Digestive endoscopy image abnormal feature real-time labeling system and method

Abstract

The invention discloses a digestive endoscopy image abnormal feature real-time labeling system and method. The system comprises an image acquisition module, an image preprocessing module, a model training module, an anomaly detection module and a label display module; the model training module comprises an image data set, a classification model training unit and a detection model training unit. Classification information of suspicious stomach precancerous diseases is acquired through a deep learning CNN classification model, and a target detection model is utilized to quickly and accurately acquire the focus position by means of deep learning CNN and on the basis of a regression method. By using the method, stomach abnormal features are effectively classified and detected under digestive endoscopy, the missed diagnosis rate on the basis of long-time and subjective diagnosis of doctors can be reduced, real-time analysis and real-time suspicious focus display under an endoscope are supported when the doctors conduct endoscopic tests, the working burden of the doctors is reduced, and the efficiency of medical diagnosis work is improved.

Description

technical field [0001] The invention belongs to the field of medical data mining, in particular to a real-time marking system and method for abnormal features of digestive endoscope images. Background technique [0002] There are 405,000 new gastric cancer cases and 325,000 deaths each year in my country, accounting for 42.6% and 45.0% of the global total respectively. Reducing the incidence and mortality of gastric cancer in my country is an urgent public health problem. Clinical studies have shown that the prognosis of gastric cancer is closely related to the treatment effect. For patients with advanced gastric cancer (advanced gastric cancer, AGC), even if they receive surgery-based gastric cancer resection, the postoperative five-year survival rate of the patient is still lower than 30%, and the postoperative quality of life of the patient is low. It is a huge burden on the family and society. If patients receive endoscopic examination and treatment in time in the earl...

AI Technical Summary

Problems solved by technology

CNN is widely used in image feature extraction and classification detection, especially CNN for object detection based on candidate regions. Its recognition accuracy has been continuously improved, but due to the requirement of millions of model training parameters, the time performance is low, and it is difficult to meet the requirements of Requirements for real-time detection of gastroscope images in gastroscope video scenarios

Images