Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations
This addresses the need for improved volumetric image analysis in clinical and retrospective MRI cohorts, though it is incremental as it applies an existing INR method to a specific medical imaging bottleneck.
The paper tackles the problem of generating high-resolution isotropic 3D MRI scans from anisotropic 2D multi-contrast views by proposing a subject-specific framework using Implicit Neural Representations (INR), which trains in minutes on a single GPU and achieves anatomically faithful reconstruction as measured by Mutual Information.
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/