深度学习在甲状腺癌颈部淋巴结转移CT诊断中的应用
本研究收集202例甲状腺癌患者术前CT的995幅轴位图像(良性淋巴结647枚、恶性348枚),随机分为训练集(79.0%)、验证集(10.5%)和测试集(10.5%),用8种深度卷积神经网络模型分类转移性与良性淋巴结。测试算法AUROC为0.909~0.953,最佳模型ResNet50在验证集AUROC为0.953,测试集敏感度、特异度、准确率均为90.4%。作者认为该模型可能有助于临床检测术前CT上的淋巴结转移。
要点
- 基于CT的深度学习CAD系统可分类甲状腺癌颈部淋巴结转移,最佳模型测试集准确率90.4%。
- 8种测试算法AUROC为0.909~0.953,ResNet50在验证集表现最佳(AUROC 0.953)。
- 注意力热图可突出对临床复核重要的子区域。
核心结论
- 基于深度学习的CAD系统可在术前CT上准确分类甲状腺癌患者的颈部淋巴结转移,最佳模型AUROC为0.953;该方法是否具有临床实用性需在临床环境中评估。
研究设计与样本
- 回顾性收集2017年7月至2018年1月间202例甲状腺癌患者术前CT的995幅轴位图像(良性淋巴结647枚、恶性348枚),随机分为训练集79.0%、验证集10.5%、测试集10.5%,使用8种深度卷积神经网络模型,采用ImageNet预训练网络并选择最佳算法。
关键影像表现/征象
- 注意力热图突出对进一步临床复核重要的子区域。
诊断标准与关键数值
- 8种测试算法AUROC范围为0.909~0.953。
- ResNet50为验证集最佳模型,AUROC为0.953。
- ResNet50在测试集的敏感度、特异度、准确率均为90.4%。
临床应用与阅片要点
- 作者认为基于90.4%的准确率,该模型可能有助于临床检测甲状腺癌患者术前CT上的淋巴结转移。
- 注意力热图可突出重要子区域供进一步临床复核。
- 该方法是否具有临床实用性需在临床环境中评估。
局限性
- 原文结论指出该方法是否具有临床实用性需在临床环境中评估。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: 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.
METHODS: 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.
RESULTS: 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.
CONCLUSION: 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.
KEY POINTS: • 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.
引用
- Lee JH, Ha EJ, Kim JH, et al. Application of deep learning to the diagnosis of cervical lymph node metastasis from thyroid cancer with CT. Eur Radiol. 2019. PMID: 30877461. doi:10.1007/s00330-019-06098-8
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。