A semi‐automatic framework based upon quantitative analysis of MR‐images for classification of femur cartilage into asymptomatic, early OA, and advanced‐OA groups. Issue 4 (8th June 2021)

• Record Type: Journal Article
• Authors: Thaha, Rafeek; Jogi, Sandeep P.; Rajan, Sriram; Mahajan, Vidur; Mehndiratta, Amit; Singh, Anup
• Is Part Of: Journal of orthopaedic research. Volume 40:Issue 4(2022)
• Page Start: 779
• Page End: 790
• Publication Date: 2021-06-08
• Subjects: cartilage degeneration -- cartilage thickness -- osteoarthritis -- quantitative MRI -- T2 relaxation time; Orthopedics -- Periodicals; Musculoskeletal system -- Periodicals; 616.7
• DOI: 10.1002/jor.25109
• Languages: English
• ISSNs: 0736-0266

Abstract

Abstract: To develop a semi‐automatic framework for quantitative analysis of biochemical properties and thickness of femur cartilage using magnetic resonance (MR) images and evaluate its potential for femur cartilage classification into asymptomatic (AS), early osteoarthritis (OA), and advanced OA groups. In this study, knee joint MRI data (fat suppressed‐proton density‐weighted and multi‐echo T2‐weighted images) of eight AS‐volunteers (data acquired twice) and 34 OA patients including 20 early OA (16 Grade‐I and 4 Grade‐II), 14 advanced‐OA (Grade‐III) were acquired at 3.0T MR scanner. Modified Outerbridge classification criteria was performed for the clinical evaluation of data by an experienced radiologist. Cartilage segmentation, T2‐mapping, 2D‐WearMap generation, and subregion analysis were performed semi‐automatically using in‐house developed algorithms. The intraclass correlation coefficient (ICC) and coefficient of variation (CV) were computed for testing the reproducibility of T2 values. One‐way analysis of variance with Tukey–Kramer post hoc test was performed for evaluating the differences among the groups. The performance of individual T2 and thickness, as well as their combination using logistic regression, were evaluated with receiver operating characteristics (ROC) curve analysis. The interscan agreement based on the ICC index was 0.95 and the CV was 2.45 ± 1.33%. T2 mean of values greater than 75th percentile showed sensitivity and specificity of 94.1% and 81.3% (AUC = 0.93, cut‐off value = 47.9 ms) in differentiating AS volunteers versus OA group, while sensitivity and specificity of 90.0% and 81.3% (AUC = 0.90, cut‐off value = 47.9 ms) in differentiating AS volunteers versus early OA groups, respectively. In the differentiation of early OA versus advanced‐OA group, ROC results of combination (T2 and thickness) showed the highest sensitivity and specificity of 85.7%, and 70.0% (AUC = 0.79, cut‐off value = 0.39) compared with individual T2 and thickness features, respectively. A computer‐aided quantitative evaluation of femur cartilage degeneration showed promising results and can be used to assist clinicians in diagnosing OA. Abstract : A framework for femur articular cartilage segmentation, 2D‐WearMap generation, and subregion region of interest selection on knee joint magnetic resonance images was implemented for the quantitative analysis using in‐house developed algorithms. A logistic regression classifier based on combined features (T2 mean of greater than 90th percentile values and normalized mean thickness of value less than 10th percentile) of cartilage demonstrated the highest AUC, sensitivity, and specificity between early OA and advanced‐OA group, particularly in the trochlear and central medial femur subregion.