Yao Jincao, Wang Yunpeng, Lei Zhikai, Wang Kai, Feng Na, Dong Fajin, Zhou Jianhua, Li Xiaoxian, Hao Xiang, Shen Jiafei, Zhao Shanshan, Gao Yuan, Wang Vicky, Ou Di, Li Wei, Lu Yidan, Chen Liyu, Yang Chen, Wang Liping, Feng Bojian, Zhou Yahan, Chen Chen, Yan Yuqi, Wang Zhengping, Ru Rongrong, Chen Yaqing, Zhang Yanming, Liang Ping, Xu Dong
Department of Diagnostic Ultrasound Imaging & Interventional Therapy, Zhejiang Cancer Hospital, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, China.
Interventional Medicine and Engineering Research Center, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, China.
NPJ Digit Med. 2025 May 3;8(1):245. doi: 10.1038/s41746-025-01652-9.
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.
尽管使用人工智能（AI）分析超声图像是评估甲状腺结节风险的一种有前景的方法，但传统的AI模型缺乏透明度和可解释性。我们开发了一种用于甲状腺结节的多模态生成式预训练变换器（ThyGPT），旨在为甲状腺结节风险评估和管理提供一个透明且可解释的AI辅助模型。回顾性收集了来自九家医院的59406名患者的超声数据，用于训练和测试该模型。训练后发现，ThyGPT有助于在不增加漏诊率的情况下将活检率降低40%以上。此外，它检测超声报告中的错误比人类快1610倍。在ThyGPT的辅助下，放射科医生评估甲状腺结节风险的曲线下面积从0.805提高到了0.908（p<0.001）。作为一种人工智能生成内容增强的计算机辅助诊断（AIGC-CAD）模型，ThyGPT有可能彻底改变放射科医生使用此类工具的方式。
