深度学习自动检测和分类肩关节置换假体模型
研究纳入482例公开影像库的肩关节X线片,训练基于ResNet的深度卷积神经网络二分类器,分别检测肩关节置换假体、区分全肩关节置换与反式全肩关节置换、区分五种全肩关节置换模型;检测假体AUC-ROC为1.0,区分全肩与反式AUC-ROC为0.97,区分五种模型AUC-ROC为0.86至1.0。
要点
- 深度卷积神经网络检测肩关节置换假体的AUC-ROC达1.0。
- 区分全肩关节置换与反式全肩关节置换的AUC-ROC为0.97。
- 区分五种全肩关节置换模型的AUC-ROC为0.86至1.0。
核心结论
- 深度卷积神经网络能准确识别肩关节置换假体的存在、区分全肩关节置换与反式全肩关节置换,并以高准确率分类五种全肩关节置换模型。
研究设计与样本
- 研究为基于深度卷积神经网络(DCNN)的影像分类研究,纳入482例来自公开影像库的肩关节X线摄影检查,包含原生肩关节、反式全肩关节置换植入物及五种不同的全肩关节置换模型。
- 训练了基于ResNet的独立二分类器,分别用于检测肩关节置换植入物、区分全肩关节置换与反式全肩关节置换,以及区分五种全肩关节置换模型(每种模型使用一个独立分类器)。
- 数据集分为训练集、验证集和测试集,训练集和验证集进行了20倍数据增强;测试性能采用受试者工作特征曲线下面积(AUC-ROC)分析评估。
关键影像表现/征象
- 类激活图分析显示,DCNN在决策时重点关注的区域为假体组件的特征性表现。
- 区分五种全肩关节置换模型的类激活图分析显示,DCNN重点关注的区域为各植入物独特的设计特征。
诊断标准与关键数值
- 检测肩关节置换植入物存在的DCNN的AUC-ROC为1.0。
- 区分全肩关节置换与反式全肩关节置换的AUC-ROC为0.97。
- 区分五种全肩关节置换模型的DCNN的AUC-ROC范围为0.86(Stryker Solar)至1.0(Zimmer Bigliani-Flatow)。
临床应用与阅片要点
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
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
OBJECTIVE: To develop and evaluate the performance of deep convolutional neural networks (DCNN) to detect and identify specific total shoulder arthroplasty (TSA) models.
MATERIALS AND METHODS: We included 482 radiography studies obtained from publicly available image repositories with native shoulders, reverse TSA (RTSA) implants, and five different TSA models. We trained separate ResNet DCNN-based binary classifiers to (1) detect the presence of shoulder arthroplasty implants, (2) differentiate between TSA and RTSA, and (3) differentiate between the five TSA models, using five individual classifiers for each model, respectively. Datasets were divided into training, validation, and test datasets. Training and validation datasets were 20-fold augmented. Test performances were assessed with area under the receiver-operating characteristic curves (AUC-ROC) analyses. Class activation mapping was used to identify distinguishing imaging features used for DCNN classification decisions.
RESULTS: The DCNN for the detection of the presence of shoulder arthroplasty implants achieved an AUC-ROC of 1.0, whereas the AUC-ROC for differentiation between TSA and RTSA was 0.97. Class activation map analysis demonstrated the emphasis on the characteristic arthroplasty components in decision-making. DCNNs trained to distinguish between the five TSA models achieved AUC-ROCs ranging from 0.86 for Stryker Solar to 1.0 for Zimmer Bigliani-Flatow with class activation map analysis demonstrating an emphasis on unique implant design features.
CONCLUSION: DCNNs can accurately identify the presence of and distinguish between TSA & RTSA, and classify five specific TSA models with high accuracy. The proof of concept of these DCNNs may set the foundation for an automated arthroplasty atlas for rapid and comprehensive model identification.
引用
- Yi PH, Kim TK, Wei J, et al. Automated detection and classification of shoulder arthroplasty models using deep learning. Skeletal Radiol. 2020. PMID: 32415371. doi:10.1007/s00256-020-03463-3
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。