Zhou Hui, Wang Kun, Tian Jie
IEEE Trans Biomed Eng. 2020 Oct;67(10):2773-2780. doi: 10.1109/TBME.2020.2971065. Epub 2020 Feb 3.
We aimed to propose a highly automatic and objective model named online transfer learning (OTL) for the differential diagnosis of benign and malignant thyroid nodules from ultrasound (US) images.
The OTL mothed combined the strategy of transfer learning and online learning. Two datasets (1750 thyroid nodules with 1078 benign and 672 malignant nodules, and 3852 thyroid nodules with 3213 benign and 639 malignant nodules) were collected to develop the model. The diagnostic accuracy was also compared with VGG-16 based transfer learning model and different input images based model. Analysis of receiver operating characteristic (ROC) curves were performed to calculate optimal area under it (AUC) for benign and malignant nodules.
AUC, sensitivity and specificity of OTL were 0.98 (95% confidence interval [CI]: 0.97-0.99), 98.7% (95% confidence interval [CI]: 97.8%-99.6%) and 98.8% (95% confidence interval [CI]: 97.9%-99.7%) in the final online learning step, which was significantly better than other deep learning models (P < 0.01).
OTL model shows the best overall performance comparing with other deep learning models. The model holds a good potential for improving the overall diagnostic efficacy in thyroid nodule US examinations.
The proposed OTL model could be seamlessly integrated into the conventional work-flow of thyroid nodule US examinations.
我们旨在提出一种名为在线迁移学习（OTL）的高度自动化且客观的模型，用于从超声（US）图像中对甲状腺良恶性结节进行鉴别诊断。
OTL方法结合了迁移学习和在线学习策略。收集了两个数据集（1750个甲状腺结节，其中1078个良性结节和672个恶性结节，以及3852个甲状腺结节，其中3213个良性结节和639个恶性结节）来开发该模型。还将诊断准确性与基于VGG - 16的迁移学习模型以及基于不同输入图像的模型进行了比较。进行了受试者操作特征（ROC）曲线分析，以计算良性和恶性结节的最佳曲线下面积（AUC）。
在最终的在线学习步骤中，OTL的AUC、敏感性和特异性分别为0.98（95%置信区间[CI]：0.97 - 0.99）、98.7%（95%置信区间[CI]：97.8% - 99.6%）和98.8%（95%置信区间[CI]：97.9% - 99.7%），显著优于其他深度学习模型（P < 0.01）。
与其他深度学习模型相比，OTL模型显示出最佳的整体性能。该模型在提高甲状腺结节超声检查的整体诊断效能方面具有良好的潜力。
所提出的OTL模型可以无缝集成到甲状腺结节超声检查的传统工作流程中。
