The KNee OsteoArthritis Prediction (KNOAP2020) challenge: An image analysis challenge to predict incident symptomatic radiographic knee osteoarthritis from MRI and X-ray images.

OBJECTIVES: The KNee OsteoArthritis Prediction (KNOAP2020) challenge was organized to objectively compare methods for the prediction of incident symptomatic radiographic knee osteoarthritis within 78 months on a test set with blinded ground truth. DESIGN: The challenge participants were free to use any available data sources to train their models. A test set of 423 knees from the Prevention of Knee Osteoarthritis in Overweight Females (PROOF) study consisting of magnetic resonance imaging (MRI) and X-ray image data along with clinical risk factors at baseline was made available to all challenge participants. The ground truth outcomes, i.e., which knees developed incident symptomatic radiographic knee osteoarthritis (according to the combined ACR criteria) within 78 months, were not provided to the participants. To assess the performance of the submitted models, we used the area under the receiver operating characteristic curve (ROCAUC) and balanced accuracy (BACC). RESULTS: Seven teams submitted 23 entries in total. A majority of the algorithms were trained on data from the Osteoarthritis Initiative. The model with the highest ROCAUC (0.64 (95% confidence interval (CI): 0.57-0.70)) used deep learning to extract information from X-ray images combined with clinical variables. The model with the highest BACC (0.59 (95% CI: 0.52-0.65)) ensembled three different models that used automatically extracted X-ray and MRI features along with clinical variables. CONCLUSION: The KNOAP2020 challenge established a benchmark for predicting incident symptomatic radiographic knee osteoarthritis. Accurate prediction of incident symptomatic radiographic knee osteoarthritis is a complex and still unsolved problem requiring additional investigation.

Imaging in Osteoarthritis.

Osteoarthritis (OA) is the most frequent form of arthritis with major implications on both individual and public health care levels. The field of joint imaging, and particularly magnetic resonance imaging (MRI), has evolved rapidly due to the application of technical advances to the field of clinical research. This narrative review will provide an introduction to the different aspects of OA imaging aimed at an audience of scientists, clinicians, students, industry employees, and others who are interested in OA but who do not necessarily focus on OA. The current role of radiography and recent advances in measuring joint space width will be discussed. The status of cartilage morphology assessment and evaluation of cartilage biochemical composition will be presented. Advances in quantitative three-dimensional morphologic cartilage assessment and semi-quantitative whole-organ assessment of OA will be reviewed. Although MRI has evolved as the most important imaging method used in OA research, other modalities such as ultrasound, computed tomography, and metabolic imaging play a complementary role and will also be discussed.

Assessing collagen alterations in enzymatic degradation models of osteoarthritis via second harmonic generation microscopy.

INTRODUCTION: Structural changes in the collagen II architecture of osteoarthritis (OA) are poorly understood, which is a large shortcoming in the early diagnosis of this disease. Though degradation can be simulated by enzymes including trypsin and bacterial collagenase, the specific structural features of each digestion and their relationship to naturally occurring OA remain unclear. EXPERIMENTAL DESIGN: We used collagen sensitive/specific Second Harmonic Generation (SHG) microscopy in conjunction with optical scattering measurements to probe the resulting architecture changes in bovine knee cartilage upon trypsin and collagenase degradation. Image features extracted from SHG images were used to train a linear discriminant (LD) model capable of classifying enzymatic degradation, which was then applied to human cartilage with varied modified Mankin histological scores. RESULTS: The treatment of cartilage with these enzymes resulted in more disorganized collagen structure, where this effect was greatest with collagenase treatment. Using the LD model, we classified the control and degraded tissues in the three zones with >92% accuracy, showing that these enzymes have distinct activity on the collagen assembly. Application of the LD model to human cartilage indicated that collagenase effects were more representative of in vivo degeneration and were also consistent with damage beginning at the articular surface and progressing into deeper zones. CONCLUSIONS: SHG and optical scattering measurements successfully delineate trypsin and collagenase degradation and suggest that collagen alterations in human OA are better simulated by the latter mechanism. These results lay the groundwork for using high-resolution SHG and optical scattering as an earlier diagnostic tool than is currently available.

Deep learning risk assessment models for predicting progression of radiographic medial joint space loss over a 48-MONTH follow-up period.

OBJECTIVE: To develop and evaluate deep learning (DL) risk assessment models for predicting the progression of radiographic medial joint space loss using baseline knee X-rays. METHODS: Knees from the Osteoarthritis Initiative without and with progression of radiographic joint space loss (defined as ≥ 0.7 mm decrease in medial joint space width measurement between baseline and 48-month follow-up X-rays) were randomly stratified into training (1400 knees) and hold-out testing (400 knees) datasets. A DL network was trained to predict the progression of radiographic joint space loss using the baseline knee X-rays. An artificial neural network was used to develop a traditional model for predicting progression utilizing demographic and radiographic risk factors. A combined joint training model was developed using a DL network to extract information from baseline knee X-rays as a feature vector, which was further concatenated with the risk factor data vector. Area under the curve (AUC) analysis was performed using the hold-out test dataset to evaluate model performance. RESULTS: The traditional model had an AUC of 0.660 (61.5% sensitivity and 64.0% specificity) for predicting progression. The DL model had an AUC of 0.799 (78.0% sensitivity and 75.5% specificity), which was significantly higher (P < 0.001) than the traditional model. The combined model had an AUC of 0.863 (80.5% sensitivity and specificity), which was significantly higher than the DL (P = 0.015) and traditional (P < 0.001) models. CONCLUSION: DL models using baseline knee X-rays had higher diagnostic performance for predicting the progression of radiographic joint space loss than the traditional model using demographic and radiographic risk factors.

Osteoarthritis year in review 2019: imaging.

OBJECTIVE: To provide a narrative review of original articles on osteoarthritis (OA) imaging published between April 1, 2018 and March 30, 2019. METHODS: All original research articles on OA imaging published in English between April 1, 2018 and March 30, 2019 were identified using a PubMed database search. The search terms of "Osteoarthritis" or "OA" were combined with the search terms "Radiography", "X-Rays", "Magnetic Resonance Imaging", "MRI", "Ultrasound", "US", "Computed Tomography", "Dual Energy X-Ray Absorptiometry", "DXA", "DEXA", "CT", "Nuclear Medicine", "Scintigraphy", "Single-Photon Emission Computed Tomography", "SPECT", "Positron Emission Tomography", "PET", "PET-CT", or "PET-MRI". Articles were reviewed to determine relevance based upon the following criteria: 1) study involved human subjects with OA or risk factors for OA and 2) study involved imaging to evaluate OA disease status or OA treatment response. Relevant articles were ranked according to scientific merit, with the best publications selected for inclusion in the narrative report. RESULTS: The PubMed search revealed a total of 1257 articles, of which 256 (20.4%) were considered relevant to OA imaging. Two-hundred twenty-six (87.1%) articles involved the knee joint, while 195 (76.2%) articles involved the use of magnetic resonance imaging (MRI). The proportion of published studies involving the use of MRI was higher than previous years. An increasing number of articles were also published on imaging of subjects with joint injury and on deep learning application in OA imaging. CONCLUSION: MRI and other imaging modalities continue to play an important role in research studies designed to better understand the pathogenesis, progression, and treatment of OA.

A narrative overview of the current status of MRI of the hip and its relevance for osteoarthritis research - what we know, what has changed and where are we going?

OBJECTIVE: To review and discuss the role of magnetic resonance imaging (MRI) in the context of hip osteoarthritis (OA) research. DESIGN: The content of this narrative review, based on an extensive PubMed database research including English literature only, describes the advances in MRI of the hip joint and its potential usefulness in hip OA research, reviews the relevance of different MRI features in regard to symptomatic and structural progression in hip OA, and gives an outlook regarding future use of MRI in hip OA research endeavors. RESULTS: Recent technical advances have helped to overcome many of the past difficulties related to MRI assessment of hip OA. MRI-based morphologic scoring systems allow for detailed assessment of several hip joint tissues and, in combination with the recent advances in MRI, may increase reproducibility and sensitivity to change. Compositional MRI techniques may add to our understanding of disease onset and progression. Knowledge about imaging pitfalls and anatomical variants is crucial to avoid misinterpretation. In comparison to research on knee OA, the associations between MRI features and the incidence and progression of disease as well as with clinical symptoms have been little explored. Anatomic alterations of the hip joint as seen in femoro-acetabular impingement (FAI) seem to play a role in the onset and progression of structural damage. CONCLUSIONS: With the technical advances occurring in recent years, MRI may play a major role in investigating the natural history of hip OA and provide an improved method for assessment of the efficacy of new therapeutic approaches.

OARSI Clinical Trials Recommendations: Knee imaging in clinical trials in osteoarthritis.

Significant advances have occurred in our understanding of the pathogenesis of knee osteoarthritis (OA) and some recent trials have demonstrated the potential for modification of the disease course. The purpose of this expert opinion, consensus driven exercise is to provide detail on how one might use and apply knee imaging in knee OA trials. It includes information on acquisition methods/techniques (including guidance on positioning for radiography, sequence/protocol recommendations/hardware for magnetic resonance imaging (MRI)); commonly encountered problems (including positioning, hardware and coil failures, sequences artifacts); quality assurance (QA)/control procedures; measurement methods; measurement performance (reliability, responsiveness, validity); recommendations for trials; and research recommendations.

OARSI Clinical Trials Recommendations: Hip imaging in clinical trials in osteoarthritis.

Imaging of hip in osteoarthritis (OA) has seen considerable progress in the past decade, with the introduction of new techniques that may be more sensitive to structural disease changes. The purpose of this expert opinion, consensus driven recommendation is to provide detail on how to apply hip imaging in disease modifying clinical trials. It includes information on acquisition methods/techniques (including guidance on positioning for radiography, sequence/protocol recommendations/hardware for magnetic resonance imaging (MRI)); commonly encountered problems (including positioning, hardware and coil failures, artifacts associated with various MRI sequences); quality assurance/control procedures; measurement methods; measurement performance (reliability, responsiveness, and validity); recommendations for trials; and research recommendations.

Imaging following acute knee trauma.

Joint injury has been recognized as a potent risk factor for the onset of osteoarthritis. The vast majority of studies using imaging technology for longitudinal assessment of patients following joint injury have focused on the injured knee joint, specifically in patients with anterior cruciate ligament injury and meniscus tears where a high risk for rapid onset of post-traumatic osteoarthritis is well known. Although there are many imaging modalities under constant development, magnetic resonance (MR) imaging is the most important instrument for longitudinal monitoring after joint injury. MR imaging is sensitive for detecting early cartilage degeneration and can evaluate other joint structures including the menisci, bone marrow, tendons, and ligaments which can be sources of pain following acute injury. In this review, focusing on imaging following acute knee trauma, several studies were identified with promising short-term results of osseous and soft tissue changes after joint injury. However, studies connecting these promising short-term results to the development of osteoarthritis were limited which is likely due to the long follow-up periods needed to document the radiographic and clinical onset of the disease. Thus, it is recommended that additional high quality longitudinal studies with extended follow-up periods be performed to further investigate the long-term consequences of the early osseous and soft tissue changes identified on MR imaging after acute knee trauma.

Cross-relaxation imaging of human patellar cartilage in vivo at 3.0T.

OBJECTIVE: To compare quantitative magnetization transfer (qMT) parameters of patellar cartilage measured using cross-relaxation imaging (CRI) in asymptomatic volunteers and patients with osteoarthritis. DESIGN: The study was performed with Institutional Review Board approval and with all subjects signing informed consent. CRI of the knee joint was performed at 3.0T on 20 asymptomatic volunteers and 11 patients with osteoarthritis. The fraction of macromolecular bound protons (f), the exchange rate constant between macromolecular bound protons and free water protons (k), and the T2 relaxation time of macromolecular bound protons (T2(B)) of patellar cartilage were measured. Mann-Whitney-Wilcoxon rank-sum tests were used to compare qMT parameters between asymptomatic volunteers and patients with osteoarthritis. RESULTS: Average f, k, and T2(B) of patellar cartilage was 12.46%, 7.22 s(-1), and 6.49 µs respectively for asymptomatic volunteers and 12.80%, 6.13 s(-1), and 6.80 µs respectively for patients with osteoarthritis. There were statistically significant differences between groups of subjects for k (P < 0.01) and T2(B) (P < 0.0001) but not f (P = 0.38) of patellar cartilage. CONCLUSION: Patients with osteoarthritis had significantly lower k and significantly higher T2(B) of patellar cartilage than asymptomatic volunteers which suggests that qMT parameters can detect changes in the macromolecular matrix of degenerative cartilage.

Role of neuropeptides in pathogenesis of reflex sympathetic dystrophy.

In 1993, a study was undertaken at the Hand Clinics of Loyola University Medical Center in Chicago to investigate the role of the neuropeptides in the pathogenesis of Reflex Sympathetic Dystrophy. All of the patients had recurrent or continuous pain, swelling, and stiffness of one or both extremities following either acute trauma or surgical intervention. All of the patients showed a markedly increased level of bradykinin as well as calcitonin gene-related peptide. The levels of bradykinin were four times as high as the controls. A few showed increased levels of the other neuropeptides. With these results, we agree with Veldman, Goris and others who consider Reflex Sympathetic Dystrophy to be an exaggerated regional inflammatory disorder.

Role of tissue factor pathway inhibitor in post surgical deep venous thrombosis (DVT) prophylaxis in patients treated with low molecular weight heparin.

Low molecular weight heparins (LMWHs) are now considered to be the drugs of choice for prophylaxis against deep venous thrombosis (DVT) in post operative patients undergoing both general and orthopaedic surgical procedures. Despite extensive research, the exact mechanism of the antithrombotic activity of LMWHs remains unclear. These agents have been shown to activate the fibrinolytic system and to directly inhibit both the activity and the generation of factor Xa and thrombin. New evidence suggests that LMWHs also stimulate the release of endogenous tissue factor pathway inhibitor (TFPI) from the vascular endothelium. This study was designed to investigate the role of TFPI in mediating the antithrombotic activity of LMWHs. We measured the plasma levels of TFPI in a group of post orthopaedic surgery patients treated with daily subcutaneous injections of LMWH and a group of patients treated with placebo. In the placebo group (n = 25), the plasma TFPI levels were slightly elevated immediately after surgery but returned to their baseline value by the fifth post operative day. In contrast, in the group of patients treated with LMWH (n = 34), the plasma levels of TFPI increased significantly and remained elevated for up to 7 days following surgery. However, the TFPI levels in both groups showed wide patient to patient variability. These results indicate that LMWHs stimulate the release of TFPI into the bloodstream of post surgical patients. This suggests the importance of TFPI in mediating the antithrombotic activity of LMWHs.

Protamine sulfate neutralization of the anticoagulant activity of Aprosulate, a synthetic sulfated lactobionic acid amide.

Aprosulate or lactobionic acid is a highly sulfated analogue of heparin which is currently undergoing clinical trials in Europe as a potential antithrombotic drug. Aprosulate exerts a strong anticoagulant effect in plasma as a result of its interaction with heparin cofactor II. In this study, the ability of protamine sulfate to neutralize the anticoagulant activity of Aprosulate was investigated. In vitro, ex vivo, and in vivo coagulation studies were performed using various clotting assays such as the APTT, Heptest, and thrombin time as a measure of the anticoagulant activity of Aprosulate. In the first study, protamine sulfate when administered in vitro to plasma samples containing various concentrations of Aprosulate was found to effectively neutralize the anticoagulant activity of the Aprosulate in both normal human and normal monkey plasma systems. However, the relative index of neutralization of Aprosulate was assay dependent. Protamine sulfate was also found to antagonize the anticoagulant effects of Aprosulate in an ex vivo study. The ex vivo supplementation of protamine sulfate to plasma samples collected at various time intervals following the subcutaneous administration of Aprosulate to a group of primates completely neutralized the anticoagulant activity of the Aprosulate. In a third in vivo study, protamine sulfate when injected intravenously into the bloodstream of a group of primate was found to completely neutralize the anticoagulant effects of a previously administered dosage of Aprosulate. The results of these three studies clearly suggest that protamine sulfate can be used to effectively neutralize the anticoagulant activity of Aprosulate.