Department of Biomedical Engineering, Schulich School of Engineering, University of Calgary, Calgary, Canada; McCaig Institute for Bone and Joint Health, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.
McCaig Institute for Bone and Joint Health, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada; Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada.
Comput Biol Med. 2024 Aug;178:108791. doi: 10.1016/j.compbiomed.2024.108791. Epub 2024 Jun 20.
Traumatic bone marrow lesions (BML) are frequently identified on knee MRI scans in patients following an acute full-thickness, complete ACL tear. BMLs coincide with regions of elevated localized bone loss, and studies suggest these may act as a precursor to the development of post-traumatic osteoarthritis. This study addresses the labour-intensive manual assessment of BMLs by using a 3D U-Net for automated identification and segmentation from MRI scans.
A multi-task learning approach was used to segment both bone and BML from T2 fat-suppressed (FS) fast spin echo (FSE) MRI sequences for BML assessment. Training and testing utilized datasets from individuals with complete ACL tears, employing a five-fold cross-validation approach and pre-processing involved image intensity normalization and data augmentation. A post-processing algorithm was developed to improve segmentation and remove outliers. Training and testing datasets were acquired from different studies with similar imaging protocol to assess the model's performance robustness across different populations and acquisition conditions.
The 3D U-Net model exhibited effectiveness in semantic segmentation, while post-processing enhanced segmentation accuracy and precision through morphological operations. The trained model with post-processing achieved a Dice similarity coefficient (DSC) of 0.75 ± 0.08 (mean ± std) and a precision of 0.87 ± 0.07 for BML segmentation on testing data. Additionally, the trained model with post-processing achieved a DSC of 0.93 ± 0.02 and a precision of 0.92 ± 0.02 for bone segmentation on testing data. This demonstrates the approach's high accuracy for capturing true positives and effectively minimizing false positives in the identification and segmentation of bone structures.
Automated segmentation methods are a valuable tool for clinicians and researchers, streamlining the assessment of BMLs and allowing for longitudinal assessments. This study presents a model with promising clinical efficacy and provides a quantitative approach for bone-related pathology research and diagnostics.
在急性全层、完全 ACL 撕裂后，膝关节 MRI 扫描常发现外伤性骨髓病变（BML）。BML 与局部骨量升高的区域重合，研究表明这些区域可能是创伤后骨关节炎发展的前兆。本研究通过使用 3D U-Net 对 MRI 扫描进行自动识别和分割，解决了 BML 手动评估繁琐的问题。
采用多任务学习方法，从 T2 脂肪抑制（FS）快速自旋回波（FSE）MRI 序列中分割骨和 BML ，用于 BML 评估。训练和测试使用 ACL 完全撕裂患者的数据，采用五折交叉验证方法，预处理包括图像强度归一化和数据增强。开发了一种后处理算法来提高分割的准确性和去除异常值。训练和测试数据集来自不同的研究，采用相似的成像协议，以评估模型在不同人群和采集条件下的性能稳健性。
3D U-Net 模型在语义分割方面表现出有效性，而后处理通过形态学操作提高了分割的准确性和精度。经过后处理的训练模型在测试数据上的 BML 分割中达到了 0.75±0.08（平均值±标准差）的 Dice 相似系数（DSC）和 0.87±0.07 的精度。此外，经过后处理的训练模型在测试数据上的骨分割中达到了 0.93±0.02 的 DSC 和 0.92±0.02 的精度。这表明该方法在识别和分割骨骼结构时具有很高的准确性，能够有效地减少假阳性的出现。
自动化分割方法是临床医生和研究人员的有用工具，可以简化 BML 的评估，并允许进行纵向评估。本研究提出了一种具有临床应用潜力的模型，为骨相关病理学研究和诊断提供了一种定量方法。
