Qiao Tingting, Liu Simin, Cui Zhijun, Yu Xiaqing, Cai Haidong, Zhang Huijuan, Sun Ming, Lv Zhongwei, Li Dan
Department of Nuclear Medicine, Shanghai Tenth People's Hospital, Tongji University School of Medicine, Shanghai, China.
Department of Medicine Imaging, the Chongming Branch of Shanghai Tenth People's Hospital, Tongji University, Shanghai, China.
J Int Med Res. 2021 Jan;49(1):300060520982842. doi: 10.1177/0300060520982842.
To construct deep learning (DL) models to improve the accuracy and efficiency of thyroid disease diagnosis by thyroid scintigraphy.
We constructed DL models with AlexNet, VGGNet, and ResNet. The models were trained separately with transfer learning. We measured each model's performance with six indicators: recall, precision, negative predictive value (NPV), specificity, accuracy, and F1-score. We also compared the diagnostic performances of first- and third-year nuclear medicine (NM) residents with assistance from the best-performing DL-based model. The Kappa coefficient and average classification time of each model were compared with those of two NM residents.
The recall, precision, NPV, specificity, accuracy, and F1-score of the three models ranged from 73.33% to 97.00%. The Kappa coefficient of all three models was >0.710. All models performed better than the first-year NM resident but not as well as the third-year NM resident in terms of diagnostic ability. However, the ResNet model provided "diagnostic assistance" to the NM residents. The models provided results at speeds 400 to 600 times faster than the NM residents.
DL-based models perform well in diagnostic assessment by thyroid scintigraphy. These models may serve as tools for NM residents in the diagnosis of Graves' disease and subacute thyroiditis.
构建深度学习（DL）模型，以提高甲状腺闪烁扫描对甲状腺疾病诊断的准确性和效率。
我们使用AlexNet、VGGNet和ResNet构建了DL模型。这些模型通过迁移学习分别进行训练。我们用六个指标来衡量每个模型的性能：召回率、精确率、阴性预测值（NPV）、特异性、准确率和F1分数。我们还在性能最佳的基于DL的模型的辅助下，比较了第一年和第三年核医学（NM）住院医师的诊断性能。将每个模型的Kappa系数和平均分类时间与两名NM住院医师的进行比较。
三个模型的召回率、精确率、NPV、特异性、准确率和F1分数在73.33%至97.00%之间。所有三个模型的Kappa系数均>0.710。在诊断能力方面，所有模型的表现均优于第一年的NM住院医师，但不如第三年的NM住院医师。然而，ResNet模型为NM住院医师提供了“诊断辅助”。这些模型给出结果的速度比NM住院医师快400至600倍。
基于DL的模型在甲状腺闪烁扫描的诊断评估中表现良好。这些模型可作为NM住院医师诊断Graves病和亚急性甲状腺炎的工具。
