Cheung Jason Pui Yin, Kuang Xihe, Zhang Teng, Wang Kun, Yang Cao
Department of Orthopaedics and Traumatology, The University of Hong Kong, Hong Kong SAR, China.
Digital Health Laboratory, School of Clinical Medicine, The University of Hong Kong, Hong Kong SAR, China.
J Orthop. 2023 Mar 1;38:7-13. doi: 10.1016/j.jor.2023.03.001. eCollection 2023 Apr.
Lumbar disc degeneration (LDD) is considered as one of the main causes of low back pain. For clinical diagnosis of LDD, magnetic resonance imaging (MRI) is commonly used. Schmorl's node, high intensity zone (HIZ), Modic changes, and other MRI biomarkers of intervertebral disc (IVD) degeneration are also associated with low back pain. However, the progression and natural history of these features are unclear and there is limited predictive capacity with MRI.
We aim to establish and validate a deep learning pipeline, EDPP-Flow, for the 5-year progression prediction of Schmorl's node, HIZ, and Modic changes, based on clinical MRIs.
An MRI dataset developed on 1152 volunteers was used in this study. For each volunteer, two MRI scans, at baseline and 5-year follow-up, were collected and pathology labels were annotated as present or absent (with/without pathology) by two specialists with over 10 years of clinical experience. Our pipeline contained the published MRI-SegFlow and state-of-the-art convolutional neural network for progression prediction of endplate defects. The label distribution of the dataset is unbalanced, where the number of present samples was much smaller than absent samples. The resampling and data augmentation strategies were adopted to increase the number of present samples in the training process and balance the influence of different samples on the model, which can improve the prediction accuracy.
Our pipeline achieved high weighted accuracy, sensitivity, and specificity for progression prediction of Schmorl's node (89.46 ± 3.71%, 89.19 ± 2.70%, 89.72 ± 2.42%), HIZ (91.75 ± 2.48%, 93.07 ± 3.96%, 90.43 ± 2.51%), and Modic changes (87.51 ± 2.23%, 87.93 ± 1.72%, 87.10 ± 1.99%), on the unbalanced dataset (present sample's percentages of the 3 pathologies above were 4.3%, 11.7%, and 6.7%).
We developed and validated a deep learning pipeline, for the progression prediction of endplate defects, which showed high prediction accuracy on unbalanced data. The method has significant potential for clinical implementation.
腰椎间盘退变（LDD）被认为是腰痛的主要原因之一。对于LDD的临床诊断，磁共振成像（MRI）是常用的方法。Schmorl结节、高强度区（HIZ）、Modic改变以及椎间盘（IVD）退变的其他MRI生物标志物也与腰痛相关。然而，这些特征的进展情况和自然病史尚不清楚，并且MRI的预测能力有限。
我们旨在基于临床MRI建立并验证一种深度学习流程EDPP-Flow，用于对Schmorl结节、HIZ和Modic改变进行5年进展预测。
本研究使用了一个基于1152名志愿者建立的MRI数据集。对于每名志愿者，收集了基线和5年随访时的两次MRI扫描图像，由两名具有超过10年临床经验的专家将病理标签标注为存在或不存在（有/无病理）。我们的流程包含已发表的MRI-SegFlow和用于终板缺陷进展预测的先进卷积神经网络。该数据集的标签分布不均衡，其中存在样本的数量远少于不存在样本的数量。在训练过程中采用了重采样和数据增强策略，以增加存在样本的数量并平衡不同样本对模型产生的影响，从而提高预测准确性。
在不均衡数据集上（上述3种病理的存在样本百分比分别为4.3%、11.7%和6.7%），我们的流程对Schmorl结节进展预测的加权准确率、敏感性和特异性较高（分别为89.46±3.71%、89.19±2.70%、89.72±2.42%），对HIZ进展预测的加权准确率、敏感性和特异性较高（分别为91.75±2.48%、93.07±3.96%、90.43±2.51%），对Modic改变进展预测的加权准确率、敏感性和特异性较高（分别为87.51±2.23%、87.93±1.72%、87.10±1.99%）。
我们开发并验证了一种用于终板缺陷进展预测的深度学习流程，并在不均衡数据上显示出较高的预测准确性。该方法具有显著的临床应用潜力。
