Open AccessAutomated detection and delineation of hepatocellular carcinoma on multiphasic contrast-enhanced MRI using deep learning
Author(s) -
Khaled Bousabarah,
Brian Letzen,
Jonathan Tefera,
Lynn Jeanette Savic,
Isabel Schobert,
Todd Schlachter,
Lawrence H. Staib,
Martin Köcher,
Julius Chapiro,
Ming De Lin
Publication year - 2020
Publication title -
abdominal radiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.824
H-Index - 74
eISSN - 2366-004X
pISSN - 2366-0058
DOI - 10.1007/s00261-020-02604-5
Subject(s) - artificial intelligence , hepatocellular carcinoma , medicine , convolutional neural network , hepatology , deep learning , random forest , receiver operating characteristic , magnetic resonance imaging , test set , artificial neural network , radiology , nuclear medicine , pattern recognition (psychology) , computer science
Liver Imaging Reporting and Data System (LI-RADS) uses multiphasic contrast-enhanced imaging for hepatocellular carcinoma (HCC) diagnosis. The goal of this feasibility study was to establish a proof-of-principle concept towards automating the application of LI-RADS, using a deep learning algorithm trained to segment the liver and delineate HCCs on MRI automatically.