Lu Wenwu, Zhang Di, Zhou Wang, Wei Wei, Wu Xin, Ding Wenbo, Zhang Chaoxue
Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, China.
Affiliated Hospital of Integration Chinese and Western Medicine with Nanjing University of Traditional Chinese Medicine, Nanjing, China.
Quant Imaging Med Surg. 2025 Jun 6;15(6):5689-5702. doi: 10.21037/qims-2025-159. Epub 2025 May 30.
The high incidence of thyroid nodules (TNs) necessitates accurate and effective differentiation between benign and malignant cases to avoid overtreatment, which is crucial for both patients and doctors. The aim of this study was to develop and visualize an integrated model to enhance the diagnostic capability of young radiologists in evaluating TNs.
A retrospective collection of 1,501 ultrasound (US) images of TNs were randomly divided into training and validation sets. An independent test set comprised 541 patients from The First Affiliated Hospital of Anhui Medical University and the Affiliated Hospital of Integration Chinese and Western Medicine with Nanjing University of Traditional Chinese Medicine. We fine-tuned five ImageNet-pretrained deep learning (DL) models via transfer learning (TL) on US images to generate prediction scores and construct the final model. Gradient-weighted class activation mapping (Grad-CAM) was employed to highlight sensitive areas of the US images that contribute to nodule classification. Additionally, a comprehensive model was established utilizing both US image features and DL features, and an online dynamic nomogram was subsequently created for practical application. Models were compared and evaluated for discrimination, calibration, and effectiveness, to ascertain whether the DL model can improve radiologists' diagnosis of TNs.
The DL model demonstrated superior performance compared to the US model, with area under the receiver operating characteristic (ROC) curve (AUC) values of 0.875 and 0.787 on the test set, respectively. When combined into a comprehensive diagnostic model, a significant improvement was observed (test set AUC: 0.907). The Net Reclassification Index (NRI) results indicate that the heat maps and scores output by the DL model help to improve radiologists' classification accuracy in distinguishing between benign and malignant nodules.
The integrated model based on US image features and DL features demonstrates good diagnostic performance for distinguishing between benign and malignant TNs.
甲状腺结节（TNs）的高发病率使得准确有效地鉴别良恶性病例以避免过度治疗成为必要，这对患者和医生都至关重要。本研究的目的是开发并可视化一个综合模型，以提高年轻放射科医生评估TNs的诊断能力。
回顾性收集1501例TNs的超声（US）图像，随机分为训练集和验证集。一个独立测试集包括来自安徽医科大学第一附属医院以及南京中医药大学中西医结合附属医院的541例患者。我们通过对US图像进行迁移学习（TL）对五个ImageNet预训练的深度学习（DL）模型进行微调，以生成预测分数并构建最终模型。采用梯度加权类激活映射（Grad-CAM）来突出有助于结节分类的US图像敏感区域。此外，利用US图像特征和DL特征建立了一个综合模型，随后创建了一个在线动态列线图以供实际应用。对模型的区分度、校准度和有效性进行比较和评估，以确定DL模型是否能改善放射科医生对TNs的诊断。
与US模型相比，DL模型表现出更优的性能，测试集上的受试者操作特征（ROC）曲线下面积（AUC）值分别为0.875和0.787。当组合成一个综合诊断模型时，观察到显著改善（测试集AUC：0.907）。净重新分类指数（NRI）结果表明，DL模型输出的热图和分数有助于提高放射科医生区分良恶性结节的分类准确性。
基于US图像特征和DL特征的综合模型在区分良性和恶性TNs方面表现出良好的诊断性能。
