Knowledge distillation with a class-aware loss for endoscopic disease detection
This work addresses missed lesion detection in endoscopic disease diagnosis, which is crucial for reducing mortality from gastrointestinal cancer, but it is incremental as it builds on existing knowledge distillation methods.
The paper tackles the problem of missed detection of subtle gastrointestinal lesions in endoscopic images by proposing a knowledge distillation framework with a class-aware loss, achieving higher mean average precision on the EDD2020 and Kvasir-SEG datasets.
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