Inter-observer agreement and accuracy of LI-RADS v2018 for differentiating tumor in vein from bland thrombus using gadoxetic acid-enhanced magnetic resonance imaging.

Shintaro IchikawaClaude B SirlinGuilherme Moura CunhaTanya WolfsonKathryn J FowlerHiroyuki MorisakaKojiro OnoharaTatsuya ShimizuYoshie OmiyaHiroki SugiyamaAkihiro OkumuraHiroshi Onishi

Published in: Abdominal radiology (New York) (2023)

Using Gx-MRI, the LI-RADS criterion for TIV provides substantial inter-observer agreement, variable sensitivity, and high specificity for differentiating TIV from bland thrombus. A cross-validated multi-feature model did not improve diagnostic performance.

Keyphrases

contrast enhanced
magnetic resonance imaging
diffusion weighted imaging
ion batteries
computed tomography
magnetic resonance
machine learning
solid state
deep learning
structural basis