Technical Summary

Problems solved by technology

[0003] However, wireless capsule endoscopy will generate a large amount of image data, and each patient will generate at least 50,000 data images after the examination

Images