一种整合深度学习、影像组学和临床超声特征的联合模型，用于预测伴桥本甲状腺炎的乳头状甲状腺癌中的突变。

A combined model integrating deep learning, radiomics, and clinical ultrasound features for predicting mutation in papillary thyroid carcinoma with Hashimoto's thyroiditis.

作者信息

Zhu Peng-Fei, Zhang Xiao-Feng, Zhou Pu, Ben Jiang-Yuan, Wang Hao, Zeng Shu-E, Cui Xin-Wu, He Ying

机构信息

Department of Ultrasonic Medicine, Nantong Tumor Hospital, Nantong, Jiangsu, China.

Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.

出版信息

Front Endocrinol (Lausanne). 2025 Aug 18;16:1641037. doi: 10.3389/fendo.2025.1641037. eCollection 2025.

DOI:10.3389/fendo.2025.1641037

PMID:40900897

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12399403/

Abstract

OBJECTIVE

This study aims to develop an integrated model that combines radiomics, deep learning features, and clinical and ultrasound characteristics for predicting mutations in patients with papillary thyroid carcinoma (PTC) combined with Hashimoto's thyroiditis (HT).

METHODS

This retrospective study included 717 thyroid nodules from 672 patients with PTC combined with HT from four hospitals in China. Deep learning and radiomics were employed to extract deep learning and radiomics features from ultrasound images. Feature selection was performed using Pearson's correlation coefficient, the Minimum Redundancy Maximum Relevance (mRMR) algorithm, and LASSO regression. The optimal algorithm was selected from nine machine learning algorithms for model construction, including the traditional radiomics model (RAD), the deep learning model (DL), and their fusion model (DL_RAD). Additionally, a final combined model was developed by integrating the DL_RAD model with clinical and ultrasound features. Model performance was assessed using AUC, calibration curves, and decision curve analysis (DCA), while SHAP analysis was used to interpret the contribution of each feature to the combined model's output.

RESULTS

The combined model achieved superior diagnostic performance, with AUC values of 0.895, 0.864, and 0.815 in the training, validation, and external test sets, respectively, outperforming the RAD model, DL model, and RAD_DL model. DeLong test results indicated significant differences in the external test set (0.05). Further validation through calibration curves and DCA confirmed the model's robust performance. SHAP analysis revealed that RAD_DL signature, aspect ratio, extrathyroidal extension, and gender were key contributors to the model's predictions.

CONCLUSION

The combined model integrating radiomics, deep learning features, and clinical as well as ultrasound characteristics exhibits excellent diagnostic performance in predicting mutations in patients with PTC coexisting with HT, highlighting its strong potential for clinical application.

摘要

目的

本研究旨在开发一种综合模型，该模型结合放射组学、深度学习特征以及临床和超声特征，用于预测合并桥本甲状腺炎（HT）的甲状腺乳头状癌（PTC）患者的基因突变。

方法

这项回顾性研究纳入了来自中国四家医院的672例合并HT的PTC患者的717个甲状腺结节。采用深度学习和放射组学从超声图像中提取深度学习和放射组学特征。使用Pearson相关系数、最小冗余最大相关（mRMR）算法和LASSO回归进行特征选择。从九种机器学习算法中选择最优算法进行模型构建，包括传统放射组学模型（RAD）、深度学习模型（DL）及其融合模型（DL_RAD）。此外，通过将DL_RAD模型与临床和超声特征相结合，开发了最终的联合模型。使用AUC、校准曲线和决策曲线分析（DCA）评估模型性能，同时使用SHAP分析来解释每个特征对联合模型输出的贡献。

结果

联合模型具有卓越的诊断性能，在训练集、验证集和外部测试集中的AUC值分别为0.895、0.864和0.815，优于RAD模型、DL模型和RAD_DL模型。DeLong检验结果表明在外部测试集中存在显著差异（P<0.05）。通过校准曲线和DCA进一步验证证实了该模型的稳健性能。SHAP分析显示，RAD_DL特征、纵横比、甲状腺外侵犯和性别是模型预测的关键因素。