Dataset Information

Three-dimensional MRI Bone Models of the Glenohumeral Joint Using Deep Learning: Evaluation of Normal Anatomy and Glenoid Bone Loss.

ABSTRACT:

Purpose

To use convolutional neural networks (CNNs) for fully automated MRI segmentation of the glenohumeral joint and evaluate the accuracy of three-dimensional (3D) MRI models created with this method.

Materials and methods

Shoulder MR images of 100 patients (average age, 44 years; range, 14-80 years; 60 men) were retrospectively collected from September 2013 to August 2018. CNNs were used to develop a fully automated segmentation model for proton density-weighted images. Shoulder MR images from an additional 50 patients (mean age, 33 years; range, 16-65 years; 35 men) were retrospectively collected from May 2014 to April 2019 to create 3D MRI glenohumeral models by transfer learning using Dixon-based sequences. Two musculoskeletal radiologists performed measurements on fully and semiautomated segmented 3D MRI models to assess glenohumeral anatomy, glenoid bone loss (GBL), and their impact on treatment selection. Performance of the CNNs was evaluated using Dice similarity coefficient (DSC), sensitivity, precision, and surface-based distance measurements. Measurements were compared using matched-pairs Wilcoxon signed rank test.

Results

The two-dimensional CNN model for the humerus and glenoid achieved a DSC of 0.95 and 0.86, a precision of 95.5% and 87.5%, an average precision of 98.6% and 92.3%, and a sensitivity of 94.8% and 86.1%, respectively. The 3D CNN model, for the humerus and glenoid, achieved a DSC of 0.95 and 0.86, precision of 95.1% and 87.1%, an average precision of 98.7% and 91.9%, and a sensitivity of 94.9% and 85.6%, respectively. There was no difference between glenoid and humeral head width fully and semiautomated 3D model measurements (P value range, .097-.99).

Conclusion

CNNs could potentially be used in clinical practice to provide rapid and accurate 3D MRI glenohumeral bone models and GBL measurements. Supplemental material is available for this article. © RSNA, 2020.

SUBMITTER: Cantarelli Rodrigues T

PROVIDER: S-EPMC7529433 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PURPOSE:To describe and evaluate a new segmentation method using deep convolutional neural network (CNN), 3D fully connected conditional random field (CRF), and 3D simplex deformable modeling to improve the efficiency and accuracy of knee joint tissue segmentation. METHODS:A segmentation pipeline was built by combining a semantic segmentation CNN, 3D fully connected CRF, and 3D simplex deformable modeling. A convolutional encoder-decoder network was designed as the core of the segmentation method to perform high resolution pixel-wise multi-class tissue classification for 12 different joint structures. The 3D fully connected CRF was applied to regularize contextual relationship among voxels within the same tissue class and between different classes. The 3D simplex deformable modeling refined the output from 3D CRF to preserve the overall shape and maintain a desirable smooth surface for joint structures. The method was evaluated on 3D fast spin-echo (3D-FSE) MR image data sets. Quantitative morphological metrics were used to evaluate the accuracy and robustness of the method in comparison to the ground truth data. RESULTS:The proposed segmentation method provided good performance for segmenting all knee joint structures. There were 4 tissue types with high mean Dice coefficient above 0.9 including the femur, tibia, muscle, and other non-specified tissues. There were 7 tissue types with mean Dice coefficient between 0.8 and 0.9 including the femoral cartilage, tibial cartilage, patella, patellar cartilage, meniscus, quadriceps and patellar tendon, and infrapatellar fat pad. There was 1 tissue type with mean Dice coefficient between 0.7 and 0.8 for joint effusion and Baker's cyst. Most musculoskeletal tissues had a mean value of average symmetric surface distance below 1 mm. CONCLUSION:The combined CNN, 3D fully connected CRF, and 3D deformable modeling approach was well-suited for performing rapid and accurate comprehensive tissue segmentation of the knee joint. The deep learning-based segmentation method has promising potential applications in musculoskeletal imaging.

Project description:PurposeTo compare the efficacy of a single, intra-articular, nonconcentrated bone marrow aspirate (BMA) injection in comparison to cortisone for the treatment of glenohumeral joint osteoarthritis (GHJ OA).MethodsInclusion criteria were patients between the ages of 18 and 75 with a diagnosis of GHJ OA on radiograph. Patients were randomized to receive an ultrasound-guided, intra-articular cortisone injection or BMA injection (without concentration). The primary outcome measure was the Western Ontario Osteoarthritis of the Shoulder (WOOS) index at 12 months. Secondary outcome measures were the QuickDASH, EuroQOL 5-dimensions 5-level questionnaire (EQ-5D-5L) and visual analogue scale.ResultsThe study included 25 shoulders of 22 patients who completed baseline and 12 months' patient-reported outcome measures (12 shoulders received cortisone, 13 shoulders received BMA) after the study was terminated early by changes in Health Canada regulations. Baseline characteristics demonstrated a significant difference in the ages of the 2 groups, with the BMA group being older (61.6 vs 53.8 mean years, P = 0.021). For the BMA group, a significant improvement was seen in the WOOS index (P = 0.002), the QuickDASH (P < 0.001), and the EQ-5D-5L pain dimension (P = 0.004) between baseline and 12 months. No significant difference was seen for any outcome in the cortisone group between baseline and 12 months. No significant difference was demonstrated between changes in the WOOS scores from baseline to 12 months when compared between groups (P = 0.07). However, a significant difference in changes in scores was seen in the QuickDASH (P = 0.006) and the EQ-5D-5L pain scores (P = 0.003) and the EQ-5D-5L health scores (P = 0.032) in favor of BMA.ConclusionsThe results of this study demonstrate that patients with GHJ OA treated with BMA have superior changes in the QuickDASH and EQ-5D-5L pain and health scores but not in the WOOS outcomes measures at 12 months post injection when compared to patients treated with cortisone. However, because of the limited number of patients as a result of the early termination of the study, larger randomized studies are required to confirm these findings.Level of evidenceLevel II, randomized controlled trial.