Deep learning segmentation of orbital fat to calibrate conventional MRI for longitudinal studies

Publication date: Available online 9 December 2019Source: NeuroImageAuthor(s): Robert A. Brown, Dumitru Fetco, Robert Fratila, Giulia Fadda, Shangge Jiang, Nuha M. Alkhawajah, E. Ann Yeh, Brenda Banwell, Amit Bar-Or, Douglas L. Arnold, Canadian Pediatric Demyelinating Disease NetworkAbstractIn conventional non-quantitative magnetic resonance imaging, image contrast is consistent within images, but absolute intensity can vary arbitrarily between scans. For quantitative analysis of intensity data, images are typically normalized to a consistent reference. The most convenient reference is a tissue that is always present in the image, and is unlikely to be affected by pathological processes. In multiple sclerosis neuroimaging, both the white and gray matter are affected, so normalization techniques that depend on brain tissue may introduce bias or remove biological changes of interest. We introduce a complementary procedure, image “calibration,” the goal of which is to remove technical intensity artifacts while preserving biological differences. We demonstrate a deep learning approach to segmenting fat from within the orbit of the eyes on T1-weighted images at 1.5 and 3 T to use as a reference tissue, and use it to calibrate 1018 scans from 256 participants in a study of pediatric-onset multiple sclerosis. The machine segmentations agreed with the adjudicating expert (DF) segmentations better than did those of other expert humans, and calibration resulted in better agreemen...
Source: NeuroImage - Category: Neuroscience Source Type: research