Predicting knee osteoarthritis severity: comparative modeling based on patient's data and plain X-ray images

Deep learning analysis for rheumatologic imaging: current trends, future directions, and the role of human

Rheumatic diseases, such as rheumatoid arthritis (RA), osteoarthritis (OA), and spondyloarthritis (SpA), present diagnostic and management challenges due to their impact on connective tissues and the musculoskeletal system. Traditional imaging techniques, including plain radiography, ultrasounds, computed tomography, and magnetic resonance imaging (MRI), play a critical role in diagnosing and monitoring these conditions, but face limitations like inter-observer variability and time-consuming assessments. Recently, deep learning (DL), a subset of artificial intelligence, has emerged as a promising tool for enhancing medical imaging analysis. Convolutional neural networks, a DL model type, have shown great potential in medical image classification, segmentation, and anomaly detection, often surpassing human performance in tasks like tumor identification and disease severity grading. In rheumatology, DL models have been applied to plain radiography, ultrasounds, and MRI for assessing joint damage, synovial inflammation, and disease progression in RA, OA, and SpA patients. Despite the promise of DL, challenges such as data bias, limited explainability, and the need for large annotated datasets remain significant barriers to its widespread adoption. Furthermore, human oversight and value judgment are essential for ensuring the ethical use and effective implementation of DL in clinical settings. This review provides a comprehensive overview of DL's applications in rheumatologic imaging and explores its future potential in enhancing diagnosis, treatment decisions, and personalized medicine.

The value of deep learning-based X-ray techniques in detecting and classifying K-L grades of knee osteoarthritis: a systematic review and meta-analysis

OBJECTIVES

Knee osteoarthritis (KOA), a prevalent degenerative joint disease, is primarily diagnosed through X-ray imaging. The Kellgren-Lawrence grading system (K-L) is the gold standard for evaluating KOA severity through X-ray analysis. However, this method is highly subjective and non-quantifiable, limiting its effectiveness in detecting subtle joint changes on X-rays. Recent researchers have been directed towards developing deep-learning (DL) techniques for a more accurate diagnosis of KOA using X-ray images. Despite advancements in these intelligent methods, the debate over their diagnostic sensitivity continues. Hence, we conducted the current meta-analysis.

METHODS

A comprehensive search was conducted in PubMed, Cochrane, Embase, Web of Science, and IEEE up to July 11, 2023. The QUADAS-2 tool was employed to assess the risk of bias in the included studies. Given the multi-classification nature of DL tasks, the sensitivity of DL across different K-L grades was meta-analyzed.

RESULTS

A total of 19 studies were included, encompassing 62,158 images. These images consisted of 22,388 for K-L0, 13,415 for K-L1, 15,597 for K-L2, 7768 for K-L3, and 2990 for K-L4. The meta-analysis demonstrated that the sensitivity of DL was 86.74% for K-L0 (95% CI: 80.01%-92.28%), 64.00% for K-L1 (95% CI: 51.81%-75.35%), 75.03% for K-L2 (95% CI: 66.00%-83.09%), 84.76% for K-L3 (95% CI: 78.34%-90.25%), and 90.32% for K-L4 (95% CI: 85.39%-94.40%).

CONCLUSIONS

The DL multi-classification methods based on X-ray imaging generally demonstrate a favorable sensitivity rate (over 50%) in distinguishing between K-L0-K-L4. Specifically, for K-L4, the sensitivity is highly satisfactory at 90.32%. In contrast, the sensitivity rates for K-L1-2 still need improvement.

CLINICAL RELEVANCE STATEMENT

Deep-learning methods have been useful to some extent in assessing the effectiveness of X-rays for osteoarthritis of the knee. However, this requires further research and reliable data to provide specific recommendations for clinical practice.

KEY POINTS

X-ray deep-learning (DL) methods are debatable for evaluating knee osteoarthritis (KOA) under The Kellgren-Lawrence system (K-L). Multi-classification deep-learning methods are more clinically relevant for assessing K-L grading than dichotomous results. For K-L3 and K-L4, X-ray-based DL has high diagnostic performance; early KOA needs to be further improved.

Artificial Intelligence and the State of the Art of Orthopedic Surgery

Artificial Intelligence (AI) is rapidly transforming healthcare, particularly in orthopedics, by enhancing diagnostic accuracy, surgical planning, and personalized treatment. This review explores current applications of AI in orthopedics, focusing on its contributions to diagnostics and surgical procedures. Key methodologies such as artificial neural networks (ANNs), convolutional neural networks (CNNs), support vector machines (SVMs), and ensemble learning have significantly improved diagnostic precision and patient care. For instance, CNN-based models excel in tasks like fracture detection and osteoarthritis grading, achieving high sensitivity and specificity. In surgical contexts, AI enhances procedures through robotic assistance and optimized preoperative planning, aiding in prosthetic sizing and minimizing complications. Additionally, predictive analytics during postoperative care enable tailored rehabilitation programs that improve recovery times. Despite these advancements, challenges such as data standardization and algorithm transparency hinder widespread adoption. Addressing these issues is crucial for maximizing AI's potential in orthopedic practice. This review emphasizes the synergistic relationship between AI and clinical expertise, highlighting opportunities to enhance diagnostics and streamline surgical procedures, ultimately driving patient-centric care.

XGBoost-SHAP-based interpretable diagnostic framework for knee osteoarthritis: a population-based retrospective cohort study

OBJECTIVE

To use routine demographic and clinical data to develop an interpretable individual-level machine learning (ML) model to diagnose knee osteoarthritis (KOA) and to identify highly ranked features.

METHODS

In this retrospective, population-based cohort study, anonymized questionnaire data was retrieved from the Wu Chuan KOA Study, Inner Mongolia, China. After feature selections, participants were divided in a 7:3 ratio into training and test sets. Class balancing was applied to the training set for data augmentation. Four ML classifiers were compared by cross-validation within the training set and their performance was further analyzed with an unseen test set. Classifications were evaluated using sensitivity, specificity, positive predictive value, negative predictive value, accuracy, area under the curve(AUC), G-means, and F1 scores. The best model was explained using Shapley values to extract highly ranked features.

RESULTS

A total of 1188 participants were investigated in this study, among whom 26.3% were diagnosed with KOA. Comparatively, XGBoost with Boruta exhibited the highest classification performance among the four models, with an AUC of 0.758, G-means of 0.800, and F1 scores of 0.703. The SHAP method reveals the top 17 features of KOA according to the importance ranking, and the average of the experience of joint pain was recognized as the most important features.

CONCLUSIONS

Our study highlights the usefulness of machine learning in unveiling important factors that influence the diagnosis of KOA to guide new prevention strategies. Further work is needed to validate this approach.

A New Sensorized Approach Based on a DeepLabCut Model and IR Thermography for Characterizing the Thermal Profile in Knees During Exercise

The knee is one of the joints most vulnerable to disease and injury, particularly in athletes and older adults. Surface temperature monitoring provides insights into the health of the analysed area, supporting early diagnosis and monitoring of conditions such as osteoarthritis and tendon injuries. This study presents an innovative approach that combines infrared thermography techniques with a Resnet 152 (DeepLabCut based) to detect and monitor temperature variations across specific knee regions during repeated sit-to-stand exercises. Thermal profiles are then analysed in relation to weight distribution data collected using a Wii Balance Board during the exercise. DeepLabCut was used to automate the selection of the region of interest (ROI) for temperature assessments, improving data accuracy compared to traditional time-consuming semi-automatic methods. This integrative approach enables precise and marker-free measurements, offering clinically relevant data that can aid in the diagnosis of knee pathologies, evaluation of the rehabilitation progress, and assessment of treatment effectiveness. The results emphasize the potential of combining thermography with DeepLabCut-driven data analysis to develop accessible, non-invasive tools for joint health monitoring or preventive diagnostics of pathologies.

Generative AI in orthopedics: an explainable deep few-shot image augmentation pipeline for plain knee radiographs and Kellgren-Lawrence grading

OBJECTIVES

Recently, deep learning medical image analysis in orthopedics has become highly active. However, progress has been restricted by the absence of large-scale and standardized ground-truth images. To the best of our knowledge, this study is the first to propose an innovative solution, namely a deep few-shot image augmentation pipeline, that addresses this challenge by synthetically generating knee radiographs for training downstream tasks, with a specific focus on knee osteoarthritis Kellgren-Lawrence (KL) grading.

MATERIALS AND METHODS

This study leverages a deep few-shot image augmentation pipeline to generate synthetic knee radiographs. Despite the limited availability of training samples, we demonstrate the capability of our proposed computational strategy to produce high-fidelity plain knee radiographs and use them to successfully train a KL grade classifier.

RESULTS

Our experimental results showcase the effectiveness of the proposed computational pipeline. The generated synthetic radiographs exhibit remarkable fidelity, evidenced by the achieved average Frechet Inception Distance (FID) score of 26.33 for KL grading and 22.538 for bilateral knee radiographs. For KL grading classification, the classifier achieved a test Cohen's Kappa and accuracy of 0.451 and 0.727, respectively. Our computational strategy also resulted in a publicly and freely available imaging dataset of 86 000 synthetic knee radiographs.

CONCLUSIONS

Our approach demonstrates the capability to produce top-notch synthetic knee radiographs and use them for KL grading classification, even when working with a constrained training dataset. The results obtained emphasize the effectiveness of the pipeline in augmenting datasets for knee osteoarthritis research, opening doors for broader applications in orthopedics, medical image analysis, and AI-powered diagnosis.

Deep learning to combat knee osteoarthritis and severity assessment by using CNN-based classification

BACKGROUND

In today's digital age, various diseases drastically reduce people's quality of life. Arthritis is one amongst the most common and debilitating maladies. Osteoarthritis affects several joints, including the hands, knees, spine, and hips. This study focuses on the medical disorder underlying Knee Osteoarthritis (KOA) which severely impairs people's quality of life. KOA is characterised by restricted mobility, stiffness, and terrible pain and can be caused by a range of factors such as ageing, obesity, and traumas. This degenerative disorder leads to progressive wear and tear of the knee joint.

METHODS

To combat arthritis in the kneecap, this study employs a 12-layer Convolutional Neural Network (CNN) to reach deep learning capabilities. A collection of data from the Osteoarthritis Initiative (OAI) is used to classify KOA. Through the use of medical image processing; the study ascertains whether an individual has this ailment. A sophisticated CNN architecture created especially for binary classification and KOA severity utilising deep learning algorithms is the main component of this work.

RESULTS

The cross-entropy loss function is an important component of the model's laborious design that classifies data into two groups. The remaining section uses the Kellgren-Lawrence (KL) grade to classify the disease's severity. In the binary classification, the proposed algorithm outperforms previous methods with an accuracy rate of 92.3%, and in the multiclassification, its accuracy rate is 78.4% which is superior to the previous findings.

CONCLUSION

Looking ahead, the research broadens the scope of this work by gathering information from various sources and using these methods on a wider range of datasets and situations. The potential for major advancements in the field of osteoarthritis detection and classification is highlighted by this forward-looking approach. Furthermore, this method reduces the intervention of medical practitioners and ultimately results in accurate diagnosis.

CLINICAL TRIAL NUMBER

Not applicable.

Assessing the Value of Imaging Data in Machine Learning Models to Predict Patient-Reported Outcome Measures in Knee Osteoarthritis Patients

Knee osteoarthritis (OA) affects over 650 million patients worldwide. Total knee replacement is aimed at end-stage OA to relieve symptoms of pain, stiffness and reduced mobility. However, the role of imaging modalities in monitoring symptomatic disease progression remains unclear. This study aimed to compare machine learning (ML) models, with and without imaging features, in predicting the two-year Western Ontario and McMaster Universities Arthritis Index (WOMAC) score for knee OA patients. We included 2408 patients from the Osteoarthritis Initiative (OAI) database, with 629 patients from the Multicenter Osteoarthritis Study (MOST) database. The clinical dataset included 18 clinical features, while the imaging dataset contained an additional 10 imaging features. Minimal Clinically Important Difference (MCID) was set to 24, reflecting meaningful physical impairment. Clinical and imaging dataset models produced similar area under curve (AUC) scores, highlighting low differences in performance AUC < 0.025). For both clinical and imaging datasets, Gradient Boosting Machine (GBM) models performed the best in the external validation, with a clinically acceptable AUC of 0.734 (95% CI 0.687-0.781) and 0.747 (95% CI 0.701-0.792), respectively. The five features identified included educational background, family history of osteoarthritis, co-morbidities, use of osteoporosis medications and previous knee procedures. This is the first study to demonstrate that ML models achieve comparable performance with and without imaging features.

A Retrospective Study of Biological Risk Factors Associated with Primary Knee Osteoarthritis and the Development of a Nomogram Model

Aim

A high percentage of the elderly suffer from knee osteoarthritis (KOA), which imposes a certain economic burden on them and on society as a whole. The purpose of this study is to examine the risk of KOA and to develop a KOA nomogram model that can timely intervene in this disease to decrease patient psychological burdens.

Methods

Data was collected from patients with KOA and without KOA at our hospital from February 2021 to February 2023. Initially, a comparison was conducted between the variables, identifying statistical differences between the two groups. Subsequently, the risk of KOA was evaluated using the Least Absolute Shrinkage and Selection Operator method and multivariate logistic regression to determine the most effective predictive index and develop a prediction model. The examination of the disease risk prediction model in KOA includes the corresponding nomogram, which encompasses various potential predictors. The assessment of disease risk entails the application of various metrics, including the consistency index (C index), the area under the curve (AUC) of the receiver operating characteristic curve, the calibration chart, the GiViTi calibration band, and the model for predicting KOA. Furthermore, the potential clinical significance of the model is explored through decision curve analysis (DCA) and clinical influence curve analysis.

Results

The study included a total of 582 patients, consisting of 392 patients with KOA and 190 patients without KOA. The nomogram utilized age, haematocrit, platelet count, apolipoprotein a1, potassium, magnesium, hydroxybutyrate dehydrogenase, creatine kinase, and estimated glomerular filtration rate as predictors. The C index, AUC, calibration plot, Giviti calibration band, DCA and clinical influence KOA indicated the ability of nomogram model to differentiate KOA.

Conclusion

Using nomogram based on disease risk, high-risk KOA can be identified directly without imaging.

Deep learning in rheumatological image interpretation

Artificial intelligence techniques, specifically deep learning, have already affected daily life in a wide range of areas. Likewise, initial applications have been explored in rheumatology. Deep learning might not easily surpass the accuracy of classic techniques when performing classification or regression on low-dimensional numerical data. With images as input, however, deep learning has become so successful that it has already outperformed the majority of conventional image-processing techniques developed during the past 50 years. As with any new imaging technology, rheumatologists and radiologists need to consider adapting their arsenal of diagnostic, prognostic and monitoring tools, and even their clinical role and collaborations. This adaptation requires a basic understanding of the technical background of deep learning, to efficiently utilize its benefits but also to recognize its drawbacks and pitfalls, as blindly relying on deep learning might be at odds with its capabilities. To facilitate such an understanding, it is necessary to provide an overview of deep-learning techniques for automatic image analysis in detecting, quantifying, predicting and monitoring rheumatic diseases, and of currently published deep-learning applications in radiological imaging for rheumatology, with critical assessment of possible limitations, errors and confounders, and conceivable consequences for rheumatologists and radiologists in clinical practice.

A rapid VEGF-gene-sequence photoluminescence detector for osteoarthritis

Osteoarthritis (OA) has become a serious problem to the human society for years due to its high economic burden, disability, pain, and severe impact on the patient's lifestyle. The importance of current clinical imaging modalities in the assessment of the onset and progression of OA is well recognized by clinicians, but these modalities can only detect OA in the II stage with significant structural deterioration and clinical symptoms. Blood vessel formation induced by vascular endothelial growth factor (VEGF) occurs in the early stage and throughout the entire course of OA, enables VEGF relating gene sequence to act as a biomarker in the field of early diagnosis and monitoring of the disease. Here in, a facile rapid detection of VEGF relating ssDNA sequence was developed, in which manganese-based zeolitic imidazolate framework nanoparticles (Mn-ZIF-NPs) were synthesized by a simple coprecipitation strategy, followed by the introduction and surficial absorption of probe ssDNAs and the CRISPR/Cas12a system components. Furthermore, fluorescence experiments demonstrated that the biosensor displayed a low detection limit of 2.49 nM, a good linear response to the target ssDNA ranging from 10 nM to 500 nM, and the ability of distinguishing single nucleotide polymorphism. This finding opens a new window for the feasible and rapid detection of ssDNA molecules for the early diagnose of OA.

Charting Aging Trajectories of Knee Cartilage Thickness for Early Osteoarthritis Risk Prediction: An MRI Study from the Osteoarthritis Initiative Cohort

Knee osteoarthritis (OA), a prevalent joint disease in the U.S., poses challenges in terms of predicting of its early progression. Although high-resolution knee magnetic resonance imaging (MRI) facilitates more precise OA diagnosis, the heterogeneous and multifactorial aspects of OA pathology remain significant obstacles for prognosis. MRI-based scoring systems, while standardizing OA assessment, are both time-consuming and labor-intensive. Current AI technologies facilitate knee OA risk scoring and progression prediction, but these often focus on the symptomatic phase of OA, bypassing initial-stage OA prediction. Moreover, their reliance on complex algorithms can hinder clinical interpretation. To this end, we make this effort to construct a computationally efficient, easily-interpretable, and state-of-the-art approach aiding in the radiographic OA (rOA) auto-classification and prediction of the incidence and progression, by contrasting an individual's cartilage thickness with a similar demographic in the rOA-free cohort. To better visualize, we have developed the toolset for both prediction and local visualization. A movie demonstrating different subtypes of dynamic changes in local centile scores during rOA progression is available at https://tli3.github.io/KneeOA/. Specifically, we constructed age-BMI-dependent reference charts for knee OA cartilage thickness, based on MRI scans from 957 radiographic OA (rOA)-free individuals from the Osteoarthritis Initiative cohort. Then we extracted local and global centiles by contrasting an individual's cartilage thickness to the rOA-free cohort with a similar age and BMI. Using traditional boosting approaches with our centile-based features, we obtain rOA classification of KLG ≤ 1 versus KLG = 2 (AUC = 0.95, F1 = 0.89), KLG ≤ 1 versus KLG ≥ 2 (AUC = 0.90, F1 = 0.82) and prediction of KLG2 progression (AUC = 0.98, F1 = 0.94), rOA incidence (KLG increasing from < 2 to ≥ 2; AUC = 0.81, F1 = 0.69) and rOA initial transition (KLG from 0 to 1; AUC = 0.64, F1 = 0.65) within a future 48-month period. Such performance in classifying KLG ≥ 2 matches that of deep learning methods in recent literature. Furthermore, its clinical interpretation suggests that cartilage changes, such as thickening in lateral femoral and anterior femoral regions and thinning in lateral tibial regions, may serve as indicators for prediction of rOA incidence and early progression. Meanwhile, cartilage thickening in the posterior medial and posterior lateral femoral regions, coupled with a reduction in the central medial femoral region, may signify initial phases of rOA transition.

Recent targets of osteoarthritis research

Osteoarthritis is one of the most common diseases and poses a significant medical burden worldwide. Currently, the diagnosis and treatment of osteoarthritis primarily rely on clinical symptoms and changes observed in radiographs or other image modalities. However, identification based on reliable biomarkers would greatly improve early diagnosis, help with precise monitoring of disease progression, and provide aid for accurate treatment. In recent years, several biomarkers for osteoarthritis have been identified, including image modalities and biochemical biomarkers such as collagen degradation products, pro- or anti-inflammatory cytokines, micro RNAs, long non-coding RNAs, and circular RNAs. These biomarkers offer new insights in the pathogenesis of osteoarthritis and provide potential targets for further research. This article reviews the evolution of osteoarthritis biomarkers from the perspective of pathogenesis and emphasizes the importance of continued research to improve the diagnosis, treatment, and management of osteoarthritis.

Laser therapy versus pulsed electromagnetic field therapy as treatment modalities for early knee osteoarthritis: a randomized controlled trial

BACKGROUND

This randomized controlled trial aimed to compare the effects of pulsed electromagnetic field therapy (PEMFT) and low-level laser therapy (LLLT) on pain and physical function of participants with knee osteoarthritis (KOA).

METHODS

According to the Kellgren-Lawrence classification, participants with grade 2-3 KOA were randomized to receive PEMFT or LLLT for six sessions lasting 15 min/session over a 3-week period. Pain at rest and when walking, standing from a sitting position, and climbing the stairs was assessed using the visual analog scale. Functional level was measured by the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), timed up-and-go test (TUG), and 10-m walk (10 MW) test. Measurements were obtained before and after the interventions. Significance was determined at p ≤ 0.05.

RESULTS

Forty participants were included in the study. Pain and physical function improved significantly (p < 0.0001) in both groups. PEMFT was significantly more effective in reducing pain at rest, when standing from a sitting position, and when climbing the stairs, and in improving both WOMAC scores and TUG results (p ≤ 0.0003). The improvements in pain during the activities and the WOMAC scores reached the minimal clinically important difference. No adverse events occurred.

CONCLUSION

Six sessions of PEMFT and LLLT had immediate positive effects on pain and physical function in individuals with low-grade KOA, with PEMFT resulting in significantly better results.

TRIAL REGISTRATION

ISRCTN registry trial ID: ISRCTN17001174.

Prediction of progression rate and fate of osteoarthritis: Comparison of machine learning algorithms

Appropriate prediction models can assist healthcare systems in delaying or reversing osteoarthritis (OA) progression. We aimed to identify a reliable algorithm for predicting the progression rate and fate of OA based on patient-specific information. From May 2003 to 2019, 83,280 knees were collected. Age, sex, body mass index, bone mineral density, physical demands for occupation, comorbidities, and initial Kellgren-Lawrence (K-L) grade were used as variables for the prediction models. The prediction targets were divided into dichotomous groups for even distribution. We compared the performances of logistic regression (LR), random forest (RF), and extreme gradient boost (XGB) algorithms. Each algorithm had the best precision when the model used all variables. XGB showed the best results in accuracy, recall, F1 score, specificity, and error rates (progression rate/fate of OA: 0.710/0.877, 0.542/0.637, 0.637/0.758, 0.859/0.981, and 0.290/0.123, respectively). The feature importance of RF and XGB had the same order up to the top six for each prediction target. Age and initial K-L grade had the highest feature importance in RF and XGB for the progression rate and fate of OA, respectively. The XGB and RF machine learning algorithms showed better performance than conventional LR in predicting the progression rate and fate of OA. The best performance was obtained when all variables were combined using the XGB algorithm. For each algorithm, the initial K-L grade and physical demand for occupation were the greatest contributors with superior feature importance compared with the others.

Systematic review of artificial intelligence tack in preventive orthopaedics: is the land coming soon?

PURPOSE

This study aims to describe and assess the current stage of the artificial intelligence (AI) technology integration in preventive orthopaedics of the knee and hip joints.

MATERIALS AND METHODS

The study was conducted in strict compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. Literature databases were searched for articles describing the development and validation of AI models aimed at diagnosing knee or hip joint pathologies or predicting their development or course in patients. The quality of the included articles was assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and QUADAS-AI tools.

RESULTS

56 articles were found that meet all the inclusion criteria. We identified two problems that block the full integration of AI into the routine of an orthopaedic physician. The first of them is related to the insufficient amount, variety and quality of data for training, and validation and testing of AI models. The second problem is the rarity of rational evaluation of models, which is why their real quality cannot always be evaluated.

CONCLUSION

The vastness and relevance of the studied topic are beyond doubt. Qualitative and optimally validated models exist in all four scopes considered. Additional optimization and confirmation of the models' quality on various datasets are the last technical stumbling blocks for creating usable software and integrating them into the routine of an orthopaedic physician.

Adversarial Evolving Neural Network for Longitudinal Knee Osteoarthritis Prediction

Knee osteoarthritis (KOA) as a disabling joint disease has doubled in prevalence since the mid-20th century. Early diagnosis for the longitudinal KOA grades has been increasingly important for effective monitoring and intervention. Although recent studies have achieved promising performance for baseline KOA grading, longitudinal KOA grading has been seldom studied and the KOA domain knowledge has not been well explored yet. In this paper, a novel deep learning architecture, namely adversarial evolving neural network (A-ENN), is proposed for longitudinal grading of KOA severity. As the disease progresses from mild to severe level, ENN involves the progression patterns for accurately characterizing the disease by comparing an input image it to the template images of different KL grades using convolution and deconvolution computations. In addition, an adversarial training scheme with a discriminator is developed to obtain the evolution traces. Thus, the evolution traces as fine-grained domain knowledge are further fused with the general convolutional image representations for longitudinal grading. Note that ENN can be applied to other learning tasks together with existing deep architectures, in which the responses characterize progressive representations. Comprehensive experiments on the Osteoarthritis Initiative (OAI) dataset were conducted to evaluate the proposed method. An overall accuracy was achieved as 62.7%, with the baseline, 12-month, 24-month, 36-month, and 48-month accuracy as 64.6%, 63.9%, 63.2%, 61.8% and 60.2%, respectively.

Detection and Classification of Knee Osteoarthritis

Osteoarthritis (OA) affects nearly 240 million people worldwide. Knee OA is the most common type of arthritis, especially in older adults. Physicians measure the severity of knee OA according to the Kellgren and Lawrence (KL) scale through visual inspection of X-ray or MR images. We propose a semi-automatic CADx model based on Deep Siamese convolutional neural networks and a fine-tuned ResNet-34 to simultaneously detect OA lesions in the two knees according to the KL scale. The training was done using a public dataset, whereas the validations were performed with a private dataset. Some problems of the imbalanced dataset were solved using transfer learning. The model results average of the multi-class accuracy is 61%, presenting better performance results for classifying classes KL-0, KL-3, and KL-4 than KL-1 and KL-2. The classification results were compared and validated using the classification of experienced radiologists.

A Simple Nomogram for Predicting Osteoarthritis Severity in Patients with Knee Osteoarthritis

Objective

To explore the influencing factors of knee osteoarthritis (KOA) severity and establish a KOA nomogram model.

Methods

Inpatient data collected in the Department of Joint Surgery, Chengde Medical University Affiliated Hospital from January 2020 to January 2022 were used as the training cohort. Patients with knee osteoarthritis who were admitted to the Third Hospital of Hebei Medical University from February 2022 to May 2022 were taken as the external validation group of the model. In the training group, the least absolute shrinkage and selection operator (LASSO) method was used to screen the factors of KOA severity to determine the best prediction index. Then, after combining the significant factors from the LASSO and multivariate logistic regressions, a prediction model was established. All potential prediction factors were included in the KOA severity prediction model, and the corresponding nomogram was drawn. The consistency index (C-index), area under the receiver operating characteristic (ROC) curve (AUC), GiViTi calibration band, net classification improvement (NRI) index, and integrated discrimination improvement (IDI) index evaluation of a model predicted KOA severity. Decision curve analysis (DCA) and clinical influence curves were used to study the model's potential clinical value. The validation group also used the above evaluation indexes to measure the diagnostic efficiency of the model. Spearman correlation was used to investigate the relationship between nomogram-related markers and osteoarthritis severity.

Results

The total sample included 572 patients with knee osteoarthritis, including 400 patients in the training cohort and 172 patients in the validation cohort. The nomogram's predictive factors were age, pulse, absolute value of lymphocytes, mean corpuscular haemoglobin concentration (MCHC), and blood urea nitrogen (BUN). The C-index and AUC of the model were 0.802. The GiViTi calibration band (P = 0.065), NRI (0.091), and IDI (0.033) showed that the modified model can distinguish between severe KOA and nonsevere KOA. DCA showed that the KOA severity nomogram has clinical application value with threshold probabilities between 0.01 and 0.78. The external verification results also show the stability and diagnosis of the model. Age, pulse, MCHC, and BUN are correlated with osteoarthritis severity.

Conclusions

A nomogram model for predicting KOA severity was established for the first time that can visually identify patients with severe KOA and is novel for indirectly evaluating KOA severity by nonimaging means.

Automated identification of hip arthroplasty implants using artificial intelligence

The purpose of this study was to develop and evaluate the performance of deep learning methods based on convolutional neural networks (CNN) to detect and identify specific hip arthroplasty models. In this study, we propose a novel deep learning-based approach to identify hip arthroplasty implants' design using anterior-posterior images of both the stem and the cup. We harness the pre-trained ResNet50 CNN model and employ transfer learning methods to adapt the model for the implants identification task using a total of 714 radiographs of 4 different hip arthroplasty implant designs. Performance was compared with the operative notes and crosschecked with implant sheets. We also evaluate the difference in performance of models trained with the images of the stem, the cup or both. The training and validation data sets were comprised of 357 stem images and 357 cup radiographs across 313 patients and included 4 hip arthroplasty implants from 4 leading implant manufacturers. After 1000 training epochs the model classified 4 implant models with very high accuracy. Our results showed that jointly using stem images and cup images did not improve the classification accuracy of the CNN model. CNN can accurately distinguish between specific hip arthroplasty designs. This technology could offer a useful adjunct to the surgeon in preoperative identification of the prior implant. Using stem images or cup images to train the CNN can both achieve effective identification accuracy, with the accuracy of the stem images being higher. Using stem images and cup images together is not more effective than using images from only one perspective.

Use of machine learning in osteoarthritis research: a systematic literature review

OBJECTIVE

The aim of this systematic literature review was to provide a comprehensive and exhaustive overview of the use of machine learning (ML) in the clinical care of osteoarthritis (OA).

METHODS

A systematic literature review was performed in July 2021 using MEDLINE PubMed with key words and MeSH terms. For each selected article, the number of patients, ML algorithms used, type of data analysed, validation methods and data availability were collected.

RESULTS

From 1148 screened articles, 46 were selected and analysed; most were published after 2017. Twelve articles were related to diagnosis, 7 to prediction, 4 to phenotyping, 12 to severity and 11 to progression. The number of patients included ranged from 18 to 5749. Overall, 35% of the articles described the use of deep learning And 74% imaging analyses. A total of 85% of the articles involved knee OA and 15% hip OA. No study investigated hand OA. Most of the studies involved the same cohort, with data from the OA initiative described in 46% of the articles and the MOST and Cohort Hip and Cohort Knee cohorts in 11% and 7%. Data and source codes were described as publicly available respectively in 54% and 22% of the articles. External validation was provided in only 7% of the articles.

CONCLUSION

This review proposes an up-to-date overview of ML approaches used in clinical OA research and will help to enhance its application in this field.

Discovering Knee Osteoarthritis Imaging Features for Diagnosis and Prognosis: Review of Manual Imaging Grading and Machine Learning Approaches

Knee osteoarthritis (OA) is a deliberating joint disorder characterized by cartilage loss that can be captured by imaging modalities and translated into imaging features. Observing imaging features is a well-known objective assessment for knee OA disorder. However, the variety of imaging features is rarely discussed. This study reviews knee OA imaging features with respect to different imaging modalities for traditional OA diagnosis and updates recent image-based machine learning approaches for knee OA diagnosis and prognosis. Although most studies recognized X-ray as standard imaging option for knee OA diagnosis, the imaging features are limited to bony changes and less sensitive to short-term OA changes. Researchers have recommended the usage of MRI to study the hidden OA-related radiomic features in soft tissues and bony structures. Furthermore, ultrasound imaging features should be explored to make it more feasible for point-of-care diagnosis. Traditional knee OA diagnosis mainly relies on manual interpretation of medical images based on the Kellgren-Lawrence (KL) grading scheme, but this approach is consistently prone to human resource and time constraints and less effective for OA prevention. Recent studies revealed the capability of machine learning approaches in automating knee OA diagnosis and prognosis, through three major tasks: knee joint localization (detection and segmentation), classification of OA severity, and prediction of disease progression. AI-aided diagnostic models improved the quality of knee OA diagnosis significantly in terms of time taken, reproducibility, and accuracy. Prognostic ability was demonstrated by several prediction models in terms of estimating possible OA onset, OA deterioration, progressive pain, progressive structural change, progressive structural change with pain, and time to total knee replacement (TKR) incidence. Despite research gaps, machine learning techniques still manifest huge potential to work on demanding tasks such as early knee OA detection and estimation of future disease events, as well as fundamental tasks such as discovering the new imaging features and establishment of novel OA status measure. Continuous machine learning model enhancement may favour the discovery of new OA treatment in future.

AI MSK clinical applications: cartilage and osteoarthritis

The advancements of artificial intelligence (AI) for osteoarthritis (OA) applications have been rapid in recent years, particularly innovations of deep learning for image classification, lesion detection, cartilage segmentation, and prediction modeling of future knee OA development. This review article focuses on AI applications in OA research, first describing machine learning (ML) techniques and workflow, followed by how these algorithms are used for OA classification tasks through imaging and non-imaging-based ML models. Deep learning applications for OA research, including analysis of both radiographs for automatic detection of OA severity, and MR images for detection of cartilage/meniscus lesions and cartilage segmentation for automatic T₂ quantification will be described. In addition, information on ML models that identify individuals at high risk of OA development will be provided. The future vision of machine learning applications in imaging of OA and cartilage hinges on implementation of AI for optimizing imaging protocols, quantitative assessment of cartilage, and automated analysis of disease burden yielding a faster and more efficient workflow for a radiologist with a higher level of reproducibility and precision. It may also provide risk assessment tools for individual patients, which is an integral part of precision medicine.

Radiographic vs. MRI vs. arthroscopic assessment and grading of knee osteoarthritis - are we using appropriate imaging?

Purpose

Radiographs and MRI scans are commonly used imaging techniques in the assessment of knee osteoarthritis. However, it currently remains uncertain how good a representation of the actual condition of the knee joint these investigations provide. By comparing them against arthroscopic findings the aim of our study was to conclude how accurate these imaging techniques are at grading knee osteoarthritis.

Methods

This was a retrospective study looking at knee arthroscopies performed at a tertiary centre over a 5 year period. The Outerbridge grade given at arthroscopy was correlated with pre-operative radiograph and MRI scores, so as to assess the reliability of these imaging techniques at predicting the actual severity of knee osteoarthritis seen.

Results

Kellgren-Lawrence (KL) grading of radiographs was moderately correlated with Outerbridge grades from arthroscopy for the medial compartment of the knee (Spearman’s rho (SR) 0.483, p < 0.001), with a milder correlation in the lateral compartment (SR 0.218, p = 0.003). MRI reporting of knee osteoarthritis was moderately correlated with Outerbridge grades in the medial compartment (SR 0.451, p < 0.001), mildly correlated for both the lateral (SR 0.299, p < 0.001) and patellofemoral joint compartments (SR 0.142, p = 0.054). KL and MRI grading was moderately correlated for the medial compartment (SR 0.475, p < 0.001) and mildly correlated for the lateral compartment (SR 0.277, p < 0.001).

Conclusion

The ability of radiographs to represent the actual condition of knee osteoarthritis is underestimated. KL grading especially best represents the disease seen in the medial compartment of the knee joint, with a moderate correlation to Outerbridge scores given on arthroscopic assessment. We suggest that whilst MRI is a useful tool in the investigation of knee symptoms, it is often unnecessarily used in patients with OA, when in fact, radiographs alone would be sufficient.

Evidence level

III

Multicentre Study Using Machine Learning Methods in Clinical Diagnosis of Knee Osteoarthritis

Knee osteoarthritis (OA) is one of the most common musculoskeletal disorders. OA diagnosis is currently conducted by assessing symptoms and evaluating plain radiographs, but this process suffers from the subjectivity of doctors. In this study, we retrospectively compared five commonly used machine learning methods, especially the CNN network, to predict the real-world X-ray imaging data of knee joints from two different hospitals using Kellgren-Lawrence (K-L) grade of knee OA to help doctors choose proper auxiliary tools. Furthermore, we present attention maps of CNN to highlight the radiological features affecting the network decision. Such information makes the decision process transparent for practitioners, which builds better trust towards such automatic methods and, moreover, reduces the workload of clinicians, especially for remote areas without enough medical staff.

A Novel Hybrid Approach Based on Deep CNN Features to Detect Knee Osteoarthritis

In the recent era, various diseases have severely affected the lifestyle of individuals, especially adults. Among these, bone diseases, including Knee Osteoarthritis (KOA), have a great impact on quality of life. KOA is a knee joint problem mainly produced due to decreased Articular Cartilage between femur and tibia bones, producing severe joint pain, effusion, joint movement constraints and gait anomalies. To address these issues, this study presents a novel KOA detection at early stages using deep learning-based feature extraction and classification. Firstly, the input X-ray images are preprocessed, and then the Region of Interest (ROI) is extracted through segmentation. Secondly, features are extracted from preprocessed X-ray images containing knee joint space width using hybrid feature descriptors such as Convolutional Neural Network (CNN) through Local Binary Patterns (LBP) and CNN using Histogram of oriented gradient (HOG). Low-level features are computed by HOG, while texture features are computed employing the LBP descriptor. Lastly, multi-class classifiers, that is, Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN), are used for the classification of KOA according to the Kellgren-Lawrence (KL) system. The Kellgren-Lawrence system consists of Grade I, Grade II, Grade III, and Grade IV. Experimental evaluation is performed on various combinations of the proposed framework. The experimental results show that the HOG features descriptor provides approximately 97% accuracy for the early detection and classification of KOA for all four grades of KL.

Identifying Robust Risk Factors for Knee Osteoarthritis Progression: An Evolutionary Machine Learning Approach

Knee osteoarthritis (KOA) is a multifactorial disease which is responsible for more than 80% of the osteoarthritis disease's total burden. KOA is heterogeneous in terms of rates of progression with several different phenotypes and a large number of risk factors, which often interact with each other. A number of modifiable and non-modifiable systemic and mechanical parameters along with comorbidities as well as pain-related factors contribute to the development of KOA. Although models exist to predict the onset of the disease or discriminate between asymptotic and OA patients, there are just a few studies in the recent literature that focused on the identification of risk factors associated with KOA progression. This paper contributes to the identification of risk factors for KOA progression via a robust feature selection (FS) methodology that overcomes two crucial challenges: (i) the observed high dimensionality and heterogeneity of the available data that are obtained from the Osteoarthritis Initiative (OAI) database and (ii) a severe class imbalance problem posed by the fact that the KOA progressors class is significantly smaller than the non-progressors' class. The proposed feature selection methodology relies on a combination of evolutionary algorithms and machine learning (ML) models, leading to the selection of a relatively small feature subset of 35 risk factors that generalizes well on the whole dataset (mean accuracy of 71.25%). We investigated the effectiveness of the proposed approach in a comparative analysis with well-known FS techniques with respect to metrics related to both prediction accuracy and generalization capability. The impact of the selected risk factors on the prediction output was further investigated using SHapley Additive exPlanations (SHAP). The proposed FS methodology may contribute to the development of new, efficient risk stratification strategies and identification of risk phenotypes of each KOA patient to enable appropriate interventions.

Prediction of Joint Space Narrowing Progression in Knee Osteoarthritis Patients

Osteoarthritis is a joint disease that commonly occurs in the knee (KOA). The continuous increase in medical data regarding KOA has triggered researchers to incorporate artificial intelligence analytics for KOA prognosis or treatment. In this study, two approaches are presented to predict the progression of knee joint space narrowing (JSN) in each knee and in both knees combined. A machine learning approach is proposed with the use of multidisciplinary data from the osteoarthritis initiative database. The proposed methodology employs: (i) A clustering process to identify groups of people with progressing and non-progressing JSN; (ii) a robust feature selection (FS) process consisting of filter, wrapper, and embedded techniques that identifies the most informative risk factors; (iii) a decision making process based on the evaluation and comparison of various classification algorithms towards the selection and development of the final predictive model for JSN; and (iv) post-hoc interpretation of the features' impact on the best performing model. The results showed that bounding the JSN progression of both knees can result to more robust prediction models with a higher accuracy (83.3%) and with fewer risk factors (29) compared to the right knee (77.7%, 88 risk factors) and the left knee (78.3%, 164 risk factors), separately.

Can Additional Patient Information Improve the Diagnostic Performance of Deep Learning for the Interpretation of Knee Osteoarthritis Severity

The study compares the diagnostic performance of deep learning (DL) with that of the former radiologist reading of the Kellgren-Lawrence (KL) grade and evaluates whether additional patient data can improve the diagnostic performance of DL. From March 2003 to February 2017, 3000 patients with 4366 knee AP radiographs were randomly selected. DL was trained using knee images and clinical information in two stages. In the first stage, DL was trained only with images and then in the second stage, it was trained with image data and clinical information. In the test set of image data, the areas under the receiver operating characteristic curve (AUC)s of the DL algorithm in diagnosing KL 0 to KL 4 were 0.91 (95% confidence interval (CI), 0.88-0.95), 0.80 (95% CI, 0.76-0.84), 0.69 (95% CI, 0.64-0.73), 0.86 (95% CI, 0.83-0.89), and 0.96 (95% CI, 0.94-0.98), respectively. In the test set with image data and additional patient information, the AUCs of the DL algorithm in diagnosing KL 0 to KL 4 were 0.97 (95% confidence interval (CI), 0.71-0.74), 0.85 (95% CI, 0.80-0.86), 0.75 (95% CI, 0.66-0.73), 0.86 (95% CI, 0.79-0.85), and 0.95 (95% CI, 0.91-0.97), respectively. The diagnostic performance of image data with additional patient information showed a statistically significantly higher AUC than image data alone in diagnosing KL 0, 1, and 2 (p-values were 0.008, 0.020, and 0.027, respectively).The diagnostic performance of DL was comparable to that of the former radiologist reading of the knee osteoarthritis KL grade. Additional patient information improved DL diagnosis in interpreting early knee osteoarthritis.

Identification of Risk Factors and Machine Learning-Based Prediction Models for Knee Osteoarthritis Patients

Knee Osteoarthritis (KOA) is a multifactorial disease that causes low quality of life, poor psychology and resignation from life. Furthermore, KOA is a big data problem in terms of data complexity, heterogeneity and size as it has been commonly considered in the literature with most of the reported studies being limited in the amount of information they can adequately process. The aim of this paper is: (i) To provide a robust feature selection (FS) approach that could identify important risk factors which contribute to the prediction of KOA and (ii) to develop machine learning (ML) prediction models for KOA. The current study considers multidisciplinary data from the osteoarthritis initiative (OAI) database, the available features of which come from heterogeneous sources such as questionnaire data, physical activity indexes, self-reported data about joint symptoms, disability and function as well as general health and physical exams’ data. The novelty of the proposed FS methodology lies on the combination of different well-known approaches including filter, wrapper and embedded techniques, whereas feature ranking is decided on the basis of a majority vote scheme to avoid bias. The validation of the selected factors was performed in data subgroups employing seven well-known classifiers in five different approaches. A 74.07% classification accuracy was achieved by SVM on the group of the first fifty-five selected risk factors. The effectiveness of the proposed approach was evaluated in a comparative analysis with respect to classification errors and confusion matrices to confirm its clinical relevance. The results are the basis for the development of reliable tools for the prediction of KOA progression.

Toward automatic quantification of knee osteoarthritis severity using improved Faster R-CNN

PURPOSE

Knee osteoarthritis (OA) is a common disease that impairs knee function and causes pain. Radiologists usually review knee X-ray images and grade the severity of the impairments according to the Kellgren-Lawrence grading scheme. However, this approach becomes inefficient in hospitals with high throughput as it is time-consuming, tedious and also subjective. This paper introduces a model for automatic diagnosis of knee OA based on an end-to-end deep learning method.

METHOD

In order to process the input images with location and classification simultaneously, we use Faster R-CNN as baseline, which consists of region proposal network (RPN) and Fast R-CNN. The RPN is trained to generate region proposals, which contain knee joint and then be used by Fast R-CNN for classification. Due to the localized classification via CNNs, the useless information in X-ray images can be filtered and we can extract clinically relevant features. For the further improvement in the model's performance, we use a novel loss function whose weighting scheme allows us to address the class imbalance. Besides, larger anchors are used to overcome the problem that anchors don't match the object when increasing the input size of X-ray images.

RESULT

The performance of the proposed model is thoroughly assessed using various measures. The results show that our adjusted model outperforms the Faster R-CNN, achieving a mean average precision nearly 0.82 with a sensitivity above 78% and a specificity above 94%. It takes 0.33 s to test each image, which achieves a better trade-off between accuracy and speed.

CONCLUSION

The proposed end-to-end fully automatic model which is computationally efficient has the potential to achieve the real automatic diagnosis of knee OA and be used as computer-aided diagnosis tools in clinical applications.