Quantitative MR evaluation of the infrapatellar fat pad for knee osteoarthritis: using proton density fat fraction and T2* relaxation based on DIXON.

OBJECTIVES: To investigate the efficacy of fat fraction (FF) and T2* relaxation based on DIXON in the assessment of infrapatellar fat pad (IFP) for knee osteoarthritis (KOA) progression in older adults. METHODS: Ninety volunteers (age range 51-70 years, 65 females) were enrolled in this study. Participants were grouped based on the Kellgren-Lawrence grading (KLG). The FF and T2* values were measured based on the 3D-modified DXION technique. Cartilage defects, bone marrow lesions, and synovitis were assessed based on a modified version of whole-organ magnetic resonance imaging score (WORMS). Knee pain was assessed by self-administered Western Ontario and McMaster Osteoarthritis Index (WOMAC) questionnaire. The differences of FF and T2* measurement and the correlation with WORMS and WOMAC assessments were analyzed. Diagnostic efficiency was analyzed by using receiver operating characteristic (ROC) curves. RESULTS: A total of 60 knees were finally included (n = 20 in each group). The values were 82.6 ± 3.7%, 74.7 ± 5.4%, and 60.5 ± 14.1% for FF is the no OA, mild OA, and advanced OA groups, and were 50.7 ± 6.6 ms, 44.1 ± 6.6 ms, and 39.1 ± 4.2 ms for T2*, respectively (all p values < 0.001). The WORMS assessment and WOMAC pain assessment showed negative correlation with FF and T2* values. The ROC showed the area under the curve (AUC), sensitivity, and specificity for diagnosing OA were 0.93, 77.5%, and 100% using FF, and were 0.86, 75.0%, and 90.0% using T2*, respectively. CONCLUSIONS: FF and T2* alternations in IFP are associated with knee structural abnormalities and clinical symptoms cross-sectionally and may have the potential to predict the severity of KOA. KEY POINTS: • Fat fraction (FF) and T2* relaxation based on DIXON imaging are novel methods to quantitatively assess the infrapatellar fat pad for knee osteoarthritis (KOA) progression in older adults. • The alterations of FF and T2* using mDIXON technique in IFP were associated with knee structural abnormalities and clinical symptoms. • FF and T2* alternations in IFP can serve as the new imaging biomarkers for fast, simple, and noninvasive assessment in KOA.

Fully automated radiomic screening pipeline for osteoporosis and abnormal bone density with a deep learning-based segmentation using a short lumbar mDixon sequence.

BACKGROUND: Although lumbar bone marrow fat fraction (BMFF) has been demonstrated to be predictive of osteoporosis, its utility is limited by the requirement of manual segmentation. Additionally, quantitative features beyond simple BMFF average remain to be explored. In this study, we developed a fully automated radiomic pipeline using deep learning-based segmentation to detect osteoporosis and abnormal bone density (ABD) using a <20 s modified Dixon (mDixon) sequence. METHODS: In total, 222 subjects underwent quantitative computed tomography (QCT) and lower back magnetic resonance imaging (MRI). Bone mineral density (BMD) were extracted from L1-L3 using QCT as the reference standard; 206 subjects (48.8±14.9 years old, 140 females) were included in the final analysis, and were divided temporally into the training/validation set (142/64 subjects). A deep-learning network was developed to perform automated segmentation. Radiomic models were built using the same training set to predict ABD and osteoporosis using the mDixon maps. The performance was evaluated using the temporal validation set comprised of 64 subjects, along with the automated segmentation. Additional 25 subjects (56.1±8.8 years, 14 females) from another site and a different scanner vendor was included as independent validation to evaluate the performance of the pipeline. RESULTS: The automated segmentation achieved an outstanding mean dice coefficient of 0.912±0.062 compared to manual in the temporal validation. Task-based evaluation was performed in the temporal validation set, for predicting ABD and osteoporosis, the area under the curve, sensitivity, specificity, and accuracy were 0.925/0.899, 0.923/0.667, 0.789/0.873, 0.844/0.844, respectively. These values were comparable to that of manual segmentation. External validation (cross-vendor) was also performed; the area under the curve, sensitivity, specificity, and accuracy were 0.688/0.913, 0.786/0.857, 0.545/0.944, 0.680/0.920 for ABD and osteoporosis prediction, respectively. CONCLUSIONS: Our work is the first attempt using radiomics to predict osteoporosis with BMFF map, and the deep-learning based segmentation will further facilitate the clinical utility of the pipeline as a screening tool for early detection of ABD.