CLTS-GAN: Color-lighting-texture-specular reflection augmentation for colonoscopy Conference Paper
| Authors: | Mathew, S.; Nadeem, S.; Kaufman, A. |
| Title: | CLTS-GAN: Color-lighting-texture-specular reflection augmentation for colonoscopy |
| Conference Title: | 25th International Conference of the Medical Image Computing and Computer Assisted Intervention (MICCAI 2022) |
| Abstract: | 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 ). © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. |
| Keywords: | medical imaging; colonoscopy; endoscopy; augmentation; textures; color; lighting; polyp detection; digital storage; automated analysis; deep learning; optical colonoscopy; specular reflections; color reflection; lighting textures; training data; video frame |
| Journal Title | Lecture Notes in Computer Science |
| Volume: | 13437 |
| Conference Dates: | 2022 Sep 18-22 |
| Conference Location: | Singapore |
| ISBN: | 0302-9743 |
| Publisher: | Springer |
| Date Published: | 2022-01-01 |
| Start Page: | 519 |
| End Page: | 529 |
| Language: | English |
| DOI: | 10.1007/978-3-031-16449-1_49 |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Conference Paper, located in MICCAI 2022 Proceedings, Part VII (ISBN: 978-3-031-16448-4) -- Export Date: 1 November 2022 -- Source: Scopus |
