Meeting Banner
Abstract #3947

Super-resolution reconstruction of 4D neonatal cardiac MRI using coupled dictionary learning

Kanwal K Bhatia 1 , Anthony N Price 2 , David Cox 2 , Alan M Groves 2 , Jo V Hajnal 2 , and Daniel Rueckert 1

1 Biomedical Image Analysis Group, Imperial College London, London, London, United Kingdom, 2 Division of Imaging Sciences and Biomedical Engineering, King's College London, London, United Kingdom

We present a novel method for image enhancement of 4D neonatal cardiac MRI using example-based super-resolution reconstruction. Anisotropic, orthogonal cine stacks are acquired covering the cardiac volume. By considering small image patches within these acquisitions, we are able to exploit the inherent redundancy of these data. These are used to learn coupled dictionaries of corresponding high-resolution and low-resolution patches. These dictionaries are then used to upsample the low-resolution view of the acquired stack to isotropic. We apply the algorithm to super-resolve 4D images from six neonates showing improvement over standard bicubic interpolation.

This abstract and the presentation materials are available to members only; a login is required.

Join Here