Separation of color channels from conventional colonoscopy images improves deep neural network detection of polyps

• Published in: Journal of biomedical optics Vol. 26; no. 1; p. 015001
• Main Authors: Lai, Lily L, Blakely, Andrew, Invernizzi, Marta, Lin, James, Kidambi, Trilokesh, Melstrom, Kurt A, Yu, Kevin, Lu, Thomas
• Format: Journal Article
• Language: English
• Published: United States Society of Photo-Optical Instrumentation Engineers 01.01.2021; S P I E - International Society for
• Subjects: Artificial intelligence; Artificial neural networks; Cancer; Channels; Colon; Colonoscopy; Color; Color imagery; Colorectal carcinoma; Endoscopy; Image acquisition; Image processing; Machine learning; Medical imaging; Multilayers; Neural networks; Patients; Polyps; Rectum; Separation; Surveillance; Tumors; White light; artificial intelligence algorithms; deep learning; color channel separation; colorectal cancer; polyp discrimination; narrow-band imaging

Significance: Colorectal cancer incidence has decreased largely due to detection and removal of polyps. Computer-aided diagnosis development may improve on polyp detection and discrimination. Aim: To advance detection and discrimination using currently available commercial colonoscopy systems, we de...