Visualizing Missing Surfaces In Colonoscopy Videos using Shared Latent Space Representations

TL;DR

This paper introduces a novel framework that visualizes missed regions in colonoscopy videos by leveraging shared latent space representations with virtual colonoscopy data, aiding clinical diagnosis.

Contribution

It proposes a shared latent space model using unpaired image translation to visualize missed surfaces in colonoscopy videos, bridging OC and VC modalities.

Findings

Shared latent space effectively captures geometric information.

Model enables one-to-many mappings between OC and VC.

Framework provides a clinical visualization tool for missed regions.

Abstract

Optical colonoscopy (OC), the most prevalent colon cancer screening tool, has a high miss rate due to a number of factors, including the geometry of the colon (haustral fold and sharp bends occlusions), endoscopist inexperience or fatigue, endoscope field of view, etc. We present a framework to visualize the missed regions per-frame during the colonoscopy, and provides a workable clinical solution. Specifically, we make use of 3D reconstructed virtual colonoscopy (VC) data and the insight that VC and OC share the same underlying geometry but differ in color, texture and specular reflections, embedded in the OC domain. A lossy unpaired image-to-image translation model is introduced with enforced shared latent space for OC and VC. This shared latent space captures the geometric information while deferring the color, texture, and specular information creation to additional Gaussian noise input. This additional noise input can be utilized to generate one-to-many mappings from VC to OC and OC to OC. The code, data and trained models will be released via our Computational Endoscopy Platform at https://github.com/nadeemlab/CEP.