Superiority of Multiple-Joint Space Width over Minimum-Joint Space Width Approach in the Machine Learning for Radiographic Severity and Knee Osteoarthritis Progression

Survival analysis on subchondral bone length for total knee replacement

OBJECTIVE

Use subchondral bone length (SBL), a new MRI-derived measure that reflects the extent of cartilage loss and bone flattening, to predict the risk of progression to total knee replacement (TKR).

METHODS

We employed baseline MRI data from the Osteoarthritis Initiative (OAI), focusing on 760 men and 1214 women with bone marrow lesions (BMLs) and joint space narrowing (JSN) scores, to predict the progression to TKR. To minimize bias from analyzing both knees of a participant, only the knee with a higher Kellgren-Lawrence (KL) grade was considered, given its greater potential need for TKR. We utilized the Kaplan-Meier survival curves and Cox proportional hazards models, incorporating raw and normalized values of SBL, JSN, and BML as predictors. The study included subgroup analyses for different demographics and clinical characteristics, using models for raw and normalized SBL (merged, femoral, tibial), BML (merged, femoral, tibial), and JSN (medial and lateral compartments). Model performance was evaluated using the time-dependent area under the curve (AUC), Brier score, and Concordance index to gauge accuracy, calibration, and discriminatory power. Knee joint and region-level analyses were conducted to determine the effectiveness of SBL, JSN, and BML in predicting TKR risk.

RESULTS

The SBL model, incorporating data from both the femur and tibia, demonstrated a predictive capacity for TKR that closely matched the performance of the BML score and the JSN grade. The Concordance index of the SBL model was 0.764, closely mirroring the BML's 0.759 and slightly below JSN's 0.788. The Brier score for the SBL model stood at 0.069, showing comparability with BML's 0.073 and a minor difference from JSN's 0.067. Regarding the AUC, the SBL model achieved 0.803, nearly identical to BML's 0.802 and slightly lower than JSN's 0.827.

CONCLUSION

SBL's capacity to predict the risk of progression to TKR highlights its potential as an effective imaging biomarker for knee osteoarthritis.

Subchondral bone expansion in advanced knee osteoarthritis: Relation with radiographic severity and role in surgical decision-making

Background

Joint space width (JSW) is a traditional imaging marker for knee osteoarthritis (OA) severity, but it lacks sensitivity in advanced cases. We propose tibial subchondral bone area (TSBA), a new CT imaging marker to explore its relationship with OA radiographic severity, and to test its performance for classifying surgical decisions between unicompartmental knee arthroplasty (UKA) and total knee arthroplasty (TKA) compared to JSW.

Methods

We collected clinical, radiograph, and CT data from 182 patients who underwent primary knee arthroplasty (73 UKA, 109 TKA). The radiographic severity was scored using Kellgren-Lawrence (KL) grading system. TSBA and JSW were extracted from 3D CT-reconstruction model. We used independent t-test to investigate the relationship between TSBA and KL grade, and binary logistic regression to identify factors associated with TKA risk. The accuracy of TSBA, JSW and established classification model in differentiating between UKA and TKA was assessed using AUC.

Results

All parameters exhibited inter- and intra-class coefficients greater than 0.966. Patients with KL grade 4 had significantly larger TSBA than those with KL grade 3. TSBA (0.708 of AUC) was superior to minimal/average JSW (0.547/0.554 of AUC) associated with the risk of receiving TKA. Medial TSBA, together with gender and Knee Society Knee Score, emerged as independent classification factors in multivariate analysis. The overall AUC of composite model for surgical decision-making was 0.822.

Conclusion

Tibial subchondral bone area is an independent imaging marker for radiographic severity, and is superior to JSW for surgical decision-making between UKA and TKA in advanced OA patients.

Multi-pose-based convolutional neural network model for diagnosis of patients with central lumbar spinal stenosis

Although the role of plain radiographs in diagnosing lumbar spinal stenosis (LSS) has declined in importance since the advent of magnetic resonance imaging (MRI), diagnostic ability of plain radiographs has improved dramatically when combined with deep learning. Previously, we developed a convolutional neural network (CNN) model using a radiograph for diagnosing LSS. In this study, we aimed to improve and generalize the performance of CNN models and overcome the limitation of the single-pose-based CNN (SP-CNN) model using multi-pose radiographs. Individuals with severe or no LSS, confirmed using MRI, were enrolled. Lateral radiographs of patients in three postures were collected. We developed a multi-pose-based CNN (MP-CNN) model using the encoders of the three SP-CNN model (extension, flexion, and neutral postures). We compared the validation results of the MP-CNN model using four algorithms pretrained with ImageNet. The MP-CNN model underwent additional internal and external validations to measure generalization performance. The ResNet50-based MP-CNN model achieved the largest area under the receiver operating characteristic curve (AUROC) of 91.4% (95% confidence interval [CI] 90.9-91.8%) for internal validation. The AUROC of the MP-CNN model were 91.3% (95% CI 90.7-91.9%) and 79.5% (95% CI 78.2-80.8%) for the extra-internal and external validation, respectively. The MP-CNN based heatmap offered a logical decision-making direction through optimized visualization. This model holds potential as a screening tool for LSS diagnosis, offering an explainable rationale for its prediction.

An accurate method for measuring knee joint space width despite variations in beam projection angles

BACKGROUND

Assessing knee osteoarthritis (OA) severity through joint space width (JSW) measurements can be difficult due to anatomical variations, beam projection angle (BPA) errors, and patient posture during X-rays. Although various methods address these issues, a consensus on the reference point for accurate measurement is lacking. Therefore, establishing a precise evaluation method for JSW is imperative.

METHODS

Simulation on 30 knees with advanced OA to measure the JSW using digital reconstruction radiographs from computed tomography (CT) images was conducted. The distance between the medial femoral condyle and the anterior and posterior borders of the medial tibial plateau (represented by DAB and DPB, respectively) and their average (AVD) were used to evaluate JSW. Discrepancies were analyzed for various BPAs. Additionally, the reliability of measuring JSW using DAB, DPB, and AVD was evaluated in a proof-of-concept study on 100 knees using anteroposterior X-rays at three BPAs (neutral, 5° caudal, and 5° cephalic tilt).

RESULTS

In the simulation study, the AVD method had discrepancies below 1 mm from BPA 0° of 5°, 10° caudal tilt, and 5° cephalic tilt (P = 0.066, P = 0.120, and P < 0.001, respectively). However, the values of DAB and DPB showed significant discrepancies from BPA 0° (all over 1 mm and all P < 0.001) for various BPAs. The AVD measurement demonstrated the least discrepancy in JSW measurements based on BPA variations compared with DAB and DPB methods in the proof-of-concept study.

CONCLUSIONS

A simple method for accurately measuring joint space width, even when X-rays are taken at unintended angles can be applied in clinical practice.

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.

DeepKOA: a deep-learning model for predicting progression in knee osteoarthritis using multimodal magnetic resonance images from the osteoarthritis initiative

Background

No investigations have thoroughly explored the feasibility of combining magnetic resonance (MR) images and deep-learning methods for predicting the progression of knee osteoarthritis (KOA). We thus aimed to develop a potential deep-learning model for predicting OA progression based on MR images for the clinical setting.

Methods

A longitudinal case-control study was performed using data from the Foundation for the National Institutes of Health (FNIH), composed of progressive cases [182 osteoarthritis (OA) knees with both radiographic and pain progression for 24-48 months] and matched controls (182 OA knees not meeting the case definition). DeepKOA was developed through 3-dimensional (3D) DenseNet169 to predict KOA progression over 24-48 months based on sagittal intermediate-weighted turbo-spin echo sequences with fat-suppression (SAG-IW-TSE-FS), sagittal 3D dual-echo steady-state water excitation (SAG-3D-DESS-WE) and its axial and coronal multiplanar reformation, and their combined MR images with patient-level labels at baseline, 12, and 24 months to eventually determine the probability of progression. The classification performance of the DeepKOA was evaluated using 5-fold cross-validation. An X-ray-based model and traditional models that used clinical variables via multilayer perceptron were built. Combined models were also constructed, which integrated clinical variables with DeepKOA. The area under the curve (AUC) was used as the evaluation metric.

Results

The performance of SAG-IW-TSE-FS in predicting OA progression was similar or higher to that of other single and combined sequences. The DeepKOA based on SAG-IW-TSE-FS achieved an AUC of 0.664 (95% CI: 0.585-0.743) at baseline, 0.739 (95% CI: 0.703-0.775) at 12 months, and 0.775 (95% CI: 0.686-0.865) at 24 months. The X-ray-based model achieved an AUC ranging from 0.573 to 0.613 at 3 time points. However, adding clinical variables to DeepKOA did not improve performance (P>0.05). Initial visualizations from gradient-weighted class activation mapping (Grad-CAM) indicated that the frequency with which the patellofemoral joint was highlighted increased as time progressed, which contrasted the trend observed in the tibiofemoral joint. The meniscus, the infrapatellar fat pad, and muscles posterior to the knee were highlighted to varying degrees.

Conclusions

This study initially demonstrated the feasibility of DeepKOA in the prediction of KOA progression and identified the potential responsible structures which may enlighten the future development of more clinically practical methods.

Hybrid Techniques of X-ray Analysis to Predict Knee Osteoarthritis Grades Based on Fusion Features of CNN and Handcrafted

Knee osteoarthritis (KOA) is a chronic disease that impedes movement, especially in the elderly, affecting more than 5% of people worldwide. KOA goes through many stages, from the mild grade that can be treated to the severe grade in which the knee must be replaced. Therefore, early diagnosis of KOA is essential to avoid its development to the advanced stages. X-rays are one of the vital techniques for the early detection of knee infections, which requires highly experienced doctors and radiologists to distinguish Kellgren-Lawrence (KL) grading. Thus, artificial intelligence techniques solve the shortcomings of manual diagnosis. This study developed three methodologies for the X-ray analysis of both the Osteoporosis Initiative (OAI) and Rani Channamma University (RCU) datasets for diagnosing KOA and discrimination between KL grades. In all methodologies, the Principal Component Analysis (PCA) algorithm was applied after the CNN models to delete the unimportant and redundant features and keep the essential features. The first methodology for analyzing x-rays and diagnosing the degree of knee inflammation uses the VGG-19 -FFNN and ResNet-101 -FFNN systems. The second methodology of X-ray analysis and diagnosis of KOA grade by Feed Forward Neural Network (FFNN) is based on the combined features of VGG-19 and ResNet-101 before and after PCA. The third methodology for X-ray analysis and diagnosis of KOA grade by FFNN is based on the fusion features of VGG-19 and handcrafted features, and fusion features of ResNet-101 and handcrafted features. For an OAI dataset with fusion features of VGG-19 and handcrafted features, FFNN obtained an AUC of 99.25%, an accuracy of 99.1%, a sensitivity of 98.81%, a specificity of 100%, and a precision of 98.24%. For the RCU dataset with the fusion features of VGG-19 and the handcrafted features, FFNN obtained an AUC of 99.07%, an accuracy of 98.20%, a sensitivity of 98.16%, a specificity of 99.73%, and a precision of 98.08%.

Editorial to the Special Issue “Human Bodywork: Applications in Health, Disease, and Rehabilitation”

In this research topic, the question concerning how the human body functions through the musculoskeletal system was addressed [...]

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.

Comparison of Radiologic Results after Lateral Meniscal Allograft Transplantation with or without Capsulodesis Using an All-Soft Suture Anchor

Background and Objectives: Studies analyzing magnetic resonance imaging (MRI) after simultaneously performing lateral meniscal allograft transplantation (MAT) and capsulodesis are currently rare. This study aimed to compare the MRI results between the group that performed lateral MAT alone and the group that performed both lateral MAT and capsulodesis simultaneously. Materials and Methods: A total of 55 patients who underwent lateral MAT with a 1-year follow-up MRI were included. The patients were divided into two groups according to the surgical procedure: group I (isolated lateral MAT, n = 26) and group C (combined lateral MAT and capsulodesis, n = 29). Differences between groups were compared regarding subjective knee scores, graft extrusion, graft signal, articular cartilage loss, and joint space width (JSW). Results: The subjective knee scores improved significantly in both groups (all, p < 0.001), and there were no significant differences in these scores between both groups at the 1-year follow-up. Group C showed less coronal graft extrusion at the 1-year follow-up (1.1 ± 1.7 mm vs. 2.4 ± 1.8 mm, p < 0.001). Pathologic coronal graft extrusion (≥3 mm) was found in seven (26.9%) patients in group I and three (10.3%) in group C. Concerning the graft signal, group C showed less grade 3 signal intensity in the posterior root of the graft. There were no significant differences in preoperative and postoperative cartilage status between groups. Regarding JSW, there were no significant differences in postoperative JSW between both groups. However, in group C, JSW significantly increased from 3.9 ± 0.4 mm to 4.5 ± 1.4 mm (p = 0.031). Conclusions: In lateral MAT, capsulodesis (open decortication and suture anchor fixation) could reduce graft extrusion without complications. In the future, large-volume and long-term prospective comparative studies are needed to confirm the clinical effects following capsulodesis.

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.

Quantifying Joint Congruence with an Elastic Foundation

The level of congruence between the articulating surfaces of a diarthrodial joint can vary substantially between individuals. Quantifying joint congruence using the most widespread metric, the 'congruence index', is not straightforward: the areas of the segmented bone that constitute the articular surfaces require accurate identification, their shape must be carefully described with appropriate functions, and the relative orientation of the surfaces measured precisely. In this work, we propose a new method of measuring joint congruence, which does not require these steps. First, a Finite Element (FE) simulation of an elastic layer compressed between each set of segmented bones is performed. These are then interpreted using the elastic foundation model, enabling an equivalent, but simpler, contact geometry to be identified. From this, the equivalent radius (quantification of joint congruence) is found. This defines the radius of a sphere contacting plane (or 'ball on flat') that produces an equivalent contact to that in each joint. The minimal joint space width (in this joint position) can also be estimated from the FE simulations. The new method has been applied to 10 healthy instances of the thumb metacarpophalangeal (MCP) joint. The ten thumb MCPs had similar levels and variability of congruence as the other diarthrodial joints that have been characterised previously. This new methodology enables efficient quantification of joint congruence and minimal joint space width directly from CT or MRI derived bone geometry in any relative orientation. It lends itself to large data sets and coupling with kinematic models.

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.