CLTS-GAN: Color-Lighting-Texture-Specular Reflection Augmentation for Colonoscopy
This work addresses the problem of data variability in colonoscopy for medical professionals and students, though it is incremental as it builds on existing GAN-based augmentation methods.
The paper tackled the challenge of automated analysis in colonoscopy videos by developing CLTS-GAN, a model that synthesizes colonoscopy-specific augmentations for color, lighting, texture, and specular reflections, which improved state-of-the-art polyp detection and segmentation methods.
Automated analysis of optical colonoscopy (OC) video frames (to assist endoscopists during OC) is challenging due to variations in color, lighting, texture, and specular reflections. Previous methods either remove some of these variations via preprocessing (making pipelines cumbersome) or add diverse training data with annotations (but expensive and time-consuming). We present CLTS-GAN, a new deep learning model that gives fine control over color, lighting, texture, and specular reflection synthesis for OC video frames. We show that adding these colonoscopy-specific augmentations to the training data can improve state-of-the-art polyp detection/segmentation methods as well as drive next generation of OC simulators for training medical students. The code and pre-trained models for CLTS-GAN are available on Computational Endoscopy Platform GitHub (https://github.com/nadeemlab/CEP).