High performance in risk stratification of intraductal papillary mucinous neoplasms by confocal laser endomicroscopy image analysis with convolutional neural networks (with video)

Jorge D Machicado , Wei-Lun Chao , David E. Carlyn , Tai-Yu Daniel Pan , Sarah Poland , Victoria L Alexander , Tassiana G Maloof , Kelly Dubay , Olivia Ueltschi , Dana M Middendorf , Muhammed O Jajeh , Aadit B Vishwanath , Kyle Porter , Phil A Hart , Georgios I Papachristou , Zobeida Cruz-Monserrate , Darwin L Conwell , Somashekar G Krishna
July, 2021
PDF Cite

Abstract

EUS-guided needle-based confocal laser endomicroscopy (EUS-nCLE) can differentiate high-grade dysplasia/adenocarcinoma (HGD-Ca) in intraductal papillary mucinous neoplasms (IPMNs) but requires manual interpretation. We sought to derive predictive computer-aided diagnosis (CAD) and artificial intelligence (AI) algorithms to facilitate accurate diagnosis and risk stratification of IPMNs.

Type
2
Publication
Gastrointestinal endoscopy
Tai-Yu Daniel Pan
Tai-Yu Daniel Pan
Ph.D. Candidate

PhD candidate working on machine learning and computer vision at The Ohio State University