# Unsupervised Segmentation of Colonoscopy Images

Source: [Unsupervised Segmentation of Colonoscopy Images](<https://www.sota2.com/research/paper/68fa71831e209131cea51b44>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:08:33.784Z

Authors: Heming Yao, J\\'er\\^ome L\\"uscher, Benjamin Gutierrez Becker, Josep Ar\\'us-Pous, Tommaso Biancalani, Amelie Bigorgne, David Richmond

Published: 2023-12-19T20:59:19.000Z

## Abstract

Colonoscopy plays a crucial role in the diagnosis and prognosis of various gastrointestinal diseases. Due to the challenges of collecting large-scale high-quality ground truth annotations for colonoscopy images, and more generally medical images, we explore using self-supervised features from vision transformers in three challenging tasks for colonoscopy images. Our results indicate that image-level features learned from DINO models achieve image classification performance comparable to fully supervised models, and patch-level features contain rich semantic information for object detection. Furthermore, we demonstrate that self-supervised features combined with unsupervised segmentation can be used to discover multiple clinically relevant structures in a fully unsupervised manner, demonstrating the tremendous potential of applying these methods in medical image analysis.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2312.12599>)

[PDF](<https://arxiv.org/pdf/2312.12599.pdf>)