Magnetic Resonance Imaging (MRI) offers strong soft tissue contrast but suffers from long acquisition times and requires tedious annotation from radiologists. Traditionally, these challenges have been addressed separately with reconstruction and image analysis algorithms. To see if performance could be improved by treating both as end-to-end, we hosted the K2S challenge, in which challenge participants segmented knee bones and cartilage from 8× undersampled k-space. We curated the 300-patient K2S dataset of multicoil raw k-space and radiologist quality-checked segmentations. 87 teams registered for the challenge and there were 12 submissions, varying in methodologies from serial reconstruction and segmentation to end-to-end networks to another that eschewed a reconstruction algorithm altogether. Four teams produced strong submissions, with the winner having a weighted Dice Similarity Coefficient of 0.910 ± 0.021 across knee bones and cartilage. Interestingly, there was no correlation between reconstruction and segmentation metrics. Further analysis showed the top four submissions were suitable for downstream biomarker analysis, largely preserving cartilage thicknesses and key bone shape features with respect to ground truth. K2S thus showed the value in considering reconstruction and image analysis as end-to-end tasks, as this leaves room for optimization while more realistically reflecting the long-term use case of tools being developed by the MR community.

Artificial intelligence in musculoskeletal applications: a primer for radiologists - Diagnostic and Interventional Radiology

Loading is invariably an important factor of consideration for understanding the causality flow and parallel existence of articular cartilage and subchondral bone changes. The goal of this study was to investigate the patterns of subregional ¹⁸NaF-SUV vs. T_1p-T₂ associations and vertical ground reaction force loading rates; in isolated patellofemoral-joint-osteoarthritis (PFJ-OA) patients. Thirty-five isolated PFJ-OA patients, with no tibiofemoral involvement, underwent simultaneous scans in a 3.0T whole-body hybrid positron emission tomography-magnetic resonance imaging scanner. MRI Whole-Organ Magnetic Resonance Imaging Scoring assessments were performed to identify/confirm isolated PFJ-OA knees from bilateral scans. T_1p-T₂ relaxation and SUV values were automatically computed for both trochlear and patellar cartilage and subchondral bone subregions (deep, superficial, lateral, and medial). Maximum vertical impact loading rates (Loading-Rate_Norm) were calculated from walking trials. Relationships were explored between SUV uptake, T_1p-T₂ values, and Loading-Rate_Norm via linear mixed-effects modeling. Significant and complex association patterns were noted between medial and lateral bone ¹⁸NaF-SUV uptakes vs. medial and lateral cartilage sub-regional T_1p and T₂. SUV_Mean and SUV_Max were positively associated with deep cartilage subregional T_1pand T₂ values; and negatively associated with superficial cartilage subregional T_1p-T₂ values in both medial and lateral regions. Both medial and lateral bone ¹⁸NaF-SUV_Mean and SUV_Max uptakes remained positively associated with the individual gait characteristics, i.e., peak vertical impact loading rates (Loading-Rate_Norm). Evidence of simultaneous, complementary, cross-sectional associations between T_1p-T₂ values and peak vertical loading rates with ¹⁸NaF-SUV, have been rare in the isolated PFJ-OA cohort. The clinical implications of such novel associations remain of utmost importance from a gait retraining perspective.

Background: The polyarticular nature of Osteoarthritis (OA) tends to manifest in multi‐joints. Associations between cartilage health in connected joints can help identify early degeneration and offer the potential for biomechanical intervention. Such associations between hip and knee cartilages remain understudied.Purpose: To investigate T_1p associations between hip‐femoral and acetabular‐cartilage subregions with Intra‐limb and Inter‐limb patellar cartilage; whole and deep‐medial (DM), deep‐lateral (DL), superficial‐medial (SM), superficial‐lateral (SL) subregions.Study Type: Prospective.Subjects: Twenty‐eight subjects (age 55.1 ± 12.8 years, 15 females) with none‐to‐moderate hip‐OA while no radiographic knee‐OA.Field Strength/Sequence: 3‐T, bilateral hip, and knee: 3D‐proton‐density‐fat‐saturated (PDFS) Cube and Magnetization‐Prepared‐Angle‐Modulated‐Partitioned‐k‐Space‐Spoiled‐Gradient‐Echo‐Snapshots (MAPSS).Assessment: Ages of subjects were categorized into Group‐1 (≤40), Group‐2 (41–50), Group‐3 (51–60), Group‐4 (61–70), Group‐5 (71–80), and Group‐6 (≥81). Hip T_1p maps, co‐registered to Cube, underwent an atlas‐based algorithm to quantify femoral and acetabular subregional (R₂–R₇) cartilage T_1p. For knee Cube, a combination of V‐Net architectures was used to segment the patellar cartilage and subregions (DM, DL, SM, SL). T_1p values were computed from co‐registered MAPSS.Statistical Tests: For Intra‐and‐Inter‐limb, 5 optimum predictors out of 13 (Hip subregional T_1p, age group, gender) were selected by univariate linear‐regression, to predict outcome (patellar T_1p). The top five predictors were stepwise added to six linear mixed‐effect (LME) models. In all LME models, we assume the data come from the same subject sharing the same random effect. The best‐performing models (LME‐model_best) selected via ANOVA, were tested with DM, SM, SL, and DL subregional‐mean T_1p. LME assumptions were verified (normality of residuals, random‐effects, and posterior‐predictive‐checks).Results: LME‐model_best (Intra‐limb) had significant negative and positive fixed‐effects of femoral‐R₅ and acetabular‐R₂ T_1p, respectively (conditional‐R² = 0.581). LME‐model_best (Inter‐limb) had significant positive fixed‐effects of femoral‐R₃ T_1p (conditional‐R² = 0.26).Data Conclusion: Significant positive and negative T_1p associations were identified between load‐bearing hip cartilage‐subregions vs. ipsilateral and contralateral patellar cartilages respectively. The effects were localized on medial subregions of Inter‐limb, in particular.Evidence Level: 1Technical Efficacy: Stage 1

A 2D U-Net was trained to generate synthetic T_1p maps from T₂ maps for knee MRI to explore the feasibility of domain adaptation for enriching existing datasets and enabling rapid, reliable image reconstruction. The network was developed using 509 healthy contralateral and injured ipsilateral knee images from patients with ACL injuries and reconstruction surgeries acquired across three institutions. Network generalizability was evaluated on 343 knees acquired in a clinical setting and 46 knees from simultaneous bilateral acquisition in a research setting. The deep neural network synthesized high-fidelity reconstructions of T_1p maps, preserving textures and local T_1p elevation patterns in cartilage with a normalized mean square error of 2.4% and Pearson’s correlation coefficient of 0.93. Analysis of reconstructed T_1p maps within cartilage compartments revealed minimal bias (−0.10 ms), tight limits of agreement, and quantification error (5.7%) below the threshold for clinically significant change (6.42%) associated with osteoarthritis. In an out-of-distribution external test set, synthetic maps preserved T_1p textures, but exhibited increased bias and wider limits of agreement. This study demonstrates the capability of image synthesis to reduce acquisition time, derive meaningful information from existing datasets, and suggest a pathway for standardizing T_1p as a quantitative biomarker for osteoarthritis.