Search papers, labs, and topics across Lattice.
The paper introduces SIINR, a novel framework that enhances the resolution of clinical diffusion MRI datasets while providing uncertainty quantification in the reconstructed images. By integrating a supervised 3D U-net with a self-supervised implicit neural representation, SIINR effectively combines high-resolution priors with low-resolution data, enabling improved structural fidelity and analytic posterior distributions for uncertainty assessment. Validation on diverse dMRI datasets shows that SIINR significantly outperforms traditional interpolation methods, particularly in clinical scenarios involving complex conditions like multiple sclerosis and brain lesions.
SIINR not only super-resolves clinical dMRI images but also quantifies uncertainty, offering a game-changing approach for neuroimaging analysis.
Diffusion Magnetic Resonance Imaging (dMRI) is a powerful tool for probing brain microstructure, but clinical acquisitions are often limited by low out-of-plane resolution, resulting in degraded structural information and reduced utility for advanced analysis. We introduce SIINR (Structurally Informed Implicit Neural Representations), a general framework for super-resoltion of clinical dMRI datasets while quantifying uncertainty in the reconstructed outputs. SIINR utilizes a supervised 3D U-net as a prior and combines it with a self-supervised implicit neural representation (INR) that fuses the high-resolution prior and the original low-resolution data. The INR enables joint modeling across spatial and angular domains, enforces data consistency, and provides analytic approximate posterior distributions for downstream uncertainty quantification. We validate the framework on a diverse set of open-access dMRI datasets, demonstrating that SIINR outperforms standard interpolation methods in both quantitative error metrics and qualitative anatomical fidelity. Experiments on clinical cases, including subjects with multiple sclerosis and brain lesions, illustrate the framework its ability to propagate intensity changes and flag uncertain regions in challenging scenarios. SIINR is flexible, modular, and can be adapted to different upsampling ratios and downstream tasks, providing a principled approach for enhancing clinical dMRI and supporting robust interpretation of derived neuroimaging metrics.
