FINDER: Zero-Shot Field-Integrated Network for Distortion-free EPI Reconstruction in Diffusion MRI

2026-03-27

AI Summary

This work proposes a zero-shot, scan-specific, end-to-end reconstruction framework to address geometric distortions in diffusion MRI caused by B₀ field inhomogeneities in echo-planar imaging (EPI). For the first time, it jointly optimizes image reconstruction and off-resonance field estimation within a self-supervised setting. The method employs a physics-guided unrolled network in conjunction with an implicit neural representation (INR) to model a continuously differentiable B₀ field, while an alternating minimization strategy decouples distortion from anatomical structure. Robustness is further enhanced through a dual-domain denoiser and virtual coil expansion. Experiments demonstrate that the proposed approach outperforms current state-of-the-art methods in both geometric fidelity and image quality, offering a reliable solution for high-quality diffusion MRI without requiring additional calibration data.

Abstract

Echo-planar imaging (EPI) remains the cornerstone of diffusion MRI, but it is prone to severe geometric distortions due to its rapid sampling scheme that renders the sequence highly sensitive to $B_{0}$ field inhomogeneities. While deep learning has helped improve MRI reconstruction, integrating robust geometric distortion correction into a self-supervised framework remains an unmet need. To address this, we present FINDER (Field-Integrated Network for Distortion-free EPI Reconstruction), a novel zero-shot, scan-specific framework that reformulates reconstruction as a joint optimization of the underlying image and the $B_{0}$ field map. Specifically, we employ a physics-guided unrolled network that integrates dual-domain denoisers and virtual coil extensions to enforce robust data consistency. This is coupled with an Implicit Neural Representation (INR) conditioned on spatial coordinates and latent image features to model the off-resonance field as a continuous, differentiable function. Employing an alternating minimization strategy, FINDER synergistically updates the reconstruction network and the field map, effectively disentangling susceptibility-induced geometric distortions from anatomical structures. Experimental results demonstrate that FINDER achieves superior geometric fidelity and image quality compared to state-of-the-art baselines, offering a robust solution for high-quality diffusion imaging.

Problem

• EPI distortion
• B0 field inhomogeneity
• diffusion MRI
• geometric distortion correction
• self-supervised reconstruction

Innovation

• zero-shot
• B0 field estimation
• implicit neural representation
• distortion correction
• physics-guided unrolled network