Topological SLAM in colonoscopies leveraging deep features and topological priors

TL;DR

ColonSLAM is a novel topological SLAM system for colonoscopy mapping that integrates deep features, topological priors, and transformer-based matching to produce comprehensive maps of the entire colon from video data.

Contribution

It introduces a topological SLAM approach that combines deep learning and topological priors to improve colon mapping in medical endoscopy.

Findings

Successfully maps the entire colon in real human explorations

Outperforms existing methods in creating complex topological maps

Demonstrates robustness in relating far-in-time submaps

Abstract

We introduce ColonSLAM, a system that combines classical multiple-map metric SLAM with deep features and topological priors to create topological maps of the whole colon. The SLAM pipeline by itself is able to create disconnected individual metric submaps representing locations from short video subsections of the colon, but is not able to merge covisible submaps due to deformations and the limited performance of the SIFT descriptor in the medical domain. ColonSLAM is guided by topological priors and combines a deep localization network trained to distinguish if two images come from the same place or not and the soft verification of a transformer-based matching network, being able to relate far-in-time submaps during an exploration, grouping them in nodes imaging the same colon place, building more complex maps than any other approach in the literature. We demonstrate our approach in the Endomapper dataset, showing its potential for producing maps of the whole colon in real human explorations. Code and models are available at: https://github.com/endomapper/ColonSLAM.