Division of Biomedical Informatics, Seoul National University Biomedical Informatics (SNUBI), Seoul National University College of Medicine, Seoul, 110799, Republic of Korea.
Department of Radiology, Ajou University School of Medicine, Wonchon-Dong, Yeongtong-Gu, Suwon, 443-380, South Korea.
Eur Radiol. 2019 Oct;29(10):5452-5457. doi: 10.1007/s00330-019-06098-8. Epub 2019 Mar 15.
To develop a deep learning-based computer-aided diagnosis (CAD) system for use in the CT diagnosis of cervical lymph node metastasis (LNM) in patients with thyroid cancer.
A total of 995 axial CT images that included benign (n = 647) and malignant (n = 348) lymph nodes were collected from 202 patients with thyroid cancer who underwent CT for surgical planning between July 2017 and January 2018. The datasets were randomly split into training (79.0%), validation (10.5%), and test (10.5%) datasets. Eight deep convolutional neural network (CNN) models were used to classify the images into metastatic or benign lymph nodes. Pretrained networks were used on the ImageNet and the best-performing algorithm was selected. Class-specific discriminative regions were visualized with attention heatmap using a global average pooling method.
The area under the ROC curve (AUROC) for the tested algorithms ranged from 0.909 to 0.953. The sensitivity, specificity, and accuracy of the best-performing algorithm were all 90.4%, respectively. Attention heatmap highlighted important subregions for further clinical review.
A deep learning-based CAD system could accurately classify cervical LNM in patients with thyroid cancer on preoperative CT with an AUROC of 0.953. Whether this approach has clinical utility will require evaluation in a clinical setting.
• A deep learning-based CAD system could accurately classify cervical lymph node metastasis. The AUROC for the eight tested algorithms ranged from 0.909 to 0.953. • Of the eight models, the ResNet50 algorithm was the best-performing model for the validation dataset with 0.953 AUROC. The sensitivity, specificity, and accuracy of the ResNet50 model were all 90.4%, respectively, in the test dataset. • Based on its high accuracy of 90.4%, we consider that this model may be useful in a clinical setting to detect LNM on preoperative CT in patients with thyroid cancer.
开发一种基于深度学习的计算机辅助诊断（CAD）系统，用于甲状腺癌患者 CT 诊断颈部淋巴结转移（LNM）。
从 2017 年 7 月至 2018 年 1 月期间因手术计划接受 CT 检查的 202 例甲状腺癌患者中收集了 995 张包括良性（n=647）和恶性（n=348）淋巴结的轴向 CT 图像。数据集随机分为训练（79.0%）、验证（10.5%）和测试（10.5%）数据集。使用 8 个深度卷积神经网络（CNN）模型将图像分类为转移性或良性淋巴结。在 ImageNet 上使用预训练的网络，并选择性能最佳的算法。使用全局平均池化方法通过注意力热图可视化具有类别特异性的判别区域。
测试算法的 ROC 曲线下面积（AUROC）范围为 0.909 至 0.953。性能最佳算法的敏感性、特异性和准确性分别为 90.4%。注意力热图突出了用于进一步临床复查的重要子区域。
基于深度学习的 CAD 系统可以在术前 CT 上准确分类甲状腺癌患者的颈部 LNM，AUROC 为 0.953。该方法是否具有临床实用性，需要在临床环境中进行评估。
基于深度学习的 CAD 系统可以准确分类颈部淋巴结转移。测试的 8 种算法的 AUROC 范围为 0.909 至 0.953。
在验证数据集中，ResNet50 算法是表现最好的模型，AUROC 为 0.953。在测试数据集中，ResNet50 模型的敏感性、特异性和准确性分别为 90.4%。
基于其 90.4%的高准确率，我们认为该模型在临床环境中可能有助于在术前 CT 上检测甲状腺癌患者的 LNM。
