Habitat radiomics and deep learning on gadoxetic acid-enhanced MRI for noninvasive assessment of CK19 expression and recurrence-free survival in hepatocellular carcinoma
The DL-HR nomogram model integrating clinical, radiologic, habitat radiomics, and deep learning features effectively predicted the CK19 expression and served as an effective tool for RFS risk stratification in HCC.
Authors
- Qian Wu (ORCID: https://orcid.org/0000-0002-8912-0118)
- Tao Zhang (ORCID: https://orcid.org/0000-0002-4493-7220)
- Yanfen Fan (ORCID: https://orcid.org/0000-0002-3860-8439)
- Ximing Wang (ORCID: https://orcid.org/0000-0002-1213-1003)
- Weihao Chen (ORCID: https://orcid.org/0000-0003-3649-165X)
- Chunyan Gu (ORCID: https://orcid.org/0009-0007-1563-0063)
- Yixing Yu (ORCID: https://orcid.org/0000-0001-6895-962X)
- Jingcheng Hu
- Mingzhan Du
- Chunhong Hu
Institutions
- Nantong University (CN)
- Soochow University (CN)
- Second People's Hospital of NanTong (CN)
- Wuxi Third People's Hospital (CN)
- First Affiliated Hospital of Soochow University (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-11-10
- DOI
- https://doi.org/10.3389/fonc.2025.1684264
- Primary Topic
- Hepatocellular Carcinoma Treatment and Prognosis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- China Postdoctoral Science Foundation