Multi-modal Latent-Space Self-alignment for Super-Resolution Cardiac MR Segmentation

Stat Atlases Comput Models Heart. 2022 Sep:13593:26-35. doi: 10.1007/978-3-031-23443-9_3. Epub 2023 Jan 28.

Abstract

2D cardiac MR cine images provide data with a high signal-to-noise ratio for the segmentation and reconstruction of the heart. These images are frequently used in clinical practice and research. However, the segments have low resolution in the through-plane direction, and standard interpolation methods are unable to improve resolution and precision. We proposed an end-to-end pipeline for producing high-resolution segments from 2D MR images. This pipeline utilised a bilateral optical flow warping method to recover images in the through-plane direction, while a SegResNet automatically generated segments of the left and right ventricles. A multi-modal latent-space self-alignment network was implemented to guarantee that the segments maintain an anatomical prior derived from unpaired 3D high-resolution CT scans. On 3D MR angiograms, the trained pipeline produced high-resolution segments that preserve an anatomical prior derived from patients with various cardiovascular diseases.

Keywords: CT angiogram; Cardiac MR; Domain adaptation; Super-resolution segmentation; VAE.