SIINR: Structurally Informed Implicit Neural Representations for super-resolution with uncertainty quantification of clinical quality diffusion MRI datasets

2026-07-22

AI Summary

Clinical diffusion MRI (dMRI) often suffers from degraded structural fidelity due to low through-plane resolution, compromising the reliability of downstream analyses. To address this, this work proposes SIINR, a novel framework that uniquely integrates a supervised 3D U-Net structural prior with self-supervised implicit neural representations (INRs) to achieve super-resolution reconstruction in the joint spatial-angular domain. The method enables approximation of the posterior distribution for uncertainty quantification while rigorously enforcing data consistency. Extensive experiments on multiple public dMRI datasets and clinical cases of multiple sclerosis demonstrate that SIINR substantially outperforms conventional interpolation techniques, yielding consistent improvements in quantitative metrics, anatomical fidelity, and identification of uncertain regions.

Abstract

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.

Problem

• diffusion MRI
• super-resolution
• low resolution
• structural information
• clinical imaging

Innovation

• Implicit Neural Representation
• Super-resolution
• Uncertainty Quantification
• Diffusion MRI
• Data Consistency