Visible and Near-Infrared Spectroscopy Enables Differentiation of Normal and Early Osteoarthritic Human Knee Joint Articular Cartilage

Abstract

Osteoarthritis degenerates cartilage and impairs joint function. Early intervention opportunities are missed as current diagnostic methods are insensitive to early tissue degeneration. We investigated the capability of visible light-near-infrared spectroscopy (Vis-NIRS) to differentiate normal human cartilage from early osteoarthritic one. Vis-NIRS spectra, biomechanical properties and the state of osteoarthritis (OARSI grade) were quantified from osteochondral samples harvested from different anatomical sites of human cadaver knees. Two support vector machines (SVM) classifiers were developed based on the Vis-NIRS spectra and OARSI scores. The first classifier was designed to distinguish normal (OARSI: 0-1) from general osteoarthritic cartilage (OARSI: 2-5) to check the general suitability of the approach yielding an average accuracy of 75% (AUC = 0.77). Then, the second classifier was designed to distinguish normal from early osteoarthritic cartilage (OARSI: 2-3) yielding an average accuracy of 71% (AUC = 0.73). Important wavelength regions for differentiating normal from early osteoarthritic cartilage were related to collagen organization (wavelength region: 400-600 nm), collagen content (1000-1300 nm) and proteoglycan content (1600-1850 nm). The findings suggest that Vis-NIRS allows objective differentiation of normal and early osteoarthritic tissue, e.g., during arthroscopic repair surgeries.

Keywords: Biomechanics; Cartilage; Machine learning; Near-infrared spectroscopy; Osteoarthritis; Visible light spectroscopy.

Fig. 1

Schematic of the knee map. Cartilage samples were extracted from the patella, trochlea, femur, and tibia regions. Modified from [32]

Fig. 2

a Cartilage samples were extracted from six (6) sites of the human knee joint. b The samples were characterized using Vis-NIR spectroscopy followed by biomechanical testing of the samples. Subsequently, histological sections of the samples were prepared and graded according to OARSI grading. c The acquired spectra were trimmed (400–1400 nm, 1520–1850 nm) and the 30 most important wavelengths were selected using a sequential feature selection algorithm. d This was followed by model training based on SVM. e A T-distributed Stochastic Neighboring Entity (t-SNE) plot is used to illustrate SVM classification. The blue concentric diamond-shaped rings show the probability of classification as normal tissue. The purple dots indicate normal tissue, and the yellow dots indicate OA tissue. f Permutation feature importance was used to rank wavelength contribution to classifier accuracy

Fig. 3

Schematic of the spectral data collection setup

Fig. 4

a Biomechanical stress-relaxation and dynamic testing were performed. Instantaneous, equilibrium, dynamic moduli and phase angles were determined for each sample. b Representative histological images of cartilage samples with varying histological grades.

Fig. 5

a The mean spectra comparison of normal, early OA, and advanced OA tissue. Spectral regions associated with collagen structure (400–700 nm) [17] based on scattering, collagen content (1000–1400 nm) [1, 31], and proteoglycan content (1600–1800 nm) [1, 31] are indicated. Due to noise, the spectral region 1400–1520 nm and 1850–2400 nm were truncated, b Site-specific comparison of model accuracy when full spectral wavelengths are included and when 30 wavelengths are selected using sequential feature selection.

Fig. 6

ROC curves and corresponding areas under the curve (AUC) for evaluating the ability of Vis-NIR to detect normal from OA or early OA tissue based on OARSI groups in each joint site, a AUC for Classifier 1 and, b AUC for Classifier 2. AUC measures the ability of the classifiers to avoid erroneous classification.

Fig. 7

Comparison between normal and OA tissue based on OARSI groups assigned by trained individuals (normal = OARSI 0–1 and OA = OARSI 2–5) and groups assigned based on Classifier 1 predictions. The plain box and whisker plots show the biomechanical properties of OARSI groups. The box with oblique lines shows the biomechanical properties of Classifier 1 prediction groups. The dynamic modulus and phase angles were analyzed at 1 Hz loading frequency. LF lateral femur, MF medial femur, LT lateral tibial, MT medial tibial, TR trochlear, PT patella. *p < 0.05 and **p < 0.001

Fig. 8

Comparison between normal and OA tissue based on OARSI groups assigned by trained individuals (normal = OARSI 0–1 and early OA = OARSI 2−3) and groups assigned based on Classifier 2 predictions. The plain box and whisker plots show the biomechanical properties of OARSI groups. The box with oblique lines shows the biomechanical properties of Classifier 2 prediction groups. The dynamic modulus and phase angles were analyzed at 1 Hz loading frequency. LF lateral femur, MF medial femur, LT lateral tibial, MT medial tibial, TR trochlear, PT patella. *p < 0.05 and **p < 0.001