Simplified LI-RADS Table for Hepatocellular Carcinoma Diagnosis on Extracellular-Contrast Enhanced MRI: AFP as an Additional Major Feature
Motivation: The MRI LI-RADS v2018 table is complex and has insufficient sensitivity. Goal(s): To evaluate the diagnostic performance of the simplified LI-RADS table for HCC on ECA-MRI, and to determine the value of AFP level as an additional major feature. Approach: We developed and compared the per-lesion sensitivity for HCC defined by LI-RADS v2018, simplified LI-RADS table, and both of them combined with AFP ≥ 200 ng/mL. Results: Compared with LR-5 v2018, the simplified LI-RADS table provided higher sensitivity and comparable specificity for HCC. AFP ≥ 200 ng/mL may be a suitable additional major feature for further improving LR-5 v2018 and sLR-5 classification. Impact: Our simplified LI-RADS table may be more convenient and clinically helpful, and the AFP ≥ 200 ng/mL may be a suitable additional major feature for accurate LR-5 and sLR-5 classification.
Authors
- Yufeng Wang (ORCID: https://orcid.org/0000-0003-1417-1460)
- Hang Jiang (ORCID: https://orcid.org/0000-0002-6697-409X)
- Han Yu (ORCID: https://orcid.org/0000-0001-6893-8650)
- Tianhui Zhang (ORCID: https://orcid.org/0000-0002-5162-5751)
- Jin Wang (ORCID: https://orcid.org/0000-0002-7956-9579)
- Yang Yang (ORCID: https://orcid.org/0000-0001-7432-4735)
- Yao Zhang (ORCID: https://orcid.org/0000-0002-6424-8254)
- Linqi Zhang (ORCID: https://orcid.org/0000-0002-0607-6300)
- Jingbiao Chen (ORCID: https://orcid.org/0000-0002-8573-709X)
- Lichun Chen (ORCID: https://orcid.org/0000-0001-7380-0218)
- Jinhui Zhou (ORCID: https://orcid.org/0009-0002-7345-2203)
- Xi Zhong (ORCID: https://orcid.org/0000-0002-0713-105X)
- Yikai Xu
- Jing Zhang (ORCID: https://orcid.org/0009-0009-3188-4471)
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2024-11-26
- DOI
- https://doi.org/10.58530/2024/4142
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00