Machine learning augmented near-infrared spectroscopy: In vivo follow-up of cartilage defects.

OBJECTIVE: To assess the potential of near-infrared spectroscopy (NIRS) for in vivo arthroscopic monitoring of cartilage defects. METHOD: Sharp and blunt cartilage grooves were induced in the radiocarpal and intercarpal joints of Shetland ponies and monitored at baseline (0 weeks) and at three follow-up timepoints (11, 23, and 39 weeks) by measuring near-infrared spectra in vivo at and around the grooves. The animals were sacrificed after 39 weeks and the joints were harvested. Spectra were reacquired ex vivo to ensure reliability of in vivo measurements and for reference analyses. Additionally, cartilage thickness and instantaneous modulus were determined via computed tomography and mechanical testing, respectively. The relationship between the ex vivo spectra and cartilage reference properties was determined using convolutional neural network. RESULTS: In an independent test set, the trained networks yielded significant correlations for cartilage thickness (ρ = 0.473) and instantaneous modulus (ρ = 0.498). These networks were used to predict the reference properties at baseline and at follow-up time points. In the radiocarpal joint, cartilage thickness increased significantly with both groove types after baseline and remained swollen. Additionally, at 39 weeks, a significant difference was observed in cartilage thickness between controls and sharp grooves. For the instantaneous modulus, a significant decrease was observed with both groove types in the radiocarpal joint from baseline to 23 and 39 weeks. CONCLUSION: NIRS combined with machine learning enabled determination of cartilage properties in vivo, thereby providing longitudinal evaluation of post-intervention injury development. Additionally, radiocarpal joints were found more vulnerable to cartilage degeneration after damage than intercarpal joints.

Semi-automated International Cartilage Repair Society scoring of equine articular cartilage lesions in optical coherence tomography images.

BACKGROUND: Arthroscopic optical coherence tomography (OCT) is a promising tool for the detailed evaluation of articular cartilage injuries. However, OCT-based articular cartilage scoring still relies on the operator's visual estimation. OBJECTIVES: To test the hypothesis that semi-automated International Cartilage Repair Society (ICRS) scoring of chondral lesions seen in OCT images could enhance intra- and interobserver agreement of scoring and its accuracy. STUDY DESIGN: Validation study using equine cadaver tissue. METHODS: Osteochondral samples (n = 99) were prepared from 18 equine metacarpophalangeal joints and imaged using OCT. Custom-made software was developed for semi-automated ICRS scoring of cartilage lesions on OCT images. Scoring was performed visually and semi-automatically by five observers, and levels of inter- and intraobserver agreement were calculated. Subsequently, OCT-based scores were compared with ICRS scores based on light microscopy images of the histological sections of matching locations (n = 82). RESULTS: When semi-automated scoring of the OCT images was performed by multiple observers, mean levels of intraobserver and interobserver agreement were higher than those achieved with visual OCT scoring (83% vs. 77% and 74% vs. 33%, respectively). Histology-based scores from matching regions of interest agreed better with visual OCT-based scoring than with semi-automated OCT scoring; however, the accuracy of the software was improved by optimising the threshold combinations used to determine the ICRS score. MAIN LIMITATIONS: Images were obtained from cadavers. CONCLUSIONS: Semi-automated scoring software improved the reproducibility of ICRS scoring of chondral lesions in OCT images and made scoring less observer-dependent. The image analysis and segmentation techniques adopted in this study warrant further optimisation to achieve better accuracy with semi-automated ICRS scoring. In addition, studies on in vivo applications are required.

Estimation of articular cartilage properties using multivariate analysis of optical coherence tomography signal.

OBJECTIVE: The aim was to investigate the applicability of multivariate analysis of optical coherence tomography (OCT) information for determining structural integrity, composition and mechanical properties of articular cartilage. DESIGN: Equine osteochondral samples (N = 65) were imaged with OCT, and their total attenuation and backscattering coefficients (µt and µb) were measured. Subsequently, the Mankin score, optical density (OD) describing the fixed charge density, light absorbance in amide I region (Aamide), collagen orientation, permeability, fibril network modulus (Ef) and non-fibrillar matrix modulus (Em) of the samples were determined. Partial least squares (PLS) regression model was calculated to predict tissue properties from the OCT signals of the samples. RESULTS: Significant correlations between the measured and predicted mean collagen orientation (R(2) = 0.75, P < 0.0001), permeability (R(2) = 0.74, P < 0.0001), mean OD (R(2) = 0.73, P < 0.0001), Mankin scores (R(2) = 0.70, P < 0.0001), Em (R(2) = 0.50, P < 0.0001), Ef (R(2) = 0.42, P < 0.0001), and Aamide (R(2) = 0.43, P < 0.0001) were obtained. Significant correlation was also found between µb and Ef (ρ = 0.280, P = 0.03), but not between µt and any of the determined properties of articular cartilage (P > 0.05). CONCLUSION: Multivariate analysis of OCT signal provided good estimates for tissue structure, composition and mechanical properties. This technique may significantly enhance OCT evaluation of articular cartilage integrity, and could be applied, for example, in delineation of degenerated areas around cartilage injuries during arthroscopic repair surgery.

Arthroscopic optical coherence tomography provides detailed information on articular cartilage lesions in horses.

Arthroscopy enables direct inspection of the articular surface, but provides no information on deeper cartilage layers. Optical coherence tomography (OCT), based on measurement of reflection and backscattering of light, is a diagnostic technique used in cardiovascular surgery and ophthalmology. It provides cross-sectional images at resolutions comparable to that of low-power microscopy. The aim of this study was to determine if OCT is feasible for advanced clinical assessment of lesions in equine articular cartilage during diagnostic arthroscopy. Diagnostic arthroscopy of 36 metacarpophalangeal joints was carried out ex vivo. Of these, 18 joints with varying degrees of cartilage damage were selected, wherein OCT arthroscopy was conducted using an OCT catheter (diameter 0.9 mm) inserted through standard instrument portals. Five sites of interest, occasionally supplemented with other locations where defects were encountered, were arthroscopically graded according to the International Cartilage Repair Society (ICRS) classification system. The same sites were evaluated qualitatively (ICRS classification and morphological description of the lesions) and quantitatively (measurement of cartilage thickness) on OCT images. OCT provided high resolution images of cartilage enabling determination of cartilage thickness. Comparing ICRS grades determined by both arthroscopy and OCT revealed poor agreement. Furthermore, OCT visualised a spectrum of lesions, including cavitation, fibrillation, superficial and deep clefts, erosion, ulceration and fragmentation. In addition, with OCT the arthroscopically inaccessible area between the dorsal MC3 and P1 was reachable in some cases. Arthroscopically-guided OCT provided more detailed and quantitative information on the morphology of articular cartilage lesions than conventional arthroscopy. OCT could therefore improve the diagnostic value of arthroscopy in equine orthopaedic surgery.