PS-DeVCEM: Pathology-sensitive deep learning model for video capsule endoscopy based on weakly labeled data

TL;DR

This paper introduces PS-DeVCEM, a deep learning model for detecting and classifying colon diseases in video capsule endoscopy, trained with weak labels and capable of temporal localization without detailed annotations.

Contribution

The paper presents a novel weakly supervised deep learning approach with attention mechanisms and self-supervision for colon disease detection in VCE videos, along with a new annotated dataset.

Findings

Achieved 61.6% precision and 55.1% F1-score, outperforming state-of-the-art methods.

Enabled temporal localization of pathologies without frame-level annotations.

Collected and annotated the largest VCE dataset with weak labels.

Abstract

We propose a novel pathology-sensitive deep learning model (PS-DeVCEM) for frame-level anomaly detection and multi-label classification of different colon diseases in video capsule endoscopy (VCE) data. Our proposed model is capable of coping with the key challenge of colon apparent heterogeneity caused by several types of diseases. Our model is driven by attention-based deep multiple instance learning and is trained end-to-end on weakly labeled data using video labels instead of detailed frame-by-frame annotation. The spatial and temporal features are obtained through ResNet50 and residual Long short-term memory (residual LSTM) blocks, respectively. Additionally, the learned temporal attention module provides the importance of each frame to the final label prediction. Moreover, we developed a self-supervision method to maximize the distance between classes of pathologies. We demonstrate through qualitative and quantitative experiments that our proposed weakly supervised learning model gives superior precision and F1-score reaching, 61.6% and 55.1%, as compared to three state-of-the-art video analysis methods respectively. We also show our model's ability to temporally localize frames with pathologies, without frame annotation information during training. Furthermore, we collected and annotated the first and largest VCE dataset with only video labels. The dataset contains 455 short video segments with 28,304 frames and 14 classes of colorectal diseases and artifacts. Dataset and code supporting this publication will be made available on our home page.