Clinical routine and retrospective cohorts commonly include multi-parametric Magnetic Resonance Imaging; however, they are mostly acquired in different anisotropic 2D views due to signal-to-noise-ratio and scan-time constraints. Thus acquired views suffer from poor out-of-plane resolution and affect downstream volumetric image analysis that typically requires isotropic 3D scans. Combining different views of multi-contrast scans into high-resolution isotropic 3D scans is challenging due to the lack of a large training cohort, which calls for a subject-specific framework. This work proposes a novel solution to this problem leveraging Implicit Neural Representations (INR). Our proposed INR jointly learns two different contrasts of complementary views in a continuous spatial function and benefits from exchanging anatomical information between them. Trained within minutes on a single commodity GPU, our model provides realistic super-resolution across different pairs of contrasts in our experiments with three datasets. Using Mutual Information (MI) as a metric, we find that our model converges to an optimum MI amongst sequences, achieving anatomically faithful reconstruction. Code is available at: https://github.com/jqmcginnis/multi_contrast_inr/
@article{arxiv.2303.15065,
title = {Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations},
author = {Julian McGinnis and Suprosanna Shit and Hongwei Bran Li and Vasiliki Sideri-Lampretsa and Robert Graf and Maik Dannecker and Jiazhen Pan and Nil Stolt Ansó and Mark Mühlau and Jan S. Kirschke and Daniel Rueckert and Benedikt Wiestler},
journal= {arXiv preprint arXiv:2303.15065},
year = {2024}
}