MRI-based 2.5D deep learning and radiomics effectively predicted microvascular invasion and Ki-67 expression in hepatocellular carcinoma
The integrated MRI 2.5D DL model synergizing radiomics and clinical features surpasses single-modality models for preoperative prediction of MVI/Ki-67 dual positivity in HCC. This tool shows strong potential for enhancing HCC risk stratification and guiding personalized treatment planning.
Authors
- Ju Huang (ORCID: https://orcid.org/0000-0002-7810-4550)
- Dexia Kong (ORCID: https://orcid.org/0000-0002-5311-1906)
- Yang Wang (ORCID: https://orcid.org/0000-0003-0447-3107)
- Jie Wu (ORCID: https://orcid.org/0000-0002-7211-2816)
- Xiaofei Mo (ORCID: https://orcid.org/0000-0002-8633-4188)
- Hongmei Yu (ORCID: https://orcid.org/0009-0005-6207-4536)
- Feizhou Du (ORCID: https://orcid.org/0009-0002-9288-2399)
Institutions
- China National Nuclear Corporation (CN)
- Chengdu Medical College (CN)
- Chinese General Hospital College of Nursing and Liberal Arts (PH)
Publication Details
- Journal
- PLoS ONE
- Published
- 2025-11-14
- DOI
- https://doi.org/10.1371/journal.pone.0336579
- Primary Topic
- Hepatocellular Carcinoma Treatment and Prognosis
- Type
- article
- Field-Weighted Citation Impact
- 0.00