Non-invasive CT radiomic biomarkers predict microsatellite stability status in colorectal cancer: a multicenter validation study.

Zuhir BodalalEun Kyoung HongStefano TrebeschiIeva KurilovaFederica LandolfiNino BogveradzeFrancesca CastagnoliGiovanni RandonPetur SnaebjornssonFilippo PietrantonioJeong Min LeeGeerard BeetsRegina G H Beets-Tan

Published in: European radiology experimental (2024)

Noninvasive CT-based radiomics predicted MSI in colorectal cancer, enhancing stratification. A seven-feature radiomic signature differentiated tumors with MSI from those with MSS in multicenter cohorts. Integrating radiomic and clinical data improved the algorithm's predictive performance.

Keyphrases

contrast enhanced
image quality
dual energy
computed tomography
machine learning
deep learning
cross sectional
positron emission tomography
electronic health record
lymph node metastasis
neural network
clinical trial
squamous cell carcinoma
artificial intelligence