Department of Physical Therapy, Faculty of Rehabilitation Medicine, University of Alberta, 2-50 Corbett Hall, Edmonton, AB, T6G2G4, Canada.
Neuromuscular Control and Biomechanics Laboratory, Department of Mechanical Engineering, Faculty of Engineering, Nanotechnology Research Centre, University of Alberta, 5-046, Edmonton, AB, T6G 2M9, Canada.
Eur Spine J. 2022 Aug;31(8):1979-1991. doi: 10.1007/s00586-021-07036-3. Epub 2021 Oct 30.
Recent advances in texture analysis and machine learning offer new opportunities to improve the application of imaging to intervertebral disc biomechanics. This study employed texture analysis and machine learning on MRIs to investigate the lumbar disc's response to loading.
Thirty-five volunteers (30 (SD 11) yrs.) with and without chronic back pain spent 20 min lying in a relaxed unloaded supine position, followed by 20 min loaded in compression, and then 20 min with traction applied. T-weighted MR images were acquired during the last 5 min of each loading condition. Custom image analysis software was used to segment discs from adjacent tissues semi-automatically and segment each disc into the nucleus, anterior and posterior annulus automatically. A grey-level, co-occurrence matrix with one to four pixels offset in four directions (0°, 45°, 90° and 135°) was then constructed (320 feature/tissue). The Random Forest Algorithm was used to select the most promising classifiers. Linear mixed-effect models and Cohen's d compared loading conditions.
All statistically significant differences (p < 0.001) were observed in the nucleus and posterior annulus in the 135° offset direction at the L4-5 level between lumbar compression and traction. Correlation (P, P) and information measure of correlation 1 (P, P) detected significant changes in the nucleus. Statistically significant changes were also observed for homogeneity (P, P), contrast (P), and difference variance (P) of the posterior annulus.
MRI textural features may have the potential of identifying the disc's response to loading, particularly in the nucleus and posterior annulus, which appear most sensitive to loading.
Diagnostic: individual cross-sectional studies with consistently applied reference standard and blinding.
纹理分析和机器学习的最新进展为提高成像在椎间盘生物力学中的应用提供了新的机会。本研究通过 MRI 上的纹理分析和机器学习来研究腰椎间盘对载荷的反应。
35 名志愿者（30 岁（标准差 11 岁），有无慢性腰痛）分别在放松的仰卧无负载位、压缩负载位和牵引位各躺 20 分钟。在每个加载条件的最后 5 分钟内采集 T2 加权 MRI 图像。使用定制的图像分析软件半自动地将椎间盘与相邻组织分离，并自动将每个椎间盘分割为核、前环和后环。然后构建一个灰度、共生矩阵，其中一个到四个像素在四个方向（0°、45°、90°和 135°）偏移（320 个特征/组织）。随机森林算法用于选择最有前途的分类器。线性混合效应模型和 Cohen's d 比较了加载条件。
在 L4-5 水平的 135°偏移方向，核和后环在腰椎压缩和牵引之间，所有具有统计学意义的差异（p < 0.001）均可见。相关性（P，P）和相关信息测度 1（P，P）检测到核的显著变化。后环的同质性（P，P）、对比度（P）和差方差（P）也观察到了统计学上显著的变化。
MRI 纹理特征可能具有识别椎间盘对载荷反应的潜力，特别是在核和后环，它们对载荷最敏感。
诊断：个体横断面研究，始终应用参考标准和盲法。
