PDF(Pubmed)
Abstract：
BACKGROUND: To develop a deep learning(DL) model utilizing ultrasound images, and evaluate its efficacy in distinguishing between benign and malignant parotid tumors (PTs), as well as its practicality in assisting clinicians with accurate diagnosis.
METHODS: A total of 2211 ultrasound images of 980 pathologically confirmed PTs (Training set: n = 721; Validation set: n = 82; Internal-test set: n = 89; External-test set: n = 88) from 907 patients were retrospectively included in this study. The optimal model was selected and the diagnostic performance evaluation is conducted by utilizing the area under curve (AUC) of the receiver-operating characteristic(ROC) based on five different DL networks constructed at varying depths. Furthermore, a comparison of different seniority radiologists was made in the presence of the optimal auxiliary diagnosis model. Additionally, the diagnostic confusion matrix of the optimal model was calculated, and an analysis and summary of misjudged cases\' characteristics were conducted.
RESULTS: The Resnet18 demonstrated superior diagnostic performance, with an AUC value of 0.947, accuracy of 88.5%, sensitivity of 78.2%, and specificity of 92.7% in internal-test set, and with an AUC value of 0.925, accuracy of 89.8%, sensitivity of 83.3%, and specificity of 90.6% in external-test set. The PTs were subjectively assessed twice by six radiologists, both with and without the assisted of the model. With the assisted of the model, both junior and senior radiologists demonstrated enhanced diagnostic performance. In the internal-test set, there was an increase in AUC values by 0.062 and 0.082 for junior radiologists respectively, while senior radiologists experienced an improvement of 0.066 and 0.106 in their respective AUC values.
CONCLUSIONS: The DL model based on ultrasound images demonstrates exceptional capability in distinguishing between benign and malignant PTs, thereby assisting radiologists of varying expertise levels to achieve heightened diagnostic performance, and serve as a noninvasive imaging adjunct diagnostic method for clinical purposes.
METHODS: A total of 2211 ultrasound images of 980 pathologically confirmed PTs (Training set: n = 721; Validation set: n = 82; Internal-test set: n = 89; External-test set: n = 88) from 907 patients were retrospectively included in this study. The optimal model was selected and the diagnostic performance evaluation is conducted by utilizing the area under curve (AUC) of the receiver-operating characteristic(ROC) based on five different DL networks constructed at varying depths. Furthermore, a comparison of different seniority radiologists was made in the presence of the optimal auxiliary diagnosis model. Additionally, the diagnostic confusion matrix of the optimal model was calculated, and an analysis and summary of misjudged cases\' characteristics were conducted.
RESULTS: The Resnet18 demonstrated superior diagnostic performance, with an AUC value of 0.947, accuracy of 88.5%, sensitivity of 78.2%, and specificity of 92.7% in internal-test set, and with an AUC value of 0.925, accuracy of 89.8%, sensitivity of 83.3%, and specificity of 90.6% in external-test set. The PTs were subjectively assessed twice by six radiologists, both with and without the assisted of the model. With the assisted of the model, both junior and senior radiologists demonstrated enhanced diagnostic performance. In the internal-test set, there was an increase in AUC values by 0.062 and 0.082 for junior radiologists respectively, while senior radiologists experienced an improvement of 0.066 and 0.106 in their respective AUC values.
CONCLUSIONS: The DL model based on ultrasound images demonstrates exceptional capability in distinguishing between benign and malignant PTs, thereby assisting radiologists of varying expertise levels to achieve heightened diagnostic performance, and serve as a noninvasive imaging adjunct diagnostic method for clinical purposes.
摘要：
背景：为了利用超声图像开发深度学习（DL）模型，并评估其在区分良性和恶性腮腺肿瘤（PT）中的功效，以及它在协助临床医生准确诊断方面的实用性。
方法：回顾性研究共纳入907例患者的980例经病理证实的PT的2211张超声图像（训练集：n=721；验证集：n=82；内部测试集：n=89；外部测试集：n=88）。选择最佳模型，并基于在不同深度构建的五个不同DL网络，通过利用接收器工作特性（ROC）的曲线下面积（AUC）进行诊断性能评估。此外，在存在最佳辅助诊断模型的情况下，对不同资历的放射科医师进行了比较。此外,计算了最优模型的诊断混淆矩阵，并对误判案件的特点进行了分析和总结。
结果：Resnet18表现出卓越的诊断性能，AUC值为0.947，准确率为88.5%，灵敏度为78.2%，内部测试集的特异性为92.7%，AUC值为0.925，准确率为89.8%，灵敏度83.3%,外部测试集的特异性为90.6%。六位放射科医生对PT进行了两次主观评估，无论有没有模型的辅助。在模型的辅助下，初级和高级放射科医师均表现出增强的诊断性能.在内部测试集中，初级放射科医生的AUC值分别增加了0.062和0.082，而资深放射科医师的AUC值分别提高了0.066和0.106。
结论：基于超声图像的DL模型显示出区分良性和恶性PT的特殊能力，从而协助不同专业知识水平的放射科医生实现提高诊断性能，并作为临床目的的非侵入性成像辅助诊断方法。
方法：回顾性研究共纳入907例患者的980例经病理证实的PT的2211张超声图像（训练集：n=721；验证集：n=82；内部测试集：n=89；外部测试集：n=88）。选择最佳模型，并基于在不同深度构建的五个不同DL网络，通过利用接收器工作特性（ROC）的曲线下面积（AUC）进行诊断性能评估。此外，在存在最佳辅助诊断模型的情况下，对不同资历的放射科医师进行了比较。此外,计算了最优模型的诊断混淆矩阵，并对误判案件的特点进行了分析和总结。
结果：Resnet18表现出卓越的诊断性能，AUC值为0.947，准确率为88.5%，灵敏度为78.2%，内部测试集的特异性为92.7%，AUC值为0.925，准确率为89.8%，灵敏度83.3%,外部测试集的特异性为90.6%。六位放射科医生对PT进行了两次主观评估，无论有没有模型的辅助。在模型的辅助下，初级和高级放射科医师均表现出增强的诊断性能.在内部测试集中，初级放射科医生的AUC值分别增加了0.062和0.082，而资深放射科医师的AUC值分别提高了0.066和0.106。
结论：基于超声图像的DL模型显示出区分良性和恶性PT的特殊能力，从而协助不同专业知识水平的放射科医生实现提高诊断性能，并作为临床目的的非侵入性成像辅助诊断方法。
