Osteoarthritis imaging最新文献

{"title":"A SYSTEMATIC POST-PROCESSING APPROACH FOR T1Ρ IMAGING OF KNEE ARTICULAR CARTILAGE","authors":"J. Zhong ,&nbsp;Y. Yao ,&nbsp;F. Xiao ,&nbsp;T.Y.M. Ong ,&nbsp;K.W.K. Ho ,&nbsp;S. Li ,&nbsp;C. Huang ,&nbsp;Q. Chan ,&nbsp;J.F. Griffith ,&nbsp;W. Chen","doi":"10.1016/j.ostima.2025.100332","DOIUrl":"10.1016/j.ostima.2025.100332","url":null,"abstract":"<div><h3>INTRODUCTION</h3><div>T_1ρ imaging is an emerging technique in knee MRI for the evaluation of OA. This modality possesses the unique capability to image biochemical components, such as proteoglycans, facilitating early detection and post-treatment monitoring of knee OA. However, a significant challenge associated with T_1ρ imaging lies in the complexity of its post-processing, which encompasses parameter fitting, cartilage segmentation, and subregional parcellation.</div></div><div><h3>OBJECTIVE</h3><div>This abstract presents a systematic methodology for automating knee T_1ρ MRI post-processing by leveraging deep learning and advanced computational techniques.</div></div><div><h3>METHODS</h3><div>Our methodology automated the three primary steps of T_1ρ knee MRI post-processing and provided the mean T_1ρ values for 20 subregions of the femoral and tibial cartilage in the knee (Figure). In our experiments, we utilized four T_1ρ-weighted images to generate the T_1ρ map for 30 OA patients (age 67.63±5.80 years, BMI 26.00±4.08 kg/m²) and 10 healthy volunteers (age 24.90±2.59 years, BMI 22.75±4.51 kg/m²). For each subject, four T_1ρ-weighted images were acquired using a spin-lock frequency of 300 Hz and spin-lock times of 0, 10, 30, and 50 ms, with a resolution of 0.8 × 1 × 3 mm³, resulting in an image matrix size of 44 × 256 × 256 . The spin-lock preparation was followed by an FSE readout with TE/TR = 31/2000 ms. Additionally, we computed the mean of the four T_1ρ-weighted images and employed this mean for automated cartilage segmentation and subregion parcellation. We employed a nnU-Net trained with all 40 subjects for cartilage segmentation, while subregion parcellation was conducted using our previously published rule-based method, CartiMorph. The performance of the approach using deep learning segmentation was assessed using the Dice Coefficient Similarity (DSC), the root-mean-squared deviation (RMSD), and the coefficient of variance of RMSD (CV_RMSD) against the manual segmentation. We excluded 3 OA patients with full cartilage loss above 50% of one cartilage area (FC, MTC, or LTC) in subregion analysis.</div></div><div><h3>RESULTS</h3><div>Our experimental results demonstrated the satisfactory performance of our proposed approach. The mean DSC values for the FC, MTC and LTC in OA patients and healthy volunteers were 0.83, 0.80, and 0.82, respectively. Table 2 provides a comprehensive breakdown of the performance metrics of the agreement in T_1ρ quantification across 20 subregions.</div></div><div><h3>CONCLUSION</h3><div>We proposed a systematic approach for post-processing knee T_1ρ MRI data. The experimental results demonstrated the efficacy of the proposed approach.</div></div>","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100332"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TRANSLATION OF X-RAY TO MRI: DIAGNOSTIC PERFORMANCE OF MRI-DEFINED SIMULATED KELLGREN-LAWRENCE GRADING","authors":"F.W. Roemer ,&nbsp;A. Guermazi ,&nbsp;C.K. Kwoh ,&nbsp;S. Demehri ,&nbsp;D.J. Hunter ,&nbsp;J.E. Collins","doi":"10.1016/j.ostima.2025.100312","DOIUrl":"10.1016/j.ostima.2025.100312","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;INTRODUCTION&lt;/h3&gt;&lt;div&gt;While it has been acknowledged that mild-to-moderate radiographic disease severity of knee osteoarthritis (OA), i.e. knees with grades 2 and 3 on the Kellgren-Lawrence (KL) scale – reflect a wide spectrum of tissue damage, it is unknown whether a knee MRI can easily be translated into a specific radiographic (r) KL grade (KLG). In order to potentially use MRI as a single screening tool for eligibility in clinical trials, it is necessary to define which knees correspond to the current inclusion criteria of rKLG 2 and 3.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;OBJECTIVE&lt;/h3&gt;&lt;div&gt;The aim of this study was to assess the diagnostic performance of a priori-determined definitions of MRI-assessed KLG based on osteophytes (OPs) and cartilage damage in the tibiofemoral joint (TFJ).&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;METHODS&lt;/h3&gt;&lt;div&gt;We included MRI readings from the following Osteoarthritis Initiative substudies: FNIH Biomarker consortium, POMA and BEAK. Included are visits with centrally read rKLG and available MOAKS readings. In order to match the anteroposterior (a.p.) radiograph, four locations for OPs assessed in the coronal plane (central medial femur, central medial tibia, central lateral femur, central lateral tibia) were considered. Eight subregions were considered for cartilage damage to mirror the weight bearing tibiofemoral joints on X-ray: anterior medial tibia, central medial tibia, posterior medial tibia, central medial femur, anterior lateral tibia, central lateral tibia, posterior lateral tibia and central lateral femur. Cartilage damage was classified as minor: focal damage only (MOAKS 0, 1.0, 1.1); moderate: damage with no advanced full thickness wide-spread damage (MOAKS 2.0, 2.1, 3.0, 3.1); and severe: full thickness wide-spread damage (MOAKS 2.2, 3.2, 3.3).&lt;/div&gt;&lt;div&gt;The definitions were derived based on expert consensus opinion as follows:&lt;/div&gt;&lt;div&gt;MRI KL0: no OP (=grade 0 in all 4 locations), minor cartilage damage only&lt;/div&gt;&lt;div&gt;MRI KL1: grade 1 OP in at least 1 of 4 TFJ locations, maximum OP grade 1, minor cartilage damage only&lt;/div&gt;&lt;div&gt;MRI KL2: grade 1, 2 or 3 OP in at least 1 of 4 TFJ locations, moderate cartilage damage&lt;/div&gt;&lt;div&gt;MRI KL2a (“atrophic”): no OP (=grades 0 in all 4 TFJ locations), moderate cartilage damage&lt;/div&gt;&lt;div&gt;MRI KL 3: grade 1, 2 or 3 OP in at least 1 of 4 TFJ locations, severe cartilage damage in at least 1 of 8 subregions.&lt;/div&gt;&lt;div&gt;MRI KL3a (“atrophic”): no OP (=grades 0 in all 4 TFJ locations), severe cartilage damage in at least 1 of 8 subregions&lt;/div&gt;&lt;div&gt;MRI KL 4: grade 1, 2 or 3 OP in at least 1 of 4 TFJ locations, severe cartilage damage in at least 2 of 4 corresponding subregions medially or laterally or both.&lt;/div&gt;&lt;div&gt;Sensitivity, specificity, negative and positive predictive values were determined using radiographic KLG as the reference.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;RESULTS&lt;/h3&gt;&lt;div&gt;In total, the dataset includes 4924 visits from 1981 participants contributing 2276 knees for up to 4 timepoints. The rKL dis","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100312"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PHOTON-COUNTING CT-BASED TRABECULAR BONE ANALYSIS IN THE KNEE: A COMPARATIVE STUDY OF ADVANCED OSTEOARTHRITIS AND HEALTHY CONTROLS","authors":"M. Jarraya ,&nbsp;W. Issa ,&nbsp;C. Chane ,&nbsp;A. Zheng ,&nbsp;D. Guermazi ,&nbsp;K. Sariahmed ,&nbsp;M. Mohammadian ,&nbsp;M. Kim ,&nbsp;K.A. Flynn ,&nbsp;T.L. Redel ,&nbsp;F. Liu ,&nbsp;M. Loggia","doi":"10.1016/j.ostima.2025.100344","DOIUrl":"10.1016/j.ostima.2025.100344","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;INTRODUCTION&lt;/h3&gt;&lt;div&gt;The advent of photon counting CT is a major advance in the development of CT technology. Its enhanced spatial resolution, compared to conventional CT, and its much-reduced radiation dose make it a promising tool for in vivo assessment of bone microarchitecture in clinical settings. For example, prior studies relying on HR-pQCT and Micro CT have shown greater volumetric bone mineral density (vBMD) and trabecular (Tb) thickness (Th) were significantly higher in the medial compartment and associated with increased disease severity. There is no data on trabecular bone structure using photon counting CT in patients with osteoarthritis (OA).&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;OBJECTIVE&lt;/h3&gt;&lt;div&gt;To compare High-Resolution PCCT-defined trabecular bone microstructure between patients with advanced OA versus healthy controls.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;METHODS&lt;/h3&gt;&lt;div&gt;We used data from the ongoing DIAMOND knee study which investigates the role of neuroinflammation in chronic postoperative pain after TKR. To date, 9 healthy controls and 36 patients with advanced knee OA scheduled for total knee replacements have been recruited, including 7 patients who underwent unilateral PCCT. All other patients and healthy controls had bilateral knee scans. We used a Naeotom 144 Alpha PCCT scanner manufactured by Siemens Healthineers (Erlangen, Germany). Scans were performed with a tube voltage of (120 keV) and, to provide maximum scan performance and minimum noise deterioration, slice increments of 0.2 were used. We also utilized a slice thickness of 0.2 mm, rotation time 0.5 seconds, and pitch 0.85 Images were reconstructed with sharp bone kernel Br89 and matrix 1024 × 1024.. The field of view varied depending on the patient’s size, thus resulting in a variable voxel in plane dimension (0.2-0.4 mm). Regions of interests were defined for the proximal tibia and distal femur in a stack height defined by slices equivalent to 1/6&lt;sup&gt;th&lt;/sup&gt; to 1/4&lt;sup&gt;th&lt;/sup&gt; of the measured joint width, prescribed distally or proximally from the joint line, respectively. Images were analyzed using a previously reported iterative threshold-seeking algorithm with 3D connectivity check to separate trabecular bone from marrow. Apparent structural parameters were derived from bone volume (BV), bone surface (BS), and total volume (TV) according to equations by Parfitt’s model of parallel plates (Tb.Th, Tb.Separation, BV/TV). These trabecular bone measures were compared between OA and healthy knees using independent sample t-test or non-parametric Wilcoxon tests, depending on normality assumptions. All of the analyses were performed compartment-wise in all four ROIs. These images analyses steps were derived from methods previously published by Wong et al. (DOI: &lt;span&gt;&lt;span&gt;https://doi.org/10.1016/j.jocd.2018.04.001&lt;/span&gt;&lt;svg&gt;&lt;path&gt;&lt;/path&gt;&lt;/svg&gt;&lt;/span&gt;).&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;RESULTS&lt;/h3&gt;&lt;div&gt;We analyzed data from 12 knees of 12 patients with advanced knee OA (mean age 66.0 ± 9.4 years","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100344"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UNCOVERING STRUCTURAL DISEASE PATTERNS OF EARLY POST-TRAUMATIC OSTEOARTHRITIS IN A DMM MOUSE MODEL USING CONTRAST-ENHANCED MICRO-COMPUTED TOMOGRAPHY","authors":"J.E. Schadow ,&nbsp;E.C. Boersma ,&nbsp;A.M. Cagnoni ,&nbsp;H. Liu ,&nbsp;R.A. Davey ,&nbsp;K.S. Stok","doi":"10.1016/j.ostima.2025.100316","DOIUrl":"10.1016/j.ostima.2025.100316","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;INTRODUCTION&lt;/h3&gt;&lt;div&gt;Contrast-enhanced micro-computed tomography (CECT) is a non-destructive method to assess cartilage degeneration seen in diseases such as OA whilst also allowing for analysis of bone changes [1, 2]. Application has been limited to &lt;em&gt;ex vivo&lt;/em&gt; and &lt;em&gt;in situ&lt;/em&gt; studies but using CECT &lt;em&gt;in vivo&lt;/em&gt; holds the potential to quantify and track structural cartilage and bone changes and illuminate new understanding of disease onset and progression.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;OBJECTIVE&lt;/h3&gt;&lt;div&gt;The aim of this study was to uncover structural disease patterns of early post-traumatic osteoarthritis in a destabilized medial meniscus (DMM) mouse model using time-lapse CECT.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;METHODS&lt;/h3&gt;&lt;div&gt;DMM (n=22) or sham surgery (n=22) was performed on ten-week-old C57Bl/6 mice. A further three mice did not undergo surgery but were euthanized at 10 weeks of age and processed for histology. Of the mice that had surgery, three mice per group were euthanised and processed for histology at seven-, 14-, 21- and 28-days post-surgery. The remaining ten mice per group received an intra-articular injection of Dotarem (Guerbet) and were scanned at 10.4 μm, 70 kVp, 114 μA using microCT (vivaCT80, Scanco Medical AG) at one-day pre-surgery and seven-, 14-, 21-, 28-, and 56-days post-surgery. After scanning at the final timepoint, three mice per group were euthanised after scanning at 56-days post-surgery and processed for histology. Safranin-O histology was used to score joints following the OARSI guidelines [3]. Mean attenuation of cartilage, joint alignment, joint space morphometry, subchondral bone morphometry, and osteophyte presence were analysed from microCT images. Mixed-effects analysis was used to investigate effects of osteoarthritis, time, and joint side (medial/lateral) on mean attenuation, joint space, subchondral bone, and osteophytes as well as the effects of osteoarthritis and time on joint alignment.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;RESULTS&lt;/h3&gt;&lt;div&gt;OARSI score of medial tibia in DMM OA group increased compared to the lateral side in DMM OA group and medial side of sham controls (Figure 1A). Mean attenuation of medial tibial cartilage in DMM OA mice did not change over time whereas that of sham controls increased over time. The number of voxels in the thinnest joint space layer increased on the medial side of DMM OA group post-surgery but did not change on medial side of sham controls or lateral side of either group (Figure 1B). There was increased variability in dorsal axis and midsagittal axis angles α and γ of DMM OA mice at 14-, 21-, and 28-days post-surgery. There was no difference in shape κ and scale θ of osteophyte thickness distribution of DMM OA tibia compared to sham control, despite osteophyte development on the lateral and medial side of DMM OA tibiae and frontal side of both groups. Cortical porosity and trabecular thickness of medial tibia in DMM OA mice increased over time before decreasing at 56-days post-surg","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100316"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144524027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EARLY DETECTION OF KNEE OA – THE ROLE OF A COMPOSITE DISEASE ACTIVITY SCORE: DATA FROM THE OSTEOARTHRITIS INITIATIVE","authors":"J.C. Patarini ,&nbsp;T.E. McAlindon ,&nbsp;J. Baek ,&nbsp;E. Kirillov ,&nbsp;N. Vo ,&nbsp;M.J. Richard ,&nbsp;M. Zhang ,&nbsp;M.S. Harkey ,&nbsp;G.H. Lo ,&nbsp;S.-H. Liu ,&nbsp;K. Lapane ,&nbsp;C.B. Eaton ,&nbsp;J. MacKay ,&nbsp;J.B. Driban","doi":"10.1016/j.ostima.2025.100306","DOIUrl":"10.1016/j.ostima.2025.100306","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;INTRODUCTION&lt;/h3&gt;&lt;div&gt;BM lesions and effusion-synovitis are frequent and dynamic disease processes detected from early- to late-stage knee OA. These processes are associated with knee symptoms, representing the primary clinical manifestations of OA. Through a systematic and iterative process, we previously developed and validated a composite biomarker – the disease activity score – that combines BM lesions and effusion-synovitis volumes throughout a knee into an efficient continuous single score.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;OBJECTIVE&lt;/h3&gt;&lt;div&gt;To evaluate whether dynamic disease processes (effusion-synovitis volume and BM lesions), summarized by a validated efficient continuous composite score, are present in early OA and prognostic of incident symptomatic knee OA over the subsequent three years.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;METHODS&lt;/h3&gt;&lt;div&gt;We analyzed a convenience sample within the OAI of participants without symptomatic knee OA. Pain assessments and radiographs were collected annually. Among 913 knees (n=572 participants), most were female, white, and had a mean age of 61 (SD=9) and body mass index of 29.4 (SD=4.5) kg/m&lt;sup&gt;2&lt;/sup&gt;. MR images were collected at each OAI site using Siemens 3.0 Tesla Trio MR systems. We measured BM lesion and effusion-synovitis volumes on a sagittal IM fat-suppressed sequence (field of view=160mm, slice thickness=3mm, skip=0mm, flip angle=180 degrees, echo time=30ms, recovery time=3200ms, 313 × 448 matrix, x-resolution=0.357mm, y-resolution=0.357mm). Using MR images from the initial visit, we combined effusion-synovitis and BM lesion volumes to calculate a composite score, referred to as the disease activity score. A disease activity score of 0 approximated the average score for a reference sample (n=2,787, 50% had radiographic knee OA, average [SD] WOMAC pain score = 2.8 [3.3]); lower scores (negative scores) indicate milder disease, while greater values indicate worse disease. The outcome was incident symptomatic knee OA (the combined state of frequent knee pain and radiographic OA [KLG≥2]) within three years after the disease activity measurement. We used logistic regression with repeated measures to assess the association between disease activity (continuous measure) and incident symptomatic knee OA, adjusting for gender, age, and body mass index.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;RESULTS&lt;/h3&gt;&lt;div&gt;Disease activity ranged from -3.3 to 31.1 (lower values = less effusion-synovitis and BM lesions). Knees that developed incident symptomatic knee OA had greater disease activity (-0.3 [2.7] vs. -1.1 [2.8]): the adjusted relative risk=1.06 (per 1 unit of disease activity; 95% confidence interval: 1.02-1.10). Our stratified analyses revealed those with only radiographic OA (adjusted relative risk=1.37 [1.06-1.78]) or only symptoms (adjusted relative risk=1.15 [1.03-1.28]) at baseline drove the associations between disease activity and incident symptomatic knee OA.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;CONCLUSION&lt;/h3&gt;&lt;div&gt;Our findings underscore the critical","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100306"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144524131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DATA-DRIVEN DISCOVERY OF KNEE OSTEOARTHRITIS SUBGROUPS VIA CLUSTER ANALYSIS OF MRI BIOMARKERS","authors":"J.E. Collins ,&nbsp;L.A. Deveza ,&nbsp;D.J. Hunter ,&nbsp;V.B.K. Kraus ,&nbsp;A. Guermazi ,&nbsp;F.W. Roemer ,&nbsp;J.N. Katz ,&nbsp;T. Neogi ,&nbsp;E. Losina","doi":"10.1016/j.ostima.2025.100351","DOIUrl":"10.1016/j.ostima.2025.100351","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;INTRODUCTION&lt;/h3&gt;&lt;div&gt;Identifying structural morphotypes in knee OA, subgroups defined by anatomical and morphological attributes, may facilitate personalized treatment by aligning specific patterns of joint damage with treatment mechanism of action. Cluster analysis is a type of unsupervised machine learning used to uncover subgroups and may provide insight into structural morphotypes in knee OA.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;OBJECTIVE&lt;/h3&gt;&lt;div&gt;To use cluster analysis to investigate possible subgroups defined by imaging features in a cohort of persons with knee OA.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;METHODS&lt;/h3&gt;&lt;div&gt;We used data from the PROGRESS OA study, the second phase of the FNIH OA Biomarkers Consortium project, which includes data from the placebo arms of several completed RCTs testing various therapeutic interventions for symptomatic knee OA. MRIs were obtained at baseline and read according to the MRI OA Knee Score (MOAKS) by an experienced radiologist. We included MOAKS assessments of BML size, osteophytes, cartilage, Hoffa-synovitis, effusion-synovitis, and meniscus in the clustering algorithms. Raw ordinal MOAKS scores were used in this analysis. We used Partitioning Around Medoids (PAM) for clustering. PAM is similar to K-means, but instead of defining cluster center as the centroid (mean), the medoid is used, making the method more robust to outliers and appropriate for non-Gaussian data. We undertook several approaches to clustering to perform dimension reduction and incorporate correlations between MOAKS scores A: PAM on Gower’s distance; B: PAM on the dissimilarity matrix from Spearman correlation; C: PAM after non-metric multidimensional scaling (NMDS) using Gower distance for dimension reduction. These approaches aimed to uncover patterns orthogonal to disease severity. The number of clusters was selected based on silhouette width and the gap statistic. Silhouette scores 0.25 to 0.5 indicate weak to reasonable fit.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;RESULTS&lt;/h3&gt;&lt;div&gt;356 participants from four RCTs were included, 138 (39%) with KLG 2 radiographs and 218 (61%) with KLG 3. The cohort was 57% female with average age 62 (SD 8). The number of clusters ranged from 2 to 3 depending on method. There was modest to high overlap between clustering solutions from different methods, suggesting some stability of clustering solutions. Average silhouette scores were 0.19, 0.13, 0.40 for methods A, B, and C, suggesting poor to modest fit. This could suggest weak structure, overlapping clusters, or need for additional dimension reduction. Methods A and C had one cluster dominated (&gt;95% KLG 3) by KLG 3 knees (Figure 1). Investigation of MOAKS assessments by cluster for each of three clustering solutions is shown in Table 1. For example, method C suggested 3 clusters. Clusters 1 and 2 are both approximately 55-60% KLG 2. Cluster 1 has more lateral cartilage damage, and higher BML and osteophyte scores, while cluster 2 has more medial cartilage damage and medial meniscal dama","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100351"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144524177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"REPEATABILITY OF CT OSTEOARTHRITIS KNEE SCORE (COAKS) MULTICOMPONENT MEASURES","authors":"T.D. Turmezei ,&nbsp;A. Boddu ,&nbsp;N.H. Degala ,&nbsp;J.A. Lynch ,&nbsp;N.A. Segal","doi":"10.1016/j.ostima.2025.100325","DOIUrl":"10.1016/j.ostima.2025.100325","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;INTRODUCTION&lt;/h3&gt;&lt;div&gt;The CT Osteoarthritis Knee Score (COAKS) is a semiquantitative system for grading structural disease features in knee OA from weight bearing CT (WBCT). Previous work has demonstrated excellent inter- and intra-observer reliability of COAKS with the aid of a feature scoring atlas, but test-retest repeatability has not yet been evaluated. There is growing interest in multicomponent measures in knee OA imaging research because they may provide granularity in structural feature evaluation, in particular with respect to study baseline stratification and monitoring progression. The multi-feature and multi-compartment nature of COAKS means that it could provide novel insights into OA morphotypes and structural disease progression if found to be robust.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;OBJECTIVE&lt;/h3&gt;&lt;div&gt;To evaluate test-retest agreement of COAKS multicomponent scores based on WBCT imaging.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;METHODS&lt;/h3&gt;&lt;div&gt;14 individuals recruited and consented at the University of Kansas Medical Center had baseline and follow-up WBCT imaging suitable for analysis. Participants were (mean ± SD) 61.3 ± 8.4 years old, with BMI 30.7 ± 4.3 kg/m&lt;sup&gt;2&lt;/sup&gt; and had a male:female ratio of 8:6. All scanning was performed on a single XFI WBCT scanner (Planmed Oy, Helsinki, Finland) with the mean ± SD interval between baseline and follow-up attendances 14.9 ± 8.1 days. A Synaflexer&lt;sup&gt;TM&lt;/sup&gt; device was used to standardize knee positioning during scanning. Imaging acquisition parameters were 96 kV tube voltage, 51.4 mA tube current, 3.5 s exposure time. A standard bone algorithm was applied for reconstruction with 0.3 mm isotropic voxels and a 21 cm vertical scan range. All scans were anonymised prior to analysis both according to the individual and imaging attendance. All knees were reviewed for COAKS by an experienced musculoskeletal radiologist (T.D.T.). Scores were recorded in a cloud-based file on Google Sheets (alongside the feature atlas in Google Docs) and read by custom MATLAB scripts to generate baseline versus follow-up difference plots and intraclass correlation coefficients for absolute agreement from a single observer, Shrout-Fleiss ICC(3,1). Scores for individual COAKS features (JSW, osteophytes, subchondral cysts, subchondral sclerosis) were combined across compartments. Compartment scores (medial tibiofemoral, lateral tibiofemoral, patellofemoral, proximal tibiofibular) were combined across features. Multicomponent scores were also summated for the whole tibiofemoral compartment (medial-lateral combined) and from across the whole knee joint.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;RESULTS&lt;/h3&gt;&lt;div&gt;ICC values were excellent (&gt;0.81) for all multicomponent scores apart from subchondral sclerosis combined across all compartments (0.69, 0.43-0.84) and all features combined at the proximal tibiofibular joint (0.65, 0.38-0.82). Best agreement was seen for osteophytes combined across all compartments (0.93, 0.85-0.96) (Figure 1), all features comb","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100325"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144524200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PREDICTING KNEE OSTEOARTHRITIS PROGRESSION USING EXPLAINABLE MACHINE LEARNING AND CLINICAL IMAGING DATA","authors":"R.E. Harari ,&nbsp;J. Collins ,&nbsp;S.E. Smith ,&nbsp;S. Wells ,&nbsp;J. Duryea","doi":"10.1016/j.ostima.2025.100348","DOIUrl":"10.1016/j.ostima.2025.100348","url":null,"abstract":"<div><h3>INTRODUCTION</h3><div>Accurate prediction of knee osteoarthritis (KOA) progression remains a clinical challenge due to its heterogeneous nature and discordance between structural and symptomatic outcomes. Integrated imaging and machine learning (ML) approaches may enhance prognostic modeling but often suffer from limited interpretability or reliance on static features.</div></div><div><h3>OBJECTIVE</h3><div>We aim to develop explainable ML models for predicting KOA progression using baseline and longitudinal imaging and clinical features. This study also aims to identify key imaging biomarkers associated with structural and symptomatic progression.</div></div><div><h3>METHODS</h3><div>Data and 3T MRI measurements from 600 participants in the FNIH OA Biomarkers Consortium were analyzed. Participants were grouped into four progression categories based on 48-month joint space narrowing and WOMAC pain: (1) radiographic + pain progressors, (2) radiographic-only, (3) pain-only, and (4) non-progressors. Two binary classification frameworks were defined: (1) radiographic + pain vs. all others (primary), and (2) all radiographic progressors vs. pain-only + non-progressors (secondary). ML models included Random Forest, XGBoost, logistic regression, decision tree, and multilayer perceptron (MLP). The model used demographic information and imaging features from semi-automated segmentation software. We measured the volume of medial compartment femur cartilage (Cart), bone marrow lesion (BML) in the MF, LF, MT, LT, patella, and trochlea, osteophytes (Ost) in the MF, LF, MT, and LT, Hoffa’s synovitis (HS), and effusion/synovitis (ES). Longitudinal delta values were computed over 24 months. Performance was assessed via 10-fold stratified cross-validation (AUC, F1-score). Explainability tools included SHAP, Gini importance, coefficients, and permutation importance.</div></div><div><h3>RESULTS</h3><div>In the cross-sectional setting, the Random Forest classifier achieved the highest discrimination performance, with AUC values of 0.672 for the primary task (radiographic + pain progressors vs. others) and 0.791 for the secondary task (all radiographic progressors vs. others). The MLP model showed similar results in the secondary task (AUC = 0.743). AUC performance metrics for all models are shown in Table 1. Model performance improved notably when incorporating 24-month changes in imaging features. In the longitudinal analysis, Random Forest again performed best in the secondary task (AUC = 0.873), followed by XGBoost and MLP. The strongest predictors in these models were changes in medial femoral cartilage thickness, medial tibial bone marrow lesions, and osteophyte scores. To better understand the basis of model predictions, we applied four feature ranking methods. Among them, the SHAP method produced the most consistent and clinically interpretable results. As an example, shown in Figure 1 which show top 15 important features, SHAP highlighted 24-month r","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100348"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SIMULTANEOUS 3D CARTILAGE T2 MAPPING AND MORPHOLOGICAL IMAGING WITH RAFO-4 MRI, A MACHINE LEARNING ALGORITHM","authors":"K. Balaji ,&nbsp;M. Mendoza ,&nbsp;P.M. Vicente ,&nbsp;C. Galazis ,&nbsp;S. Kukran ,&nbsp;A.A. Bharath ,&nbsp;P.J. Lally ,&nbsp;N.K. Bangerter","doi":"10.1016/j.ostima.2025.100277","DOIUrl":"10.1016/j.ostima.2025.100277","url":null,"abstract":"<div><h3>INTRODUCTION</h3><div>Cartilage T₂ is a non-invasive, microstructural MRI biomarker for KOA, with elevated T₂ indicating early KOA onset. Cartilage T₂ maps could be used in clinical trials to test a drug candidate’s effect on microstructure. Quantitative DESS (qDESS) is widely used for cartilage imaging as it simultaneously acquires 3D, morphological whole knee images and quantitative T₂ maps in ∼5 minutes. Researchers are also developing T₂ mapping techniques using phase-cycled balanced Steady State Free Precession (pc-bSSFP). It is rapid and has higher SNR efficiency than qDESS, which could lead to better 3D morphological image quality and more reliable T₂ maps. PLANET is a technique that uses a minimum of six different pc-bSSFP acquisitions to analytically calculate T₂. This is too time-consuming to be clinically feasible. In this study, we trained Random Forest (RaFo) machine learning models to estimate T₂ from fewer pc-bSSFP acquisitions to reduce scan time while still estimating reliable voxel-level T₂ values.</div></div><div><h3>OBJECTIVE</h3><div>1) Train and test RaFo models on simulated 4 and 6 pc-bSSFP data and benchmark performance with PLANET. 2) Test RaFo models on in vivo knee data and benchmark performance with the reference T₂ mapping technique (spin echo), PLANET, and qDESS.</div></div><div><h3>METHODS</h3><div>70,000-sample training and 30,000-sample testing datasets were simulated. Each sample corresponded to 12 different pc-bSSFP measurements of the same voxel location in the tissue. The physics-informed simulated datasets were pre-processed, which included sub-sampling from 12 pc-bSSFP measurements to 4 or 6. RaFo models were then trained to estimate T₂ and tested on these pre-processed datasets. Finally, to evaluate performance on noisier <em>in vivo</em> data, fully sampled knee images of two healthy volunteers (HVs, 2F:24-25) were acquired on a 3T Siemens Verio (Erlangen, Germany) with an 8-channel knee coil using 12 measurements of bSSFP (water excitation, 8.6/4.3 ms TR/TE; 22° flip angle; 1 × 1 × 5 mm³ voxel volume; 128 × 128 × 130 mm³), qDESS (water excitation; 20° flip angle; 21.77 ms TR; 6 ms TE; 364 Hz/Px receiver bandwidth; 0 dummy scans per volume), and a gold-standard spin-echo T₂ mapping approach (2500 ms TR; 15, 45, 75 ms TE, 90° and 180° flip angle) with appropriate ethics approval. All images had 1 × 1 × 5 mm³ voxel volume and 128 × 128 mm² field of view. PLANET was tested on 6 pc-bSSFP measurements (labelled PLANET-6). RaFo models were tested on 4 and 6 bSSFP measurements (labelled RaFo-4 and RaFo-6, respectively).</div></div><div><h3>RESULTS</h3><div>Fig1 shows results from simulated data tests, with similar performance across the RaFo models and PLANET. Fig2 shows the in vivo T₂ maps, with the RaFo models visually","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100277"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"THE EFFECT OF WEIGHT LOSS AND GLUCAGON-LIKE PEPTIDE-1 RECEPTOR AGONIST ON STRUCTURAL CHANGES IN KNEE OSTEOARTHRITIS: SECONDARY ANALYSIS OF THE RANDOMISED, PLACEBO-CONTROLLED LOSEIT TRIAL","authors":"M.W. Brejnebøl ,&nbsp;T. Haugegaard ,&nbsp;R. Christensen ,&nbsp;H. Gudbergsen ,&nbsp;H. Bliddal ,&nbsp;P. Hansen ,&nbsp;L.E. Kristensen ,&nbsp;C.T. Nielsen ,&nbsp;C.L. Daugaard ,&nbsp;J.U. Nybing ,&nbsp;M. Henriksen ,&nbsp;M. Boesen","doi":"10.1016/j.ostima.2025.100280","DOIUrl":"10.1016/j.ostima.2025.100280","url":null,"abstract":"<div><h3>OBJECTIVE</h3><div>To compare the effect of weight loss and glucagon-like peptide-1 receptor agonist (GLP-1RA) (liraglutide), relative to weight loss and placebo, on structural knee osteoarthritis.</div></div><div><h3>METHODS</h3><div>This secondary analysis followed a superiority framework of data from the LOSEIT trial, a randomised, parallel-group, placebo-controlled trial. Participants aged 18 to 74 years with overweight (BMI ≥27 kg/m²), symptomatic and early-to-moderate radiographic knee OA were recruited. They underwent 8-week intensive diet intervention followed by randomisation to receive a GLP-1RA (liraglutide 3 mg/d) or placebo for 52 weeks. The primary outcome was the change in radiographic medial minimal joint space width (mmJSW). Analyses were conducted on the intention-to-treat population.</div></div><div><h3>RESULTS</h3><div>From November 14, 2016, through September 12, 2017, 156 participants were randomly assigned to GLP-1RA (n = 80) or to placebo (n = 76). As reported in the primary analysis of the data, the GLP-1RA group lost more weight than the placebo group (mean difference, - 3.21 kg, 95%CI: - 6.39 to - 0.03; P=0.050). The GLP-1RA group demonstrated an increase in mean mmJSW of 0.22 mm (95%CI: 0.06 to 0.38) while the placebo group did not change (0.07 mm, 95%CI: - 0.11 to 0.25). No evidence of a difference in mean mmJSW was observed between groups (0.15 mm, 95%CI: -0.06 to 0.36; P=0.17).</div></div><div><h3>CONCLUSION</h3><div>While the results indicate a potentially favourable effect on mmJSW within the GLP-1RA group, the observed difference in structural knee OA changes on radiographs compared to placebo did not reach statistical significance.</div></div>","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"5 ","pages":"Article 100280"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}