基于深度学习在MRI上自动检测冈上肌腱撕裂的评估
本研究从机构数据库回顾性随机抽取2015至2019年200例肩部MRI,按全层撕裂、部分层撕裂、完整肌腱平衡采样,构建三阶段深度学习流程(切片选择ResNet、分割U-Net、多输入CNN分类器),由放射科fellow阅片并经两名肌骨放射科医师共识验证建立二分类参考标签。测试集分类器敏感度85.0%(95%CI 62.1-96.8%)、特异度85.0%(95%CI 62.1-96.8%),AUROC 0.943(95%CI 0.820-0.991),Dice分割准确度0.814(95%CI 0.805-0.826);1.5 T与3.0 T研究间AUROC无显著差异,全层撕裂亚组敏感度100%优于部分层撕裂亚组72.5%。
要点
- 测试集分类器敏感度85.0%、特异度85.0%,AUROC 0.943(95%CI 0.820-0.991)。
- 全层撕裂亚组敏感度100%,高于部分层撕裂亚组72.5%。
- 1.5 T与3.0 T研究间AUROC无显著差异。
核心结论
- 深度学习是在MRI上检测冈上肌腱撕裂的可行方法。
研究设计与样本
- 回顾性研究,2015至2019年从机构数据库平衡随机抽取200例肩部MRI(全层撕裂、部分层撕裂、完整冈上肌腱),20%为留出测试集、80%用于训练与优化并采用五折交叉验证;参考标准为放射科fellow结合报告与图像阅片后、经两名肌骨放射科医师共识验证的二分类标签。
诊断标准与关键数值
- 分类器在最佳约登指数时测试集敏感度85.0%(95%CI 62.1-96.8%)、特异度85.0%(95%CI 62.1-96.8%),AUROC 0.943(95%CI 0.820-0.991);分割Dice准确度0.814(95%CI 0.805-0.826);全层撕裂亚组敏感度100%,部分层撕裂亚组敏感度72.5%。
临床应用与阅片要点
- 作者结论认为深度学习是MRI上检测冈上肌腱撕裂的可行方法,原文未据此给出临床阅片或报告流程的具体推荐。
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 evaluate if deep learning is a feasible approach for automated detection of supraspinatus tears on MRI.
MATERIALS AND METHODS: A total of 200 shoulder MRI studies performed between 2015 and 2019 were retrospectively obtained from our institutional database using a balanced random sampling of studies containing a full-thickness tear, partial-thickness tear, or intact supraspinatus tendon. A 3-stage pipeline was developed comprised of a slice selection network based on a pre-trained residual neural network (ResNet); a segmentation network based on an encoder-decoder network (U-Net); and a custom multi-input convolutional neural network (CNN) classifier. Binary reference labels were created following review of radiologist reports and images by a radiology fellow and consensus validation by two musculoskeletal radiologists. Twenty percent of the data was reserved as a holdout test set with the remaining 80% used for training and optimization under a fivefold cross-validation strategy. Classification and segmentation accuracy were evaluated using area under the receiver operating characteristic curve (AUROC) and Dice similarity coefficient, respectively. Baseline characteristics in correctly versus incorrectly classified cases were compared using independent sample t-test and chi-squared.
RESULTS: Test sensitivity and specificity of the classifier at the optimal Youden's index were 85.0% (95% CI: 62.1-96.8%) and 85.0% (95% CI: 62.1-96.8%), respectively. AUROC was 0.943 (95% CI: 0.820-0.991). Dice segmentation accuracy was 0.814 (95% CI: 0.805-0.826). There was no significant difference in AUROC between 1.5 T and 3.0 T studies. Sub-analysis showed superior sensitivity on full-thickness (100%) versus partial-thickness (72.5%) subgroups.
DATA CONCLUSION: Deep learning is a feasible approach to detect supraspinatus tears on MRI.
引用
- Yao, Chepelev, Nisha, et al. Evaluation of a deep learning method for the automated detection of supraspinatus tears on MRI. Skeletal Radiol. 2022. PMID: 35190850. doi:10.1007/s00256-022-04008-6
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。