Deep learning with attention modules and residual transformations improves hepatocellular carcinoma (HCC) differentiation using multiphase CT
Results showed the proposed method had larger AUROC (95%), better accuracy (91%) and sensitivity (93%) with acceptable specificity (88%) and prediction time (0.04s). Deep GAN with attentions and residual transformations for HCC diagnosis using multiphase CT is feasible and favorable with improved accuracy and efficiency, which harbors clinical potentials in differentiating HCC from other benign or malignant liver lesions.
Authors
- Yuenan Wang (ORCID: https://orcid.org/0000-0001-6280-6956)
- Wanwei Jian
- Fada Guan (ORCID: https://orcid.org/0000-0001-8477-7391)
- David J. Carlson (ORCID: https://orcid.org/0000-0001-8677-7707)
- Zhidong Yuan (ORCID: https://orcid.org/0000-0003-1169-0169)
Institutions
- Guangzhou University of Chinese Medicine (CN)
- Yale University (US)
- St. Vincent's Medical Center (US)
- Second Affiliated Hospital of Guangzhou Medical University (CN)
- St Vincent Medical Center (US)
- Peking University Shenzhen Hospital (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- Precision Radiation Oncology
- Published
- 2025-03-01
- DOI
- https://doi.org/10.1002/pro6.70003
- Citations
- 19
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 25.84