Development and internal validation of a multivariable MRI-based radiomics prediction model for preoperative cervical lymph node metastasis in thyroid cancer
Shuo Shen, Mingrui Zhang, Fuling Huang, Chunyi Zhou, Yajing Liang, Yimin Liang, Huimei Yang, Ruilin Xiang, HaoJun Tang, Fu Li · 2026
Read Development and internal validation of a multivariable MRI-based radiomics prediction model for preoperative cervical lymph node metastasis in thyroid cancer by Shuo Shen, Mingrui Zhang, Fuling Huang, Chunyi Zhou, Yajing Liang, Yimin Liang, Huimei Yang, Ruilin Xiang, HaoJun Tang, Fu Li (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/PMC13462804.txt.
Description
Shuo Shen and a large team build, in a 2026 study, an MRI-based prediction model for neck lymph node spread in thyroid cancer before surgery. Standard ultrasound and CT miss many involved nodes, yet the answer shapes the operation. The team enrolled 97 patients with thyroid cancer who had MRI scans and node removal at a hospital in Guangxi between 2017 and 2019. Sixty-three percent of patients had positive nodes.
Seventeen hundred image features were pulled from two MRI sequences, then winnowed into a signature read by a random forest model. The combined model, joining both sequences, beat each single-sequence model in training and checks. In the check set it caught almost all positive cases, yet its specificity was only one half, so many healthy nodes were flagged. The authors judge the model promising for sorting risk, though too trigger-happy to stand alone. Larger outside studies must come first.
Catalog record
| CREATOR | Shuo Shen, Mingrui Zhang, Fuling Huang, Chunyi Zhou, Yajing Liang, Yimin Liang, Huimei Yang, Ruilin Xiang, HaoJun Tang, Fu Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 22 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |