Liu Rongwei, Li Haiyuan, Liu Changwen, Peng Jinbo, Gao Ruizhi, Yang Hong, He Yun
Department of Medical Ultrasound, the First Affiliated Hospital of Guangxi Medical University, Nanning, China.
Department of Medical Ultrasound, the First Affiliated Hospital of Gannan Medical University, Ganzhou, China.
Gland Surg. 2025 Apr 30;14(4):584-596. doi: 10.21037/gs-2024-551. Epub 2025 Apr 25.
The risk of malignancy in cystic-solid thyroid nodules (CSTN) varies greatly and may be underestimated. This study aimed to explore the value of a comprehensive model that integrates deep transfer learning (DTL), ultrasound radiomics, and clinical, and ultrasound features in predicting the risk of malignancy of CSTN.
A retrospective analysis was conducted on 278 patients with CSTN confirmed by pathology from the First Affiliated Hospital of Guangxi Medical University from January 2023 to December 2023. Radiomics features were manually extracted from ultrasound images, and DTL features were extracted using deep learning networks. The least absolute shrinkage and selection operator (LASSO) regression was utilized to select non-zero coefficient features from radiomics and DTL features. The comprehensive model nomogram was constructed using a logistic regression algorithm that integrates clinical, ultrasound features, deep learning, and radiomics features. The predictive performance was assessed using the receiver operating characteristic (ROC) curve and the area under the curve (AUC), calibration curves, and decision curves. Subsequently, DeLong testing was performed for comparative analysis of the AUC, with parameter estimates including a 95% confidence interval (CI), and a P value of less than 0.05 was considered statistically significant.
The AUC of each model was compared, revealing that the comprehensive model outperformed the individual models in predicting the malignancy risk of CSTN, demonstrating good predictive performance with sensitivity and specificity of 87.50% and 82.90%, respectively. Additionally, the AUC of the comprehensive model in the testing set was 0.913 (95% CI: 0.844-0.982), which was higher than the radiomics model (0.913 0.898, P=0.67), and the DTL model (0.913 0.848, P=0.38). In the training set, the AUC was 0.973 (95% CI: 0.949-0.997), outperforming the radiomics model (0.973 0.926, P=0.09) and the DTL model (0.973 0.943, P=0.01).
The novel comprehensive model based on ultrasound demonstrates excellent performance in predicting the malignancy risk of CSTN, providing clinicians with a preoperative non-invasive screening method to predict the malignancy risk of CSTN.
囊实性甲状腺结节（CSTN）的恶性风险差异很大，可能被低估。本研究旨在探讨一种综合模型的价值，该模型整合了深度迁移学习（DTL）、超声影像组学以及临床和超声特征，用于预测CSTN的恶性风险。
对2023年1月至2023年12月广西医科大学第一附属医院278例经病理证实的CSTN患者进行回顾性分析。从超声图像中手动提取影像组学特征，并使用深度学习网络提取DTL特征。利用最小绝对收缩和选择算子（LASSO）回归从影像组学和DTL特征中选择非零系数特征。使用逻辑回归算法构建综合模型列线图，该算法整合了临床、超声特征、深度学习和影像组学特征。使用受试者操作特征（ROC）曲线、曲线下面积（AUC）、校准曲线和决策曲线评估预测性能。随后，进行DeLong检验以比较AUC，参数估计包括95%置信区间（CI），P值小于0.05被认为具有统计学意义。
比较各模型的AUC，发现综合模型在预测CSTN的恶性风险方面优于单个模型，其敏感性和特异性分别为87.50%和82.90%，显示出良好的预测性能。此外，综合模型在测试集中的AUC为0.913（95%CI：0.844 - 0.982），高于影像组学模型（0.913对0.898，P = 0.67）和DTL模型（0.913对0.848，P = 0.38）。在训练集中，AUC为0.973（95%CI：0.949 - 0.997），优于影像组学模型（0.973对0.926，P = 0.09）和DTL模型（0.973对0.943，P = 0.01）。
基于超声的新型综合模型在预测CSTN的恶性风险方面表现出色，为临床医生提供了一种术前非侵入性筛查方法来预测CSTN的恶性风险。
