Radiomic features of the medial meniscus predicts incident destabilizing meniscal tears: Data from the osteoarthritis initiative.

The objective of this study was to determine the optimal meniscal radiomic features to classify people who will develop an incident destabilizing medial meniscal tear. We used magnetic resonance (MR) images from an existing case-control study that includes images from the first 4 years of the Osteoarthritis Initiative (OAI). For this exploratory analysis (n = 215), we limited our study sample to people with (1) intact menisci at the OAI baseline visit, (2) 4-year meniscal status data, and (3) complete meniscal data from each region of interest. Incident destabilizing meniscal tear was defined as progressing from an intact meniscus to a destabilizing tear by the 48-month visit using intermediate-weighted fat-suppressed MR images. One reader manually segmented each participant's anterior and posterior horn of the medial menisci at the OAI baseline visit. Next, 61 different radiomic features were extracted from each medial meniscus horn. We performed a classification and regression tree (CART) analysis to determine the classification rules and important variables that predict incident destabilizing meniscal tear. The CART correctly classified 24 of the 34 cases and 172 out of 181 controls with a sensitivity of 70.6% and a specificity of 95.0%. The CART identified large zone high gray level emphasis (i.e., more coarse texture) from the posterior horn as the most important variable to classify who would develop an incident destabilizing medial meniscal tear. The use of radiomic features provides sensitive and quantitative measures of meniscal alterations, allowing us to intervene and prevent destabilizing meniscal tears.

Automatic Segmentation of Bone Marrow Lesions on MRI Using a Deep Learning Method.

Bone marrow lesion (BML) volume is a potential biomarker of knee osteoarthritis (KOA) as it is associated with cartilage degeneration and pain. However, segmenting and quantifying the BML volume is challenging due to the small size, low contrast, and various positions where the BML may occur. It is also time-consuming to delineate BMLs manually. In this paper, we proposed a fully automatic segmentation method for BMLs without requiring human intervention. The model takes intermediate weighted fat-suppressed (IWFS) magnetic resonance (MR) images as input, and the output BML masks are evaluated using both regular 2D Dice similarity coefficient (DSC) of the slice-level area metric and 3D DSC of the subject-level volume metric. On a dataset with 300 subjects, each subject has a sequence of 36 IWFS MR images approximately. We randomly separated the dataset into training, validation, and testing sets with a 70%/15%/15% split at the subject level. Since not every subject or image has a BML, we excluded the images without a BML in each subset. The ground truth of the BML was labeled by trained medical staff using a semi-automatic tool. Compared with the ground truth, the proposed segmentation method achieved a Pearson's correlation coefficient of 0.98 between the manually measured volumes and automatically segmented volumes, a 2D DSC of 0.68, and a 3D DSC of 0.60 on the testing set. Although the DSC result is not high, the high correlation of 0.98 indicates that the automatically measured BML volume is strongly correlated with the manually measured BML volume, which shows the potential to use the proposed method as an automatic measurement tool for the BML biomarker to facilitate the assessment of knee OA progression.

Bicycling over a Lifetime Is Associated with Less Symptomatic Knee Osteoarthritis: Data from the Osteoarthritis Initiative.

INTRODUCTION: To evaluate the relationship between a history of bicycling and symptomatic and structural outcomes of knee osteoarthritis (OA), the most common form of arthritis. METHODS: This was a retrospective, cross-sectional study within the Osteoarthritis Initiative (OAI), where we investigated OAI participants with complete data on bicycling, knee pain, and radiographic evidence of knee OA. We used a self-administered questionnaire at the 96-month OAI visit to identify participation in bicycling during four time periods throughout a participant's lifetime (ages 12-18, 19-34, 35-49, and > 50 years old). Using logistic regression, we evaluated the influence of prior bicycling status (any history, history for each time period, number of periods cycling) on three outcomes at the 48-month OAI visit: frequent knee pain, radiographic OA (ROA), and symptomatic radiographic OA (SOA), adjusting for age and gender. RESULTS: 2607 participants were included; 44.2% were male; mean age was 64.3 (SD 9.0) years; body mass index was 28.5 (SD 4.9) kg/m 2 . The adjusted risk ratio for the outcome of frequent knee pain, ROA, and SOA among those who reported any history of bicycling compared to non-bicyclers was 0.83 (0.73-0.92), 0.91 (0.85-0.98), and 0.79 (0.68-0.90), respectively. We observed a dose-response among those who participated in bicycling during more time periods. CONCLUSIONS: People who participated in bicycling had a lower prevalence of frequent knee pain, ROA, and SOA. The benefit appeared cumulative. This study indicates that bicycling may be favorable to knee health and should be encouraged.

Gardening/yardwork in people with knee osteoarthritis is not associated with symptom or structural progression over 48 months: data from the Osteoarthritis Initiative.

OBJECTIVE: To evaluate the relationship of gardening/yardwork with symptomatic and structural progression in those with pre-existing radiographic knee osteoarthritis (OA) in the Osteoarthritis Initiative (OAI), an observational study designed to evaluate potential and known biomarkers and risk factors of knee OA. METHODS: We conducted a cohort study nested within the OAI, including participants ≥ 50 years old with radiographic OA in at least one knee at the time of OAI enrollment. A participant reported the level of gardening/yardwork activity in a self-administered survey. Logistic regression analyses were used to evaluate the association of gardening/yardwork on new frequent knee pain, Kellgren-Lawrence (KL) worsening, medial joint space narrowing (JSN) worsening, and improved frequent knee pain. RESULTS: Of 1808 knees (1203 participants), over 60% of knees had KL grade = 2, 65% had medial JSN, and slightly more than a third had frequent knee symptoms. Gardeners/yardworkers and non-gardners/yardworkers had similar "worsening" outcomes for new knee pain (29% vs. 29%), KL worsening (19% vs. 18%), and medial JSN (23% vs. 24%). The adjusted odds ratio (OR) for the "worsening" outcomes of new knee pain, KL worsening, and medial JSN worsening were 1.0 (0.7-1.3), 1.0 (0.8-1.3), and 1.1 (0.9-1.4), respectively. The gardeners/yardworkers had an adjusted OR of 1.2 (0.9-1.7) for improved knee pain compared with non-gardners/yardworkers. CONCLUSION: Gardening/yardwork is not associated with knee OA progression and should not be discouraged in those with knee OA. Key Points • Gardening/yardwork is not associated with knee OA symptomatic or structural progression. • Gardening/yardwork should not be discouraged in people with knee OA.

Predicting the onset of end-stage knee osteoarthritis over two- and five-years using machine learning.

OBJECTIVE: Identifying participants who will progress to advanced stage in knee osteoarthritis (KOA) trials remains a significant challenge. Current tools, relying on total knee replacements (TKR), fall short in reliability due to the extraneous factors influencing TKR decisions. Acknowledging these limitations, our study identifies a critical need for a more robust metric to assess severe KOA. The end-stage KOA (esKOA) measure, which combines symptomatic and radiographic criteria, serves as a solid indicator. To enhance future trials that use esKOA as an endpoint, our study focuses on developing and validating a machine-learning tool to identify individuals likely to develop esKOA within 2 to 5 years. DESIGN: Utilizing the Osteoarthritis Initiative (OAI) data, we trained models on 3,114 participants and validated them with 606 participants for the right knee, and similarly for the left knee, with external validation from the Multicentre Osteoarthritis Study (MOST) involving 1,602 participants. We aimed to predict esKOA onset at 2-to-2.5 years and 4-to-5 years, defining esKOA by severe radiographic KOA with moderate/severe symptoms or mild/moderate radiographic KOA with persistent/intense symptoms. Our analysis considered 51 candidate predictors, including demographics, clinical history, physical examination, and X-ray evaluations. An online tool predicting esKOA progression, based on models with ten and nine predictors for the right and left knees, respectively, was developed. RESULTS: External validation (MOST) for the right knee at 2.5 years yielded an Area Under Curve (AUC) of 0.847 (95 % CI 0.811 to 0.882), and at 5 years, 0.853 (95 % CI 0.823 to 0.881); for the left knee at 2.5 years, AUC was 0.824 (95 % CI 0.782 to 0.857), and at 5 years, 0.807 (95 % CI 0.768 to 0.843). Models with fewer predictors demonstrated comparable performance. The online tool is available at: https://eskoa.shinyapps.io/webapp/. CONCLUSION: Our study unveils a robust, externally validated machine learning tool proficient in predicting the onset of esKOA over the next 2 to 5 years. Our tool can lead to more efficient KOA trials.

Associations of inflammatory and metabolic biomarkers with incident erosive hand osteoarthritis in the osteoarthritis initiative cohort.

OBJECTIVE: Erosive hand osteoarthritis (eHOA) is a subtype of hand osteoarthritis (OA) that develops in finger joints with pre-existing OA and is differentiated by clinical characteristics (hand pain/disability, inflammation, and erosions) that suggest inflammatory or metabolic processes. METHOD: This was a longitudinal nested case-cohort design among Osteoarthritis Initiative participants who had hand radiographs at baseline and 48-months, and biospecimens collected at baseline. We classified incident radiographic eHOA in individuals with ≥1 joint with Kellgren-Lawrence ≥2 and a central erosion present at 48-months but not at baseline. We used a random representative sample (n = 1282) for comparison. We measured serum biomarkers of inflammation, insulin resistance and dysglycemia, and adipokines using immunoassays and enzymatic colorimetric procedures, blinded to case status. RESULTS: Eighty-six participants developed incident radiographic eHOA. In the multivariate analyses adjusted for age, gender, race, smoking, and body mass index, and after adjustment for multiple analyses, incident radiographic eHOA was associated with elevated levels of interleukin-7 (risk ratio (RR) per SD = 1.30 [95% confidence interval (CI) 1.09, 1.55] p trend 0.01). CONCLUSION: This exploratory study suggests an association of elevated interleukin-7, an inflammatory cytokine, with incident eHOA, while other cytokines or biomarkers of metabolic inflammation were not associated. Interleukin-7 may mediate inflammation and tissue damage in susceptible osteoarthritic finger joints and participate in erosive progression.

Persistent Early Knee Osteoarthritis Symptoms in the First Two Years After ACL Reconstruction.

CONTEXT: Early identification of knee osteoarthritis (OA) symptoms after anterior cruciate ligament reconstruction (ACLR) could enable timely interventions to improve long-term outcomes. However, little is known about the change in early OA symptoms from 6 to 12 months following ACLR. OBJECTIVE: To evaluate the change over time in meeting classification criteria for early knee OA symptoms from 6 to 12 months following ACLR. DESIGN: Prospective Cohort Study. SETTING: Research laboratory. PATIENTS OR OTHER PARTICIPANTS: 82 participants aged 13-35 years who underwent unilateral primary ACLR. On average, participants' 1st and 2nd visits were 6.2 and 12.1 months post-ACLR. MAIN OUTCOME MEASURES: Early OA symptoms were classified using generic (Luyten Original) and patient population-specific (Luyten PASS) thresholds on Knee Injury and Osteoarthritis Outcome Score (KOOS) subscales. Changes in meeting early OA criteria were compared between an initial and follow-up visit at an average of 6 and 12 months post-ACLR, respectively. RESULTS: Twenty-two percent of participants exhibited persistent early OA symptoms across both visits using both the Luyten Original and PASS criteria. From initial to follow-up visit, 18-27% had resolution of early OA symptoms while 4-9% developed incident symptoms. In total, 48-51% had no early OA symptoms at either visit. There were no differences between change in early OA status between adults and adolescents. CONCLUSIONS: Nearly one quarter of participants exhibited persistent early knee OA symptoms based on KOOS thresholds from 6 to 12 months post-ACLR. Determining if this symptom persistence predicts worse long-term outcomes could inform the need for timely interventions after ACLR. Future research should examine if resolving persistent symptoms in this critical window improves later outcomes. Tracking early OA symptoms over time may identify high-risk patients who could benefit from early treatment.

Knee cartilage change on magnetic resonance imaging: Should we lump or split topographical regions? A 2-year study of data from the osteoarthritis initiative.

OBJECTIVE: We challenge the paradigm that a simplistic approach evaluating anatomic regions (e.g., medial femur or tibia) is ideal for assessing articular cartilage loss on magnetic resonance (MR) imaging. We used a data-driven approach to explore whether specific topographical locations of knee cartilage loss may identify novel patterns of cartilage loss over time that current assessment strategies miss. DESIGN: We assessed 60 location-specific measures of articular cartilage on a sample of 99 knees with baseline and 24-month MR images from the Osteoarthritis Initiative, selected as a group with a high likelihood to change. We performed factor analyses of the change in these measures in two ways: (1) summing the measures to create one measure for each of the six anatomically regional-based summary (anatomic regions; e.g., medial tibia) and (2) treating each location separately for a total of 60 measures (location-specific measures). RESULTS: The first analysis produced three factors accounting for 66% of the variation in the articular cartilage changes that occur over 24 months of follow-up: (1) medial tibiofemoral, (2) medial and lateral patellar, and (3) lateral tibiofemoral. The second produced 20 factors accounting for 75% of the variance in cartilage changes. Twelve factors only involved one anatomic region. Five factors included locations from adjoining regions (defined by the first analysis; e.g., medial tibiofemoral). Three factors included articular cartilage loss from disparate locations. CONCLUSIONS: Novel patterns of cartilage loss occur within each anatomic region and across these regions, including in disparate regions. The traditional anatomic regional approach is simpler to implement and interpret but may obscure meaningful patterns of change.

Strength Training Is Associated With Less Knee Osteoarthritis: Data From the Osteoarthritis Initiative.

OBJECTIVE: We aimed to evaluate the relationship of a history of strength training with symptomatic and structural outcomes of knee osteoarthritis (OA). METHODS: This study was a retrospective, cross-sectional study within the Osteoarthritis Initiative (OAI), a multicenter prospective longitudinal observational study. Data were collected at four OAI clinical sites: Memorial Hospital of Rhode Island, the Ohio State University, the University of Pittsburgh, and the University of Maryland/Johns Hopkins. The study included 2,607 participants with complete data on strength training, knee pain, and radiographic evidence of knee OA (male, 44.2%; mean ± SD age 64.3 ± 9.0 years; mean ± SD body mass index 28.5 ± 4.9 kg/m2 ). We used a self-administered questionnaire at the 96-month OAI visit to evaluate the exposure of strength training participation during four time periods throughout a participant's lifetime (ages 12-18, 19-34, 35-49, and ≥50 years old). The outcomes (dependent variables) were radiographic OA (ROA), symptomatic radiographic OA (SOA), and frequent knee pain. RESULTS: The fully adjusted odds ratios (95% confidence interval) for frequent knee pain, ROA, and SOA among those who participated in strength training any time in their lives were 0.82 (0.68-0.97), 0.83 (0.70-0.99), and 0.77 (0.63-0.94), respectively. Findings were similar when looking at the specific age ranges. CONCLUSION: Strength training is beneficial for future knee health, counteracting long-held assumptions that strength training has adverse effects.

Association of Weight Loss and Weight Gain With Structural Defects and Pain in Hand Osteoarthritis: Data From the Osteoarthritis Initiative.

OBJECTIVE: Our aim was to define the association of weight change (weight loss or weight gain) with the incidence and progression of hand osteoarthritis (OA), assessed either by radiography or by pain, using data from the Osteoarthritis Initiative. METHODS: Among the 4,796 participants, we selected 4,598 participants, excluding those with cancer or rheumatoid arthritis or a body mass index under 18.5 kg/m2. We investigated the association of weight change with incidence and progression of radiographic hand OA and the development and resolution of hand pain. Using multivariable logistic regression, we investigated the association of weight change from baseline to the 4-year follow-up with the incidence and progression of radiographic hand OA at the 4-year follow-up. Additionally, multivariable repeated-measure mixed-effects logistic regression analyzed the association of weight change with the development and resolution of hand pain across 2-year, 4-year, 6-year, and 8-year follow-ups. RESULTS: No statistically significant associations were observed between weight change and the investigated outcomes. Specifically, for each 5% weight loss, the odds ratios for the incidence and progression of radiographic hand OA were 0.90 (95% confidence interval [95% CI] 0.67-1.23) and 0.92 (95% CI 0.84-1.00), respectively. Similarly, for each 5% weight loss, the odds ratios for the development and resolution of hand pain at the 8-year follow-up were 1.00 (95% CI 0.92-1.09) and 1.07 (95% CI 0.91-1.25), respectively. CONCLUSION: Our study found no evidence of an association between weight change and the odds of incidence or progression of radiographic hand OA over 4 years, nor the development or resolution of hand pain over 8 years.

Evaluation of a measure of end-stage knee osteoarthritis compared to total knee replacement: An observational study using multicohort data.

OBJECTIVES: To determine if an end-stage knee osteoarthritis (esKOA) measure, based on symptomatic and radiographic criteria, can indicate progression to severe KOA earlier and with fewer research participants than total knee replacement (TKR). We employed both interventional and observational study designs as examples to estimate the required sample sizes. EsKOA in a knee was declared if either of the following two conditions were met: 1) moderate, intense, or severe symptoms of KOA indicated by pain and disability measurement and severe KOA indicated by radiographically-assessed knee structure; 2) intense or severe symptoms of KOA indicated by pain and disability measurement and frequent knee pain with mild or moderate KOA as indicated by radiographically-assessed knee structure. METHODS: We examined the association between weight loss from baseline to 2-to-2.5-year and 4-to-5-year follow-ups and the odds of esKOA and TKR in 5,593 participants (10,357 knees) from the Osteoarthritis Initiative (OAI) and the Multicenter Osteoarthritis Study (MOST). We also estimated the sample sizes needed for interventional and observational study designs to detect a 10, 20, or 50% reduction in the incidence of esKOA and TKR. RESULTS: The association of weight loss with both esKOA and TKR was detected at the 4-to-5-year follow-up. However, at the 2-to-2.5-year follow-up, the association was detected for esKOA but not TKR. The required sample sizes for detecting associations of weight loss with the incidence of esKOA were 85% to 93% smaller than those for TKR at the 4-to-5-year and 2-to-2.5-year follow-ups, respectively. CONCLUSION: The esKOA measure enables shorter and smaller studies compared to using TKR as an outcome.

Radiographic joint space width in individuals with hand osteoarthritis: Are their "healthy" joints really healthy?

OBJECTIVES: We aimed to investigate the systemic nature of hand osteoarthritis (OA). We hypothesized that people who suffer from hand OA would display narrower radiographic joint space width (JSW) - not only in joints with apparent radiographic OA but also in their unaffected "healthy" joints. METHOD: We examined 3394 participants from the Osteoarthritis Initiative with available dominant hand radiographs at baseline. Cases were defined as having interphalangeal OA (IPOA) based on a Kellgren and Lawrence (KL) score of ≥2 in two or more finger joints, whereas controls did not have IPOA. We used custom software to make JSW measurements of the metacarpophalangeal, proximal interphalangeal, and distal interphalangeal joints in fingers 2-5 per hand. In joint-level analyses, we included only KL score=0, allowing us to compare all joints without IPOA in cases and controls. We used generalized estimating equation models to compare JSW between both groups, adjusted for age, gender, metacarpal length, and joint type. RESULTS: Finger joints without radiographic OA had significantly narrower JSW in the IPOA group compared to finger joints in the control group (p < 0.001). The differences were significant across all joint types and for both total JSW measurements as well as for central and lateral sub-regions within each joint group (p < 0.001). CONCLUSION: Unaffected finger joints in people with IPOA had narrower joint space than joints of healthy controls. This implies a systemic nature of hand OA, in which people may have a predisposition for general cartilage deterioration.

Hand joints without radiographic osteoarthritis maintain their joint space width over 4 years despite what's happening elsewhere in the hand.

OBJECTIVES: We aimed to determine if hand osteoarthritis is characterized by systemic cartilage loss by assessing if radiographically normal joints had greater joint space width (JSW) loss during four years in hands with incident or prevalent osteoarthritis elsewhere in the hand compared with hands without osteoarthritis. METHODS: We used semi-automated software to measure JSW in the distal and proximal interphalangeal joints of 3,368 participants in the Osteoarthritis Initiative who had baseline and 48-month hand radiographs. A reader scored 16 hand joints (including the thumb-base) for Kellgren-Lawrence (KL) Grade. A joint had osteoarthritis if scored as KL ≥ 2. We identified three groups based on longitudinal hand osteoarthritis status: 1) no hand osteoarthritis (KL < 2 in all 16 joints) at the baseline and 48-month visits, 2) incident hand osteoarthritis (KL < 2in all 16 joints at baseline and then ≥1 joint with KL ≥ 2 at 48-months), and 3) prevalent hand osteoarthritis (≥1 joint with KL ≥ 2 at baseline and 48-months). We then assessed if JSW in radiographically normal joints (KL = 0) differed across these three groups. We calculated unpooled effect sizes to help interpret the differences between groups. RESULTS: We observed small differences in JSW loss that are unlikely to be clinically important between radiographically normal joints between those without hand osteoarthritis (n = 1054) and those with incident (n = 102) or prevalent hand osteoarthritis (n = 2212) (effect size range: -0.01 to 0.24). These findings were robust when examining JSW loss dichotomized based on meaningful change and in other secondary analyses. CONCLUSIONS: Hand osteoarthritis is not a systemic disease of cartilage.

The Prognostic Potential of End-Stage Knee Osteoarthritis and Its Components to Predict Knee Replacement: Data From the Osteoarthritis Initiative.

OBJECTIVE: We aimed to determine how 2 definitions of end-stage knee osteoarthritis (esKOA) and each component (knee symptoms, persistent knee pain, radiographic severity, and presence of limited mobility or instability) related to future knee replacement (KR). METHODS: We performed knee-based analyses of Osteoarthritis Initiative data from baseline to the first 4 annual follow-up visits, and data on KR from baseline until the fifth yearly contact. We calculated a base model using common risk factors for KR in logistic regression models with generalized estimating equations. We assessed model performance with area under the receiver-operating characteristic curve (AUC) and Hosmer-Lemeshow test. We then added esKOA or each component from the visit (< 12 months) before a KR and change in the year before a KR. We calculated the net reclassification improvement (NRI) index and the integrated discrimination improvement (IDI) index. RESULTS: Our sample was mostly female (58%), ≥ 65 years old, White (82%), and without radiographic knee osteoarthritis (50%). At the visit before a KR, Kellgren-Lawrence (KL) grades (ordinal scale; AUC 0.88, NRI 1.12, IDI 0.11), the alternate definition of esKOA (AUC 0.84, NRI 1.16, IDI 0.12), and a model with every component of esKOA (AUC 0.91, NRI 1.30, IDI 0.17) had the best performances. During the year before a KR, change in esKOA status (alternate definition) had the best performance (AUC 0.86, NRI 1.24, IDI 0.12). CONCLUSION: Radiographic severity may be a screening tool to find a knee that will likely receive a KR. However, esKOA may be an ideal outcome in clinical trials because a change in esKOA state predicts future KR.

Preventing Osteoarthritis After an Anterior Cruciate Ligament Injury: An Osteoarthritis Action Alliance Consensus Statement.

After an anterior cruciate ligament (ACL) injury, people need secondary prevention strategies to identify osteoarthritis at its earliest stages so that interventions can be implemented to halt or slow the progression toward its long-term burden. The Osteoarthritis Action Alliance formed an interdisciplinary Secondary Prevention Task Group to develop a consensus on recommendations to provide clinicians with secondary prevention strategies that are intended to reduce the risk of osteoarthritis after a person has an ACL injury. The group achieved consensus on 15 out of 16 recommendations that address patient education, exercise and rehabilitation, psychological skills training, graded-exposure therapy, cognitive-behavioral counseling (lacked consensus), outcomes to monitor, secondary injury prevention, system-level social support, leveraging technology, and coordinated care models. We hope this statement raises awareness among clinicians and researchers on the importance of taking steps to mitigate the risk of osteoarthritis after an ACL injury.

Evidence Review for Preventing Osteoarthritis After an Anterior Cruciate Ligament Injury: An Osteoarthritis Action Alliance Consensus Statement.

CONTEXT: The Osteoarthritis Action Alliance formed a secondary prevention task group to develop a consensus on secondary prevention recommendations to reduce the risk of osteoarthritis after a knee injury. OBJECTIVE: Our goal was to provide clinicians with secondary prevention recommendations that are intended to reduce the risk of osteoarthritis after a person has sustained an anterior cruciate ligament injury. Specifically, this manuscript describes our methods, literature reviews, and dissenting opinions to elaborate on the rationale for our recommendations and to identify critical gaps. DESIGN: Consensus process. SETTING: Virtual video conference calls and online voting. PATIENTS OR OTHER PARTICIPANTS: The Secondary Prevention Task Group consisted of 29 members from various clinical backgrounds. MAIN OUTCOME MEASURE(S): The group initially convened online in August 2020 to discuss the target population, goals, and key topics. After a second call, the task group divided into 9 subgroups to draft the recommendations and supportive text for crucial content areas. Twenty-one members completed 2 rounds of voting and revising the recommendations and supportive text between February and April 2021. A virtual meeting was held to review the wording of the recommendations and obtain final votes. We defined consensus as >80% of voting members supporting a proposed recommendation. RESULTS: The group achieved consensus on 15 of 16 recommendations. The recommendations address patient education, exercise and rehabilitation, psychological skills training, graded-exposure therapy, cognitive-behavioral counseling (lacked consensus), outcomes to monitor, secondary injury prevention, system-level social support, leveraging technology, and coordinated care models. CONCLUSIONS: This consensus statement reflects information synthesized from an interdisciplinary group of experts based on the best available evidence from the literature or personal experience. We hope this document raises awareness among clinicians and researchers to take steps to mitigate the risk of osteoarthritis after an anterior cruciate ligament injury.

Automatic Measuring of Finger Joint Space Width on Hand Radiograph using Deep Learning and Conventional Computer Vision Methods.

Hand osteoarthritis (OA) severity can be assessed visually through radiographs using semi-quantitative grading systems. However, these grading systems are subjective and cannot distinguish minor differences. Joint space width (JSW) compensates for these disadvantages, as it quantifies the severity of OA by accurately measuring the distances between joint bones. Current methods used to assess JSW require users' interaction to identify the joints and delineate initial joint boundary, which is time-consuming. To automate this process and offer a more efficient and robust measurement for JSW, we proposed two novel methods to measure JSW: 1) The segmentation-based (SEG) method, which uses traditional computer vision techniques to calculate JSW; 2) The regression-based (REG) method, which is a deep learning approach employing a modified VGG-19 network to predict JSW. On a dataset with 3,591 hand radiographs, 10,845 DIP joints were cut as regions of interest and served as input to the SEG and REG methods. The bone masks of the ROI images generated by a U-Net model were sent as input in addition to the ROIs. The ground truth of JSW was labeled by a trained research assistant using a semi-automatic tool. Compared with the ground truth, the REG method achieved a correlation coefficient of 0.88 and mean square error (MSE) of 0.02 mm on the testing set; the SEG method achieved a correlation coefficient of 0.42 and MSE of 0.15 mm. Results show the REG method has promising performance in automatic JSW measurement and in general, Deep Learning approaches can facilitate the automatic quantification of distance features in medical images.