Key result
Automated bone segmentation using a statistical shape model achieved mean Dice similarity coefficients of 0.926 for the humerus and 0.837 for the scapula compared to manual segmentation.
A statistical shape model approach successfully provided automated bone segmentation and bone-cartilage interface extraction from shoulder MR images, showing high agreement with manual segmentation.
Answers are grounded in this paper and cite their sources.
May streamline shoulder MRI analysis; leaves open clinical adoption pending outcome validation.
We present a statistical shape model approach for automated segmentation of the proximal humerus and scapula with subsequent bone-cartilage interface (BCI) extraction from 3D magnetic resonance (MR) images of the shoulder region. Manual and automated bone segmentations from shoulder MR examinations from 25 healthy subjects acquired using steady-state free precession sequences were compared with the Dice similarity coefficient (DSC). The mean DSC scores between the manual and automated segmentations of the humerus and scapula bone volumes surrounding the BCI region were 0.926 ± 0.050 and 0.837 ± 0.059, respectively. The mean DSC values obtained for BCI extraction were 0.806 ± 0.133 for the humerus and 0.795 ± 0.117 for the scapula. The current model-based approach successfully provided automated bone segmentation and BCI extraction from MR images of the shoulder. In future work, this framework appears to provide a promising avenue for automated segmentation and quantitative analysis of cartilage in the glenohumeral joint.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2015) studied Healthy subjects (n=25). Automated statistical shape model approach vs. Manual segmentation was evaluated on Dice similarity coefficient (DSC) between manual and automated segmentations. Automated bone segmentation using a statistical shape model achieved mean Dice similarity coefficients of 0.926 for the humerus and 0.837 for the scapula compared to manual segmentation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: