Intelligent auxiliary evaluation system for enteroscope operation skills

Abstract

The invention provides an intelligent auxiliary evaluation system for enteroscope operation skills, and belongs to the field of medical and industrial combination. The system comprises: an acquisition module, which is used for acquiring small sample eye movement data when an operator performs enteroscopy operation on an endoscope simulation training system; a construction module which is used for extracting space-time eye movement features of the learners and the clinicians in the enteroscopy operation process according to the obtained eye movement data; an identification module which is used for establishing three eye movement feature learning models based on meta learning, a long-short-term memory neural network and a full convolutional neural network, training the three eye movement feature learning models by utilizing the established space-time eye movement features, and realizing classification identification of the enteroscopy operation skills of the operator; and an evaluation module which is used for performing integrated evaluation on skill identification results obtained by the three eye movement feature learning models to obtain a final enteroscope operation skill evaluation result. By adopting the system and the method, intelligent and accurate evaluation of the enteroscope operation skills of the operator can be realized.

Description

technical field [0001] The invention relates to the field of medical-industrial integration based on artificial intelligence and deep learning, in particular to an intelligent auxiliary evaluation system for colonoscopy operation skills. Background technique [0002] In recent years, with the rapid development of virtual reality technology, colonoscopy practice teaching has gradually abandoned the traditional model based on first-line clinical cognition, imitation, operation and improvement, and gradually transformed into a "patient-oriented" immersive teaching mode. , interactive, multi-sensory and other characteristics of virtual reality colonoscopy simulation training method. At present, CAE, AccuTouch, BDS and many other brands of endoscopic simulation training systems based on virtual reality technology have gradually entered the field of colonoscopy practice teaching in my country, effectively alleviating the shortage of colonoscopy training physician resources and the...

AI Technical Summary

Problems solved by technology

[0003] However, in the current operation evaluation of the existing endoscopic simulation training system, most of the endoscopic insertion success rate, lesion discovery rate, endoscopic navigation and use strategy, maintenance of endoscopic visual field clarity, overall inspection quality, and overall score of endoscopic skills The "result-oriented" overall statistical evaluation is the evaluation standard of learners' operational skills, while the "learner-centered" acquisition status evaluation is ignored, and the objective and intelligent auxiliary evaluation methods based on deep learning technology are even rarer.

In general, in the streamlined construction of the endoscopist training system based on colonoscopy simulation training, the level of intelligent, standardized and fine colonoscopy operation skill evaluation needs to be further improved

Images