Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, 72 E. Concord Street, Evans 636, Boston, MA, 02118, USA.
Section of Rheumatology, Department of Medicine, Boston University School of Medicine, Boston, MA, 02118, USA.
Eur Radiol. 2020 Jun;30(6):3538-3548. doi: 10.1007/s00330-020-06658-3. Epub 2020 Feb 13.
It remains difficult to characterize the source of pain in knee joints either using radiographs or magnetic resonance imaging (MRI). We sought to determine if advanced machine learning methods such as deep neural networks could distinguish knees with pain from those without it and identify the structural features that are associated with knee pain.
We constructed a convolutional Siamese network to associate MRI scans obtained on subjects from the Osteoarthritis Initiative (OAI) with frequent unilateral knee pain comparing the knee with frequent pain to the contralateral knee without pain. The Siamese network architecture enabled pairwise learning of information from two-dimensional (2D) sagittal intermediate-weighted turbo spin echo slices obtained from similar locations on both knees. Class activation mapping (CAM) was utilized to create saliency maps, which highlighted the regions most associated with knee pain. The MRI scans and the CAMs of each subject were reviewed by an expert radiologist to identify the presence of abnormalities within the model-predicted regions of high association.
Using 10-fold cross-validation, our model achieved an area under curve (AUC) value of 0.808. When individuals whose knee WOMAC pain scores were not discordant were excluded, model performance increased to 0.853. The radiologist review revealed that about 86% of the cases that were predicted correctly had effusion-synovitis within the regions that were most associated with pain.
This study demonstrates a proof of principle that deep learning can be applied to assess knee pain from MRI scans.
• Our article is the first to leverage a deep learning framework to associate MR images of the knee with knee pain. • We developed a convolutional Siamese network that had the ability to fuse information from multiple two-dimensional (2D) MRI slices from the knee with pain and the contralateral knee of the same individual without pain to predict unilateral knee pain. • Our model achieved an area under curve (AUC) value of 0.808. When individuals who had WOMAC pain scores that were not discordant for knees (pain discordance < 3) were excluded, model performance increased to 0.853.
无论是使用射线照相术还是磁共振成像（MRI），都很难对膝关节的疼痛源进行特征描述。我们试图确定是否可以使用深度学习等先进的机器学习方法来区分有疼痛和无疼痛的膝关节，并确定与膝关节疼痛相关的结构特征。
我们构建了一个卷积孪生网络，将来自 Osteoarthritis Initiative（OAI）的受试者的 MRI 扫描与频繁的单侧膝关节疼痛进行关联，将疼痛的膝关节与无症状的对侧膝关节进行比较。孪生网络架构允许从两个膝关节相似位置获得的二维（2D）矢状中等加权涡轮自旋回波切片中对信息进行成对学习。利用类激活映射（CAM）创建显著图，突出与膝关节疼痛最相关的区域。对每个受试者的 MRI 扫描和 CAM 进行了专家放射科医生的审查，以识别模型预测的高关联区域内的异常情况。
使用 10 倍交叉验证，我们的模型获得了 0.808 的曲线下面积（AUC）值。当排除膝关节 WOMAC 疼痛评分不一致的个体时，模型性能提高到 0.853。放射科医生的审查结果表明，大约 86%的预测正确的病例在与疼痛最相关的区域内存在渗出性滑膜炎。
本研究证明了深度学习可用于从 MRI 扫描评估膝关节疼痛的原理。
本文首次利用深度学习框架将膝关节 MRI 图像与膝关节疼痛相关联。
我们开发了一个卷积孪生网络，该网络能够融合来自疼痛膝关节和同一个体无症状对侧膝关节的多个二维（2D）MRI 切片的信息，以预测单侧膝关节疼痛。
我们的模型获得了 0.808 的 AUC 值。当排除 WOMAC 疼痛评分不一致的个体（疼痛不一致<3）时，模型性能提高到 0.853。
