Deep learning algorithms enable MRI-based scapular morphology analysis with values comparable to CT-based assessments.

Scapular morphological attributes show promise as prognostic indicators of retear following rotator cuff repair. Current evaluation techniques using single-slice magnetic-resonance imaging (MRI) are, however, prone to error, while more accurate computed tomography (CT)-based three-dimensional techniques, are limited by cost and radiation exposure. In this study we propose deep learning-based methods that enable automatic scapular morphological analysis from diagnostic MRI despite the anisotropic resolution and reduced field of view, compared to CT. A deep learning-based segmentation network was trained with paired CT derived scapula segmentations. An algorithm to fuse multi-plane segmentations was developed to generated high-resolution 3D models of the scapula on which morphological landmark- and axes were predicted using a second deep learning network for morphological analysis. Using the proposed methods, the critical shoulder angle, glenoid inclination and version were measured from MRI with accuracies of -1.3 ± 1.7 degrees, 1.3 ± 2.1 degree, and - 1.4 ± 3.4 degrees respectively, compared to CT. Inter-class correlation between MRI and CT derived metrics were substantial for the glenoid version and almost perfect for the other metrics. This study demonstrates how deep learning can overcome reduced resolution, bone border contrast and field of view, to enable 3D scapular morphology analysis on MRI.