Tabular prior-data fitted network in real-world CT radiomics: benign vs. malignant renal tumor classification
TabPFN demonstrates robust performance in differentiating renal tumors, particularly in small-scale, high-dimensional datasets. Its transformer-based architecture and pre-training on synthetic data eliminate manual parameter tuning, enhancing clinical applicability over conventional ML approaches.
Authors
- Lesheng Huang (ORCID: https://orcid.org/0000-0002-6913-458X)
- Zhixuan Song
- Yongsong Ye (ORCID: https://orcid.org/0000-0003-1808-7418)
- Yan Guo (ORCID: https://orcid.org/0000-0002-2344-0944)
- Bin-Qi Weng
- Shanghuang Xie (ORCID: https://orcid.org/0009-0006-9636-9233)
- Guimian Zhong (ORCID: https://orcid.org/0009-0001-2351-2573)
- Huanjun Wang (ORCID: https://orcid.org/0000-0001-9089-7736)
- Xiaodan Li (ORCID: https://orcid.org/0000-0002-2586-6631)
- Tianzhu Liu (ORCID: https://orcid.org/0000-0001-6213-9356)
- Jun Chen (ORCID: https://orcid.org/0000-0001-5049-5759)
Institutions
- Guangzhou University of Chinese Medicine (CN)
- Sun Yat-sen University (CN)
- Shantou University (CN)
- Philips (China) (CN)
- Longgang Central Hospital (CN)
- Guangdong Provincial Hospital of Traditional Chinese Medicine (CN)
- Shantou University Medical College (CN)
- Panyu District Central Hospital (CN)
- The First Affiliated Hospital, Sun Yat-sen University (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- Quantitative Imaging in Medicine and Surgery
- Published
- 2025-10-29
- DOI
- https://doi.org/10.21037/qims-2025-1132
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00