Gait data from 51 healthy participants with motion capture, inertial measurement units, and computer vision.

We present a dataset comprising motion capture, inertial measurement unit data, and sagittal-plane video data from walking at three different instructed speeds (slow, comfortable, fast). The dataset contains 51 healthy participants with approximately 60 walking trials from each participant. Each walking trial contains data from motion capture, inertial measurement units, and computer vision. Motion capture data comprises ground reaction forces and moments from floor-embedded force plates and the 3D trajectories of subject-worn motion capture markers. Inertial measurement unit data comprises 3D accelerometer readings and 3D orientations from the lower limbs and pelvis. Computer vision data comprises 2D keypoint trajectories detected using the OpenPose human pose estimation algorithm from sagittal-plane video of the walking trial. Additionally, the dataset contains participant demographic and anthropometric information such as mass, height, sex, age, lower limb dimensions, and knee intercondylar distance measured from magnetic resonance images. The dataset can be used in musculoskeletal modelling and simulation to calculate kinematics and kinetics of motion and to compare data between motion capture, inertial measurement, and video capture.

Two-Stage Classification of Future Knee Osteoarthritis Severity After 8 Years Using MRI: Data from the Osteoarthritis Initiative.

Currently, there are no methods or tools available in clinical practice for classifying future knee osteoarthritis (KOA). In this study, we aimed to fill this gap by classifying future KOA into three severity grades: KL01 (healthy), KL2 (moderate), and KL34 (severe) based on the Kellgren-Lawrance scale. Due to the complex nature of multiclass classification, we used a two-stage method, which separates the classification task into two binary classifications (KL01 vs. KL234 in the first stage and KL2 vs. KL34 in the second stage). Our machine learning (ML) model used two Balanced Random Forest algorithms and was trained with gender, age, height, weight, and quantitative knee morphology obtained from magnetic resonance imaging. Our training dataset comprised longitudinal 8-year follow-up data of 1213 knees from the Osteoarthritis Initiative. Through extensive experimentation with various feature combinations, we identified KL baseline and weight as the most essential features, while gender surprisingly proved to be one of the least influential feature. Our best classification model generated a weighted F1 score of 79.0% and a balanced accuracy of 65.9%. The area under the receiver operating characteristic curve was 83.0% for healthy (KL01) versus moderate (KL2) or severe (KL34) KOA patients and 86.6% for moderate (KL2) versus severe (KL34) KOA patients. We found a statistically significant difference in performance between our two-stage classification model and the traditional single-stage classification model. These findings demonstrate the encouraging results of our two-stage classification model for multiclass KOA severity classification, suggesting its potential application in clinical settings in future.

X-ray with finite element analysis is a viable alternative for MRI to predict knee osteoarthritis: Data from the Osteoarthritis Initiative.

Magnetic resonance imaging (MRI) offers superior soft tissue contrast compared to clinical X-ray imaging methods, while also providing accurate three-dimensional (3D) geometries, it could be reasoned to be the best imaging modality to create 3D finite element (FE) geometries of the knee joint. However, MRI may not necessarily be superior for making tissue-level FE simulations of internal stress distributions within knee joint, which can be utilized to calculate subject-specific risk for the onset and development of knee osteoarthritis (KOA). Specifically, MRI does not provide any information about tissue stiffness, as the imaging is usually performed with the patient lying on their back. In contrast, native X-rays taken while the patient is standing indirectly reveal information of the overall health of the knee that is not seen in MRI. To determine the feasibility of X-ray workflow to generate FE models based on the baseline information (clinical image data and subject characteristics), we compared MRI and X-ray-based simulations of volumetric cartilage degenerations (N = 1213) against 8-year follow-up data. The results suggest that X-ray-based predictions of KOA are at least as good as MRI-based predictions for subjects with no previous knee injuries. This finding may have important implications for preventive care, as X-ray imaging is much more accessible than MRI.

Atlas-based finite element analyses with simpler constitutive models predict personalized progression of knee osteoarthritis: data from the osteoarthritis initiative.

New technologies are required to support a radical shift towards preventive healthcare. Here we focus on evaluating the possibility of finite element (FE) analysis-aided prevention of knee osteoarthritis (OA), a disease that affects 100 million citizens in the US and EU and this number is estimated to increase drastically. Current clinical methods to diagnose or predict joint health status relies on symptoms and tissue failures obtained from clinical imaging. In a joint with no detectable injuries, the diagnosis of the future health of the knee can be assumed to be very subjective. Quantitative approaches are therefore needed to assess the personalized risk for the onset and development of knee OA. FE analysis utilizing an atlas-based modeling approach has shown a preliminary capability for simulating subject-specific cartilage mechanical responses. However, it has been verified with a very limited subject number. Thus, the aim of this study is to verify the real capability of the atlas-based approach to simulate cartilage degeneration utilizing different material descriptions for cartilage. A fibril reinforced poroviscoelastic (FRPVE) material formulation was considered as state-of-the-art material behavior, since it has been preliminary validated against real clinical follow-up data. Simulated mechanical tissue responses and predicted cartilage degenerations within knee joint with FRPVE material were compared against simpler constitutive models for cartilage. The capability of the atlas-based modeling to offer a feasible approach with quantitative evaluation for the risk for the OA development (healthy vs osteoarthritic knee, p < 0.01, AUC ~ 0.7) was verified with 214 knees. Furthermore, the results suggest that accuracy for simulation of cartilage degeneration with simpler material models is similar to models using FPRVE materials if the material parameters are chosen properly.

Utilizing Atlas-Based Modeling to Predict Knee Joint Cartilage Degeneration: Data from the Osteoarthritis Initiative.

Currently, there are no clinically available tools or applications which could predict osteoarthritis development. Some computational models have been presented to simulate cartilage degeneration, but they are not clinically feasible due to time required to build subject-specific knee models. Therefore, the objective of this study was to develop a template-based modeling method for rapid prediction of knee joint cartilage degeneration. Knee joint models for 21 subjects were constructed with two different template approaches (multiple templates and one template) based on the MRI data. Geometries were also generated by manual segmentation. Evaluated volumes of cartilage degeneration for each subject, as assessed with the degeneration algorithm, were compared with experimentally observed 4 year follow up Kellgren-Lawrence (KL) grades. Furthermore, the effect of meniscus was tested by generating models with subject-specific meniscal supporting forces and those with the average meniscal supporting force from all models. All tested models were able to predict most severe cartilage degeneration to those subjects who had the highest KL grade after 4 year follow up. Surprisingly, in terms of statistical significance, the best result was obtained with one template approach and average meniscal support. This model was fully able to categorize all subjects to their experimentally defined groups (KL0, KL2 and KL3) based on the 4 year follow-up data. The results suggest that a template- or population-based approach, which is much faster than fully subject-specific, could be applied as a clinical prediction tool for osteoarthritis.

Estimation of the Effect of Body Weight on the Development of Osteoarthritis Based on Cumulative Stresses in Cartilage: Data from the Osteoarthritis Initiative.

Evaluation of the subject-specific biomechanical effects of obesity on the progression of OA is challenging. The aim of this study was to create 3D MRI-based finite element models of the knee joints of seven obese subjects, who had developed OA at 4-year follow-up, and of seven normal weight subjects, who had not developed OA at 4-year follow-up, to test the sensitivity of cumulative maximum principal stresses in cartilage in quantitative risk evaluation of the initiation and progression of knee OA. Volumes of elements with cumulative stresses over 5 MPa in tibial cartilage were significantly (p < 0.05) larger in obese subjects as compared to normal weight subjects. Locations of high peak cumulative stresses at the baseline in most of the obese subjects showed a good agreement with the locations of the cartilage loss and MRI scoring at follow-up. Simulated weight loss (to body mass index 24 kg/m2) in obese subjects led to significant reduction of the highest cumulative stresses in tibial and femoral cartilages. The modeling results suggest that an analysis of cumulative stresses could be used to evaluate subject-specific effects of obesity and weight loss on cartilage responses and potential risks for the progression of knee OA.

Evaluation of the Effect of Bariatric Surgery-Induced Weight Loss on Knee Gait and Cartilage Degeneration.

The objective of the study was to investigate the effects of bariatric surgery-induced weight loss on knee gait and cartilage degeneration in osteoarthritis (OA) by combining magnetic resonance imaging (MRI), gait analysis, finite element (FE) modeling, and cartilage degeneration algorithm. Gait analyses were performed for obese subjects before and one-year after the bariatric surgery. FE models were created before and after weight loss for those subjects who did not have severe tibio-femoral knee cartilage loss. Knee cartilage degenerations were predicted using an adaptive cartilage degeneration algorithm which is based on cumulative overloading of cartilage, leading to iteratively altered cartilage properties during OA. The average weight loss was 25.7±11.0 kg corresponding to a 9.2±3.9 kg/m2 decrease in body mass index (BMI). External knee rotation moment increased, and minimum knee flexion angle decreased significantly (p < 0.05) after weight loss. Moreover, weight loss decreased maximum cartilage degeneration by 5±23% and 13±11% on the medial and lateral tibial cartilage surfaces, respectively. Average degenerated volumes in the medial and lateral tibial cartilage decreased by 3±31% and 7±32%, respectively, after weight loss. However, increased degeneration levels could also be observed due to altered knee kinetics. The present results suggest that moderate weight loss changes knee kinetics and kinematics and can slow-down cartilage degeneration for certain patients. Simulation results also suggest that prediction of cartilage degeneration is subject-specific and highly depend on the altered gait loading, not just the patient's weight.

Application of a semi-automatic cartilage segmentation method for biomechanical modeling of the knee joint.

Manual segmentation of articular cartilage from knee joint 3D magnetic resonance images (MRI) is a time consuming and laborious task. Thus, automatic methods are needed for faster and reproducible segmentations. In the present study, we developed a semi-automatic segmentation method based on radial intensity profiles to generate 3D geometries of knee joint cartilage which were then used in computational biomechanical models of the knee joint. Six healthy volunteers were imaged with a 3T MRI device and their knee cartilages were segmented both manually and semi-automatically. The values of cartilage thicknesses and volumes produced by these two methods were compared. Furthermore, the influences of possible geometrical differences on cartilage stresses and strains in the knee were evaluated with finite element modeling. The semi-automatic segmentation and 3D geometry construction of one knee joint (menisci, femoral and tibial cartilages) was approximately two times faster than with manual segmentation. Differences in cartilage thicknesses, volumes, contact pressures, stresses, and strains between segmentation methods in femoral and tibial cartilage were mostly insignificant (p > 0.05) and random, i.e. there were no systematic differences between the methods. In conclusion, the devised semi-automatic segmentation method is a quick and accurate way to determine cartilage geometries; it may become a valuable tool for biomechanical modeling applications with large patient groups.

Simulation of Subject-Specific Progression of Knee Osteoarthritis and Comparison to Experimental Follow-up Data: Data from the Osteoarthritis Initiative.

Economic costs of osteoarthritis (OA) are considerable. However, there are no clinical tools to predict the progression of OA or guide patients to a correct treatment for preventing OA. We tested the ability of our cartilage degeneration algorithm to predict the subject-specific development of OA and separate groups with different OA levels. The algorithm was able to predict OA progression similarly with the experimental follow-up data and separate subjects with radiographical OA (Kellgren-Lawrence (KL) grade 2 and 3) from healthy subjects (KL0). Maximum degeneration and degenerated volumes within cartilage were significantly higher (p < 0.05) in OA compared to healthy subjects, KL3 group showing the highest degeneration values. Presented algorithm shows a great potential to predict subject-specific progression of knee OA and has a clinical potential by simulating the effect of interventions on the progression of OA, thus helping decision making in an attempt to delay or prevent further OA symptoms.