Deep learning classifier of locally advanced rectal cancer treatment response from endoscopy images

arXiv:2405.03762v1 Announce Type: cross
Abstract: We developed a deep learning classifier of rectal cancer response (tumor vs. no-tumor) to total neoadjuvant treatment (TNT) from endoscopic images acquired before, during, and following TNT. We further evaluated the network's ability in a near out-of-distribution (OOD) problem to identify local regrowth (LR) from follow-up endoscopy images acquired several months to years after completing TNT. We addressed endoscopic image variability by using optimal mass transport-based image harmonization. We evaluated multiple training regularization schemes to …

abstract acquired advanced arxiv cancer cancer treatment classifier cs.cv deep learning distribution eess.iv identify images near network total treatment type