Knowledge distillation with a class-aware loss for endoscopic disease detection

TL;DR

This paper introduces a class-aware knowledge distillation framework to enhance endoscopic disease detection, significantly reducing missed lesions and improving localization accuracy in challenging GI images.

Contribution

It proposes a novel end-to-end student-teacher learning approach with class-aware loss, improving detection performance and generalization in endoscopic disease detection tasks.

Findings

Achieved higher mean average precision on EDD2020 and Kvasir-SEG datasets.

Demonstrated improved detection of neoplastic and polyp categories.

Model generalizes well to unseen test data.

Abstract

Prevalence of gastrointestinal (GI) cancer is growing alarmingly every year leading to a substantial increase in the mortality rate. Endoscopic detection is providing crucial diagnostic support, however, subtle lesions in upper and lower GI are quite hard to detect and cause considerable missed detection. In this work, we leverage deep learning to develop a framework to improve the localization of difficult to detect lesions and minimize the missed detection rate. We propose an end to end student-teacher learning setup where class probabilities of a trained teacher model on one class with larger dataset are used to penalize multi-class student network. Our model achieves higher performance in terms of mean average precision (mAP) on both endoscopic disease detection (EDD2020) challenge and Kvasir-SEG datasets. Additionally, we show that using such learning paradigm, our model is generalizable to unseen test set giving higher APs for clinically crucial neoplastic and polyp categories