University of Eastern Finland, Department of Applied Physics, FI-70211 Kuopio, FinlandbKuopio University Hospital, Department of Clinical Neurophysiology, FI-70029 Kuopio, Finland.
University of Oulu, Institute of Biomedicine, Department of Medical Technology, FI-90014 Oulu, FinlanddOulu University Hospital, Department of Diagnostic Radiology, FI-90014 Oulu, FinlandeOulu University Hospital and University of Oulu, Medical Research C.
J Biomed Opt. 2014 Feb;19(2):027003. doi: 10.1117/1.JBO.19.2.027003.
Articular cartilage (AC) is mainly composed of collagen, proteoglycans, chondrocytes, and water. These constituents are inhomogeneously distributed to provide unique biomechanical properties to the tissue. Characterization of the spatial distribution of these components in AC is important for understanding the function of the tissue and progress of osteoarthritis. Fourier transform infrared (FT-IR) absorption spectra exhibit detailed information about the biochemical composition of AC. However, highly specific FT-IR analysis for collagen and proteoglycans is challenging. In this study, a chemometric approach to predict the biochemical composition of AC from the FT-IR spectra was investigated. Partial least squares (PLS) regression was used to predict the proteoglycan content (n=32) and collagen content (n=28) of bovine cartilage samples from their average FT-IR spectra. The optimal variables for the PLS regression models were selected by using backward interval partial least squares and genetic algorithm. The linear correlation coefficients between the biochemical reference and predicted values of proteoglycan and collagen contents were r=0.923 (p<0.001) and r=0.896 (p<0.001), respectively. The results of the study show that variable selection algorithms can significantly improve the PLS regression models when the biochemical composition of AC is predicted.
关节软骨（AC）主要由胶原蛋白、蛋白聚糖、软骨细胞和水组成。这些成分呈不均匀分布，为组织提供独特的生物力学特性。对 AC 中这些成分的空间分布进行特征描述对于理解组织的功能和骨关节炎的进展非常重要。傅里叶变换红外（FT-IR）吸收光谱可提供有关 AC 生化成分的详细信息。然而，针对胶原蛋白和蛋白聚糖进行高度特异性的 FT-IR 分析具有挑战性。在这项研究中，研究了从 FT-IR 光谱预测 AC 生化组成的化学计量学方法。偏最小二乘（PLS）回归用于从牛软骨样本的平均 FT-IR 光谱预测其蛋白聚糖含量（n=32）和胶原蛋白含量（n=28）。通过使用反向间隔偏最小二乘和遗传算法选择 PLS 回归模型的最佳变量。生化参考值和预测值之间的蛋白聚糖和胶原蛋白含量的线性相关系数分别为 r=0.923（p<0.001）和 r=0.896（p<0.001）。研究结果表明，当预测 AC 的生化组成时，变量选择算法可以显著提高 PLS 回归模型的性能。
