npj Digital Medicine (May 2025)
Multimodal GPT model for assisting thyroid nodule diagnosis and management
- Jincao Yao,
- Yunpeng Wang,
- Zhikai Lei,
- Kai Wang,
- Na Feng,
- Fajin Dong,
- Jianhua Zhou,
- Xiaoxian Li,
- Xiang Hao,
- Jiafei Shen,
- Shanshan Zhao,
- Yuan Gao,
- Vicky Wang,
- Di Ou,
- Wei Li,
- Yidan Lu,
- Liyu Chen,
- Chen Yang,
- Liping Wang,
- Bojian Feng,
- Yahan Zhou,
- Chen Chen,
- Yuqi Yan,
- Zhengping Wang,
- Rongrong Ru,
- Yaqing Chen,
- Yanming Zhang,
- Ping Liang,
- Dong Xu
Affiliations
- Jincao Yao
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Yunpeng Wang
- College of Optical Science and Engineering, Zhejiang University
- Zhikai Lei
- Department of Ultrasound, Zhejiang Provincial Hospital of Chinese Medicine
- Kai Wang
- Department of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University
- Na Feng
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Fajin Dong
- Department of Ultrasound, The Second Clinical Medical College, Jinan University
- Jianhua Zhou
- Department of Ultrasound, Sun Yat-sen University Cancer centre, State Key Laboratory of Oncology in South China, Collaborative Innovation centre for Cancer Medicine
- Xiaoxian Li
- Department of Ultrasound, Sun Yat-sen University Cancer centre, State Key Laboratory of Oncology in South China, Collaborative Innovation centre for Cancer Medicine
- Xiang Hao
- College of Optical Science and Engineering, Zhejiang University
- Jiafei Shen
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Shanshan Zhao
- Department of Ultrasound, Shaoxing People’s Hospital (Zhejiang University Shaoxing Hospital)
- Yuan Gao
- Department of Ultrasound, Shaoxing People’s Hospital (Zhejiang University Shaoxing Hospital)
- Vicky Wang
- Wenling Medical Big Data and Artificial Intelligence Research Institute
- Di Ou
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Wei Li
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Yidan Lu
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Liyu Chen
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Chen Yang
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Liping Wang
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Bojian Feng
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Yahan Zhou
- Wenling Medical Big Data and Artificial Intelligence Research Institute
- Chen Chen
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Yuqi Yan
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- Zhengping Wang
- Department of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University
- Rongrong Ru
- Affiliated Xiaoshan Hospital, Hangzhou Normal University
- Yaqing Chen
- Affiliated Xiaoshan Hospital, Hangzhou Normal University
- Yanming Zhang
- Faculty of Applied Sciences, Macao Polytechnic University
- Ping Liang
- Department of Ultrasound, Chinese PLA General Hospital, Chinese PLA Medical School
- Dong Xu
- Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences
- DOI
- https://doi.org/10.1038/s41746-025-01652-9
- Journal volume & issue
-
Vol. 8,
no. 1
pp. 1 – 15
Abstract
Abstract Although using artificial intelligence (AI) to analyze ultrasound images is a promising approach to assessing thyroid nodule risks, traditional AI models lack transparency and interpretability. We developed a multimodal generative pre-trained transformer for thyroid nodules (ThyGPT), aiming to provide a transparent and interpretable AI copilot model for thyroid nodule risk assessment and management. Ultrasound data from 59,406 patients across nine hospitals were retrospectively collected to train and test the model. After training, ThyGPT was found to assist in reducing biopsy rates by more than 40% without increasing missed diagnoses. In addition, it detects errors in ultrasound reports 1,610 times faster than humans. With the assistance of ThyGPT, the area under the curve for radiologists in assessing thyroid nodule risks improved from 0.805 to 0.908 (p < 0.001). As an AI-generated content-enhanced computer-aided diagnosis (AIGC-CAD) model, ThyGPT has the potential to revolutionize how radiologists use such tools.
