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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sharma, Puneet, Hindberg, Kristian Dalsbø, Frank, Eibe, Schelde-Olesen, Benedicte, Deding, Ulrik
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914269264609280
author Sharma, Puneet
Hindberg, Kristian Dalsbø
Frank, Eibe
Schelde-Olesen, Benedicte
Deding, Ulrik
author_facet Sharma, Puneet
Hindberg, Kristian Dalsbø
Frank, Eibe
Schelde-Olesen, Benedicte
Deding, Ulrik
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14771
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Using Multi-Instance Learning to Identify Unique Polyps in Colon Capsule Endoscopy Images
Sharma, Puneet
Hindberg, Kristian Dalsbø
Frank, Eibe
Schelde-Olesen, Benedicte
Deding, Ulrik
Computer Vision and Pattern Recognition
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.
title Using Multi-Instance Learning to Identify Unique Polyps in Colon Capsule Endoscopy Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.14771