Quantitative Assessment of the Whole Spine in T2 MRI Using Deep Learning

We present a fully automatic system for the quantitative assessment of discs and vertebrae using convolutional neural networks. The proposed algorithm works in three stages: 1) segmentation/identification of spinal anatomy; 2) curvature analysis; and 3) detection of pathological conditions of intervertebral discs. We validate the proposed approach on a large dataset of 1,500 subjects with sagittal T2-weighted whole spine MRI, obtained as part of a whole body MRI protocol in a preventative health screening program.