FoldIt: Haustral Folds Detection and Segmentation in Colonoscopy Videos
This work addresses the issue of high polyp miss rates in colonoscopy procedures for medical professionals, offering a tool to enhance diagnostic accuracy through better surface estimation and registration, though it appears incremental as it builds on existing GAN methods with specific adaptations.
The paper tackles the problem of detecting and segmenting haustral folds in colonoscopy videos to improve polyp detection and registration with pre-treatment scans, resulting in a novel generative adversarial network that demonstrates effectiveness on real and virtual colonoscopy videos with clinician-verified annotations.
Haustral folds are colon wall protrusions implicated for high polyp miss rate during optical colonoscopy procedures. If segmented accurately, haustral folds can allow for better estimation of missed surface and can also serve as valuable landmarks for registering pre-treatment virtual (CT) and optical colonoscopies, to guide navigation towards the anomalies found in pre-treatment scans. We present a novel generative adversarial network, FoldIt, for feature-consistent image translation of optical colonoscopy videos to virtual colonoscopy renderings with haustral fold overlays. A new transitive loss is introduced in order to leverage ground truth information between haustral fold annotations and virtual colonoscopy renderings. We demonstrate the effectiveness of our model on real challenging optical colonoscopy videos as well as on textured virtual colonoscopy videos with clinician-verified haustral fold annotations. All code and scripts to reproduce the experiments of this paper will be made available via our Computational Endoscopy Platform at https://github.com/nadeemlab/CEP.