Enhancing BRAF V600E mutation prediction in thyroid cancer through interpretable deep learning models combining clinical and ultrasound-based radiomics features
Lijie Zhang, Chunwang Huang, Zefeng Chen, Yuanlin Ying, Nan Jiang, Xiaozhu Zhong, Fenghuan Chen, Yuping Guo, Siwei Luo · 2026
Read Enhancing BRAF V600E mutation prediction in thyroid cancer through interpretable deep learning models combining clinical and ultrasound-based radiomics features by Lijie Zhang, Chunwang Huang, Zefeng Chen, Yuanlin Ying, Nan Jiang, Xiaozhu Zhong, Fenghuan Chen, Yuping Guo, Siwei Luo (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13350538.txt.
Description
Lijie Zhang and co-authors built a deep learning model in 2026 to predict a key thyroid cancer mutation from ultrasound images plus clinical details. The BRAF V600E change marks more aggressive papillary cancers, but confirming it needs tissue sampling and gene testing.
The dataset held 6,703 images from 1,257 lumps in 1,202 patients. A clinical model, six machine learning models, and a fine-tuned image network were compared, then combined through a boosting method, with per-lump scores averaged across images. Explanations of each prediction were included so doctors can see the reasoning. A reliable scan-based guess could triage who truly needs invasive testing.
Catalog record
| CREATOR | Lijie Zhang, Chunwang Huang, Zefeng Chen, Yuanlin Ying, Nan Jiang, Xiaozhu Zhong, Fenghuan Chen, Yuping Guo, Siwei Luo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47669 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |