Deep learning for multitask prediction on thyroid nodule frozen sections
The study indicates that deep learning models can effectively classify benign/malignant thyroid frozen sections, predict BRAF<sup>V600E</sup> gene mutations, and predict lymph node metastasis status. It also emphasizes the effectiveness of weakly supervised strategies in thyroid lesion frozen sections, which could lessen reliance on pathologists' annotations.
Authors
- Shixiang Wang (ORCID: https://orcid.org/0000-0001-9855-7357)
- Dehua Hu (ORCID: https://orcid.org/0000-0001-8027-405X)
- Juan Hu (ORCID: https://orcid.org/0000-0002-0175-0167)
- Xiang Li (ORCID: https://orcid.org/0000-0002-9168-1598)
- Chunyang Wang (ORCID: https://orcid.org/0000-0002-6707-2274)
- Haixia Liu (ORCID: https://orcid.org/0000-0001-7365-9488)
- Yufeng Cai
- Hu Zhongliang
- Xusheng Wu
Institutions
- Central South University (CN)
- Xiangshan County First People's Hospital (CN)
- Xiangya Hospital Central South University (CN)
- Xiang Yang No.1 People's Hospital (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2026-01-12
- DOI
- https://doi.org/10.3389/fonc.2025.1676360
- Primary Topic
- Thyroid Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00