Gastroscope-operation real-time auxiliary system and method based on deep learning

Abstract

The invention provides a gastroscope-operation real-time auxiliary system based on deep learning. The system comprises at least one client and a service end, wherein the client is used for monitoringand uploading a gastroscope image collected by current gastroscope equipment through a network, and receiving and displaying a feedback analysis result; and the service end uses an REST configurationto instantly determine a position corresponding to the gastroscope image and a position characteristic according to the gastroscope image collected from the client and feeds back an analysis result tothe client. The service end includes a sample database, a convolution neural network model and a web service module. In the invention, image quality identification, position identification and position characteristic identification are performed on the collected image and identification results are displayed on the client; a reliable reference basis is provided for an operator; detection accuracyand validity are increased; the system is simple and is easy to use; and a condition that a patient suffers twice because of an unsuccessful check is avoided.

Description

technical field [0001] The invention belongs to the field of medical detection assistance, and in particular relates to a real-time assistance system and method for gastroscope operation based on deep learning. Background technique [0002] In order to improve the detection rate of early gastric cancer, a large-scale general survey is necessary, and the main method at present is gastroscopy. Therefore, there are often long queues in front of the gastroenterology department of the hospital, and the proficiency and judgment accuracy of the operating doctors are raised Very demanding. For patients, gastroscopy is not easy. In addition to fasting for at least 6 hours before the examination, the pain caused by intubation also daunts many patients. [0003] Usually, a complete gastroscopy report needs to include at least 31 pictures of 10 parts of oropharynx, esophagus, cardia, gastric fundus, gastric body, gastric angle, gastric antrum, pylorus, duodenal bulb and descending part...

AI Technical Summary

Problems solved by technology

The former requires the patient to go through a painful examination again, which not only wastes the time and money of the patient, but also wastes the testing resources of the hospital; while the latter will put the patient's life in danger

Images