Auto-encoding of discriminating morphometry from cardiac MRI

We propose a fully-automatic morphometric encoding targeted towards differentiating diseased from healthy cardiac MRI. Existing encodings rely on accurate segmentations of each scan. Segmentation generally includes labour-intensive editing and increases the risk associated with intra- and inter-rater variability. Our morphometric framework only requires the segmentation of a template scan. This template is non-rigidly registered to the other scans. We then confine the resulting deformation maps to the regions outlined by the segmentations. We learn a manifold for each region and identify the most informative coordinates with respect to distinguishing diseased from healthy scans. Compared with volumetric measurements and a deformation-based score, this encoding is much more accurate in capturing morphome-tric patterns distinguishing healthy subjects from those with Tetralogy of Fallot, diastolic dysfunction, and hypertrophic cardiomyopathy.