Machine Learning Classification of Articular Cartilage Integrity Using Near Infrared Spectroscopy

Classification of osteoarthritic and healthy cartilage using deep learning with Raman spectra

Raman spectroscopy is a rapid method for analysing the molecular composition of biological material. However, noise contamination in the spectral data necessitates careful pre-processing prior to analysis. Here we propose an end-to-end Convolutional Neural Network to automatically learn an optimal combination of pre-processing strategies, for the classification of Raman spectra of superficial and deep layers of cartilage harvested from 45 Osteoarthritis and 19 Osteoporosis (Healthy controls) patients. Using 6-fold cross-validation, the Multi-Convolutional Neural Network achieves comparable or improved classification accuracy against the best-performing Convolutional Neural Network applied to either the raw or pre-processed spectra. We utilised Integrated Gradients to identify the contributing features (Raman signatures) in the network decision process, showing they are biologically relevant. Using these features, we compared Artificial Neural Networks, Decision Trees and Support Vector Machines for the feature selection task. Results show that training on fewer than 3 and 300 features, respectively, for the disease classification and layer assignment task provide performance comparable to the best-performing CNN-based network applied to the full dataset. Our approach, incorporating multi-channel input and Integrated Gradients, can potentially facilitate the clinical translation of Raman spectroscopy-based diagnosis without the need for laborious manual pre-processing and feature selection.

Holistic vibrational spectromics assessment of human cartilage for osteoarthritis diagnosis

Osteoarthritis (OA) is the most common degenerative joint disease, presented as wearing down of articular cartilage and resulting in pain and limited mobility for 1 in 10 adults in the UK [Osteoarthr. Cartil.28(6), 792 (2020)10.1016/j.joca.2020.03.004]. There is an unmet need for patient friendly paradigms for clinical assessment that do not use ionizing radiation (CT), exogenous contrast enhancing dyes (MRI), and biopsy. Hence, techniques that use non-destructive, near- and shortwave infrared light (NIR, SWIR) may be ideal for providing label-free, deep tissue interrogation. This study demonstrates multimodal "spectromics", low-level abstraction data fusion of non-destructive NIR Raman scattering spectroscopy and NIR-SWIR absorption spectroscopy, providing an enhanced, interpretable "fingerprint" for diagnosis of OA in human cartilage. This is proposed as method level innovation applicable to both arthro- or endoscopic (minimally invasive) or potential exoscopic (non-invasive) optical approaches. Samples were excised from femoral heads post hip arthroplasty from OA patients (n = 13) and age-matched control (osteoporosis) patients (n = 14). Under multivariate statistical analysis and supervised machine learning, tissue was classified to high precision: 100% segregation of tissue classes (using 10 principal components), and a classification accuracy of 95% (control) and 80% (OA), using the combined vibrational data. There was a marked performance improvement (5 to 6-fold for multivariate analysis) using the spectromics fingerprint compared to results obtained from solely Raman or NIR-SWIR data. Furthermore, clinically relevant tissue components were identified through discriminatory spectral features - spectromics biomarkers - allowing interpretable feedback from the enhanced fingerprint. In summary, spectromics provides comprehensive information for early OA detection and disease stratification, imperative for effective intervention in treating the degenerative onset disease for an aging demographic. This novel and elegant approach for data fusion is compatible with various NIR-SWIR optical devices that will allow deep non-destructive penetration.

Spatial analysis of the osteoarthritis microenvironment: techniques, insights, and applications

Osteoarthritis (OA) is a debilitating degenerative disease affecting multiple joint tissues, including cartilage, bone, synovium, and adipose tissues. OA presents diverse clinical phenotypes and distinct molecular endotypes, including inflammatory, metabolic, mechanical, genetic, and synovial variants. Consequently, innovative technologies are needed to support the development of effective diagnostic and precision therapeutic approaches. Traditional analysis of bulk OA tissue extracts has limitations due to technical constraints, causing challenges in the differentiation between various physiological and pathological phenotypes in joint tissues. This issue has led to standardization difficulties and hindered the success of clinical trials. Gaining insights into the spatial variations of the cellular and molecular structures in OA tissues, encompassing DNA, RNA, metabolites, and proteins, as well as their chemical properties, elemental composition, and mechanical attributes, can contribute to a more comprehensive understanding of the disease subtypes. Spatially resolved biology enables biologists to investigate cells within the context of their tissue microenvironment, providing a more holistic view of cellular function. Recent advances in innovative spatial biology techniques now allow intact tissue sections to be examined using various -omics lenses, such as genomics, transcriptomics, proteomics, and metabolomics, with spatial data. This fusion of approaches provides researchers with critical insights into the molecular composition and functions of the cells and tissues at precise spatial coordinates. Furthermore, advanced imaging techniques, including high-resolution microscopy, hyperspectral imaging, and mass spectrometry imaging, enable the visualization and analysis of the spatial distribution of biomolecules, cells, and tissues. Linking these molecular imaging outputs to conventional tissue histology can facilitate a more comprehensive characterization of disease phenotypes. This review summarizes the recent advancements in the molecular imaging modalities and methodologies for in-depth spatial analysis. It explores their applications, challenges, and potential opportunities in the field of OA. Additionally, this review provides a perspective on the potential research directions for these contemporary approaches that can meet the requirements of clinical diagnoses and the establishment of therapeutic targets for OA.

Raman Spectroscopy and Machine Learning Enables Estimation of Articular Cartilage Structural, Compositional, and Functional Properties

OBJECTIVE

To differentiate healthy from artificially degraded articular cartilage and estimate its structural, compositional, and functional properties using Raman spectroscopy (RS).

DESIGN

Visually normal bovine patellae (n = 12) were used in this study. Osteochondral plugs (n = 60) were prepared and artificially degraded either enzymatically (via Collagenase D or Trypsin) or mechanically (via impact loading or surface abrasion) to induce mild to severe cartilage damage; additionally, control plugs were prepared (n = 12). Raman spectra were acquired from the samples before and after artificial degradation. Afterwards, reference biomechanical properties, proteoglycan (PG) content, collagen orientation, and zonal (%) thickness of the samples were measured. Machine learning models (classifiers and regressors) were then developed to discriminate healthy from degraded cartilage based on their Raman spectra and to predict the aforementioned reference properties.

RESULTS

The classifiers accurately categorized healthy and degraded samples (accuracy = 86%), and successfully discerned moderate from severely degraded samples (accuracy = 90%). On the other hand, the regression models estimated cartilage biomechanical properties with reasonable error (≤ 24%), with the lowest error observed in the prediction of instantaneous modulus (12%). With zonal properties, the lowest prediction errors were observed in the deep zone, i.e., PG content (14%), collagen orientation (29%), and zonal thickness (9%).

CONCLUSION

RS is capable of discriminating between healthy and damaged cartilage, and can estimate tissue properties with reasonable errors. These findings demonstrate the clinical potential of RS.

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

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.

Non-invasive detection and differentiation of apoptotic and necroptotic cell death in vitro

Cell death plays an important role in the development of multicellular organisms and the maintenance of adult homeostasis. However, traditional methods of cell death detection can damage cells and tissues. Here, we report the use of near-infrared (NIR) spectroscopy for non-invasively distinguishing between cell death types. We found a difference between normal, apoptotic, and necroptotic mouse dermal fibroblast cells in the wavelength range of 1100-1700 nm. In particular, the differences in scattering of NIR light between cells at different states are enough to be distinguished. This feature was exploited by measuring the attenuation coefficient (δμ), which specifies the ease at which light can pass through a substance. The results showed that δμ can be used to distinguish between different types of cell death. Therefore, this study proposes a new, non-invasive, and fast method to differentiate cell death types without the additional fluorescent labeling.

Near-infrared spectroscopy for structural bone assessment

Aims

Disorders of bone integrity carry a high global disease burden, frequently requiring intervention, but there is a paucity of methods capable of noninvasive real-time assessment. Here we show that miniaturized handheld near-infrared spectroscopy (NIRS) scans, operated via a smartphone, can assess structural human bone properties in under three seconds.

Methods

A hand-held NIR spectrometer was used to scan bone samples from 20 patients and predict: bone volume fraction (BV/TV); and trabecular (Tb) and cortical (Ct) thickness (Th), porosity (Po), and spacing (Sp).

Results

NIRS scans on both the inner (trabecular) surface or outer (cortical) surface accurately identified variations in bone collagen, water, mineral, and fat content, which then accurately predicted bone volume fraction (BV/TV, inner R² = 0.91, outer R² = 0.83), thickness (Tb.Th, inner R² = 0.9, outer R² = 0.79), and cortical thickness (Ct.Th, inner and outer both R² = 0.90). NIRS scans also had 100% classification accuracy in grading the quartile of bone thickness and quality.

Conclusion

We believe this is a fundamental step forward in creating an instrument capable of intraoperative real-time use.

Cite this article: Bone Jt Open 2023;4(4):250–261.

Assessment of Ligament Viscoelastic Properties Using Raman Spectroscopy

Injuries to the ligaments of the knee commonly impact vulnerable and physically active individuals. These injuries can lead to the development of degenerative diseases such as post-traumatic osteoarthritis (PTOA). Non-invasive optical modalities, such as infrared and Raman spectroscopy, provide means for quantitative evaluation of knee joint tissues and have been proposed as potential quantitative diagnostic tools for arthroscopy. In this study, we evaluate Raman spectroscopy as a viable tool for estimating functional properties of collateral ligaments. Artificial trauma was induced by anterior cruciate ligament transection (ACLT) in the left or right knee joint of skeletally mature New Zealand rabbits. The corresponding contralateral (CL) samples were extracted from healthy unoperated joints along with a separate group of control (CNTRL) animals. The rabbits were sacrificed at 8 weeks after ACLT. The ligaments were then harvested and measured using Raman spectroscopy. A uniaxial tensile stress-relaxation testing protocol was adopted for determining several biomechanical properties of the samples. Partial least squares (PLS) regression models were then employed to correlate the spectral data with the biomechanical properties. Results show that the capacity of Raman spectroscopy for estimating the biomechanical properties of the ligament samples varies depending on the target property, with prediction error ranging from 15.78% for tissue cross-sectional area to 30.39% for stiffness. The hysteresis under cyclic loading at 2 Hz (RMSE = 6.22%, Normalized RMSE = 22.24%) can be accurately estimated from the Raman data which describes the viscous damping properties of the tissue. We conclude that Raman spectroscopy has the potential for non-destructively estimating ligament biomechanical properties in health and disease, thus enhancing the diagnostic value of optical arthroscopic evaluations of ligament integrity.

Injectable hydrogels for articular cartilage and nucleus pulposus repair: Status quo and prospects

Osteoarthritis (OA) and chronic low back pain due to degenerative (intervertebral) disc disease (DDD) are two of the major causes of disabilities worldwide, affecting hundreds of millions of people and leading to a high socioeconomic burden. Although OA occurs in synovial joints and DDD occurs in cartilaginous joints, the similarities are striking, with both joints showing commonalities in the nature of the tissues and in the degenerative processes during disease. Consequently, repair strategies for articular cartilage (AC) and nucleus pulposus (NP), the core of the intervertebral disc, in the context of OA and DDD share common aspects. One of such tissue engineering approaches is the use of injectable hydrogels for AC and NP repair. In this review, the state-of-the-art and recent developments in injectable hydrogels for repairing, restoring, and regenerating AC tissue suffering from OA and NP tissue in DDD are summarized focusing on cell-free approaches. The various biomaterial strategies exploited for repair of both tissues are compared, and the synergies that could be gained by translating experiences from one tissue to the other are identified.

Articular cartilage optical properties in the near-infrared (NIR) spectral range vary with depth and tissue integrity

Optical properties of biological tissues in the NIR spectral range have demonstrated significant potential for in vivo diagnostic applications and are critical parameters for modelling light interaction in biological tissues. This study aims to investigate the optical properties of articular cartilage as a function of tissue depth and integrity. The results suggest consistent wavelength-dependent variation in optical properties between cartilage depth-wise zones, as well as between healthy and degenerated tissue. Also, statistically significant differences (p<0.05) in both optical properties were observed between the different cartilage depth-wise zones and as a result of tissue degeneration. When taken into account, the outcome of this study could enable accurate modelling of light interaction in cartilage matrix and could provide useful diagnostic information on cartilage integrity.

Vibrational Spectroscopy in Assessment of Early Osteoarthritis-A Narrative Review

Osteoarthritis (OA) is a degenerative disease, and there is currently no effective medicine to cure it. Early prevention and treatment can effectively reduce the pain of OA patients and save costs. Therefore, it is necessary to diagnose OA at an early stage. There are various diagnostic methods for OA, but the methods applied to early diagnosis are limited. Ordinary optical diagnosis is confined to the surface, while laboratory tests, such as rheumatoid factor inspection and physical arthritis checks, are too trivial or time-consuming. Evidently, there is an urgent need to develop a rapid nondestructive detection method for the early diagnosis of OA. Vibrational spectroscopy is a rapid and nondestructive technique that has attracted much attention. In this review, near-infrared (NIR), infrared, (IR) and Raman spectroscopy were introduced to show their potential in early OA diagnosis. The basic principles were discussed first, and then the research progress to date was discussed, as well as its limitations and the direction of development. Finally, all methods were compared, and vibrational spectroscopy was demonstrated that it could be used as a promising tool for early OA diagnosis. This review provides theoretical support for the application and development of vibrational spectroscopy technology in OA diagnosis, providing a new strategy for the nondestructive and rapid diagnosis of arthritis and promoting the development and clinical application of a component-based molecular spectrum detection technology.

Applications of Vibrational Spectroscopy for Analysis of Connective Tissues

Advances in vibrational spectroscopy have propelled new insights into the molecular composition and structure of biological tissues. In this review, we discuss common modalities and techniques of vibrational spectroscopy, and present key examples to illustrate how they have been applied to enrich the assessment of connective tissues. In particular, we focus on applications of Fourier transform infrared (FTIR), near infrared (NIR) and Raman spectroscopy to assess cartilage and bone properties. We present strengths and limitations of each approach and discuss how the combination of spectrometers with microscopes (hyperspectral imaging) and fiber optic probes have greatly advanced their biomedical applications. We show how these modalities may be used to evaluate virtually any type of sample (ex vivo, in situ or in vivo) and how "spectral fingerprints" can be interpreted to quantify outcomes related to tissue composition and quality. We highlight the unparalleled advantage of vibrational spectroscopy as a label-free and often nondestructive approach to assess properties of the extracellular matrix (ECM) associated with normal, developing, aging, pathological and treated tissues. We believe this review will assist readers not only in better understanding applications of FTIR, NIR and Raman spectroscopy, but also in implementing these approaches for their own research projects.

Characterization of connective tissues using near-infrared spectroscopy and imaging

Near-infrared (NIR) spectroscopy is a powerful analytical method for rapid, non-destructive and label-free assessment of biological materials. Compared to mid-infrared spectroscopy, NIR spectroscopy excels in penetration depth, allowing intact biological tissue assessment, albeit at the cost of reduced molecular specificity. Furthermore, it is relatively safe compared to Raman spectroscopy, with no risk of laser-induced photothermal damage. A typical NIR spectroscopy workflow for biological tissue characterization involves sample preparation, spectral acquisition, pre-processing and analysis. The resulting spectrum embeds intrinsic information on the tissue's biomolecular, structural and functional properties. Here we demonstrate the analytical power of NIR spectroscopy for exploratory and diagnostic applications by providing instructions for acquiring NIR spectra, maps and images in biological tissues. By adapting and extending this protocol from the demonstrated application in connective tissues to other biological tissues, we expect that a typical NIR spectroscopic study can be performed by a non-specialist user to characterize biological tissues in basic research or clinical settings. We also describe how to use this protocol for exploratory study on connective tissues, including differentiating among ligament types, non-destructively monitoring changes in matrix formation during engineered cartilage development, mapping articular cartilage proteoglycan content across bovine patella and spectral imaging across the depth-wise zones of articular cartilage and subchondral bone. Depending on acquisition mode and experiment objectives, a typical exploratory study can be completed within 6 h, including sample preparation and data analysis.

Early Diagnosis of Type 2 Diabetes Based on Near-Infrared Spectroscopy Combined With Machine Learning and Aquaphotomics

Early diagnosis is important to reduce the incidence and mortality rate of diabetes. The feasibility of early diagnosis of diabetes was studied via near-infrared spectra (NIRS) combined with a support vector machine (SVM) and aquaphotomics. Firstly, the NIRS of entire blood samples from the population of healthy, pre-diabetic, and diabetic patients were obtained. The spectral data of the entire spectra in the visible and near-infrared region (400–2,500 nm) were used as the research object of the qualitative analysis. Secondly, several preprocessing steps including multiple scattering correction, variable standardization, and first derivative and second derivative steps were performed and the best pretreatment method was selected. Finally, for the early diagnosis of diabetes, models were established using SVM. The first overtone of water (1,300–1,600 nm) was used as the research object for an aquaphotomics model, and the aquagram of the healthy group, pre-diabetes, and diabetes groups were drawn using 12 water absorption patterns for the early diagnosis of diabetes. The results of SVM showed that the highest accuracy was 97.22% and the specificity and sensitivity were 95.65 and 100%, respectively when the pretreatment method of the first derivative was used, and the best model parameters were c = 18.76 and g = 0.008583.The results of the aquaphotomics model showed clear differences in the 1,400–1,500 nm region, and the number of hydrogen bonds in water species (1,408, 1,416, 1,462, and 1,522 nm) was evidently correlated with the occurrence and development of diabetes. The number of hydrogen bonds was the smallest in the healthy group and the largest in the diabetes group. The suggested reason is that the water matrix of blood changes with the worsening of blood glucose metabolic dysfunction. The number of hydrogen bonds could be used as biomarkers for the early diagnosis of diabetes. The result show that it is effective and feasible to establish an accurate and rapid early diagnosis model of diabetes via NIRS combined with SVM and aquaphotomics.

Classification, Categorization, and Algorithms for Articular Cartilage Defects

There is a critical unmet need in the clinical implementation of valid preventative and therapeutic strategies for patients with articular cartilage pathology based on the significant gap in understanding of the relationships between diagnostic data, disease progression, patient-related variables, and symptoms. In this article, the current state of classification and categorization for articular cartilage pathology is discussed with particular focus on machine learning methods and the authors propose a bedside-bench-bedside approach with highly quantitative techniques as a solution to these hurdles. Leveraging computational learning with available data toward articular cartilage pathology patient phenotyping holds promise for clinical research and will likely be an important tool to identify translational solutions into evidence-based clinical applications to benefit patients. Recommendations for successful implementation of these approaches include using standardized definitions of articular cartilage, to include characterization of depth, size, location, and number; using measurements that minimize subjectivity or validated patient-reported outcome measures; considering not just the articular cartilage pathology but the whole joint, and the patient perception and perspective. Application of this approach through a multistep process by a multidisciplinary team of clinicians and scientists holds promise for validating disease mechanism-based phenotypes toward clinically relevant understanding of articular cartilage pathology for evidence-based application to orthopaedic practice.

Tissue optical properties combined with machine learning enables estimation of articular cartilage composition and functional integrity

Absorption and reduced scattering coefficients ( μ a , μ s ' ) of biological tissues have shown significant potential in biomedical applications. Thus, they are effective parameters for the characterization of tissue integrity and provide vital information on the health of biological tissues. This study investigates the potential of optical properties ( μ a , μ s ' ) for estimating articular cartilage composition and biomechanical properties using multivariate and machine learning techniques. The results suggest that μ_a could optimally estimate cartilage proteoglycan content in the superficial zone, in addition to its equilibrium modulus. While μ s ' could effectively estimate the proteoglycan content of the middle and deep zones in addition to the instantaneous and dynamic moduli of articular cartilage.