Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning
This work aims to improve the accuracy and reliability of polyp detection and classification for medical professionals during colonoscopy procedures, potentially aiding in early diagnosis and treatment of colorectal cancer.
This paper proposes a system to automatically detect, localize, and classify polyps from colonoscopy videos. It addresses the challenge of imbalanced datasets by formulating polyp detection as a few-shot anomaly classification problem and includes a classifier to reject blurry frames or those with feces/water jet sprays. The system also localizes polyps with bounding boxes and classifies them into five categories, while improving reliability and interpretability through uncertainty estimation and classification calibration.
In this paper, we propose and analyse a system that can automatically detect, localise and classify polyps from colonoscopy videos. The detection of frames with polyps is formulated as a few-shot anomaly classification problem, where the training set is highly imbalanced with the large majority of frames consisting of normal images and a small minority comprising frames with polyps. Colonoscopy videos may contain blurry images and frames displaying feces and water jet sprays to clean the colon -- such frames can mistakenly be detected as anomalies, so we have implemented a classifier to reject these two types of frames before polyp detection takes place. Next, given a frame containing a polyp, our method localises (with a bounding box around the polyp) and classifies it into five different classes. Furthermore, we study a method to improve the reliability and interpretability of the classification result using uncertainty estimation and classification calibration. Classification uncertainty and calibration not only help improve classification accuracy by rejecting low-confidence and high-uncertain results, but can be used by doctors to decide how to decide on the classification of a polyp. All the proposed detection, localisation and classification methods are tested using large data sets and compared with relevant baseline approaches.