Using Multi-Instance Learning to Identify Unique Polyps in Colon Capsule Endoscopy Images

TL;DR

This paper introduces a multi-instance learning framework with attention mechanisms and self-supervised pretraining to accurately identify unique polyps in colon capsule endoscopy images, reducing clinician workload.

Contribution

It presents a novel MIL-based approach with attention and self-supervised learning for polyp identification, achieving state-of-the-art accuracy on a large medical imaging dataset.

Findings

Attention mechanisms significantly improve model performance

DBA L1 achieves 86.26% accuracy and 0.928 AUC

Self-supervised pretraining enhances embedding robustness

Abstract

Identifying unique polyps in colon capsule endoscopy (CCE) images is a critical yet challenging task for medical personnel due to the large volume of images, the cognitive load it creates for clinicians, and the ambiguity in labeling specific frames. This paper formulates this problem as a multi-instance learning (MIL) task, where a query polyp image is compared with a target bag of images to determine uniqueness. We employ a multi-instance verification (MIV) framework that incorporates attention mechanisms, such as variance-excited multi-head attention (VEMA) and distance-based attention (DBA), to enhance the model's ability to extract meaningful representations. Additionally, we investigate the impact of self-supervised learning using SimCLR to generate robust embeddings. Experimental results on a dataset of 1912 polyps from 754 patients demonstrate that attention mechanisms significantly improve performance, with DBA L1 achieving the highest test accuracy of 86.26\% and a test AUC of 0.928 using a ConvNeXt backbone with SimCLR pretraining. This study underscores the potential of MIL and self-supervised learning in advancing automated analysis of Colon Capsule Endoscopy images, with implications for broader medical imaging applications.