Regularization by Neural Style Transfer for MRI Field-Transfer Reconstruction with Limited Data

TL;DR

This paper introduces RNST, a novel MRI reconstruction framework that combines neural style transfer and denoising to produce high-quality images from limited data without needing paired training samples.

Contribution

RNST is the first method to integrate neural style transfer with denoising for MRI reconstruction, enabling high-quality, data-efficient field-transfer imaging without paired datasets.

Findings

RNST outperforms traditional methods in image clarity and contrast.

RNST maintains robustness even with unaligned style and content images.

RNST effectively reconstructs images across various anatomical planes and noise levels.

Abstract

Recent advances in MRI reconstruction have demonstrated remarkable success through deep learning-based models. However, most existing methods rely heavily on large-scale, task-specific datasets, making reconstruction in data-limited settings a critical yet underexplored challenge. While regularization by denoising (RED) leverages denoisers as priors for reconstruction, we propose Regularization by Neural Style Transfer (RNST), a novel framework that integrates a neural style transfer (NST) engine with a denoiser to enable magnetic field-transfer reconstruction. RNST generates high-field-quality images from low-field inputs without requiring paired training data, leveraging style priors to address limited-data settings. Our experiment results demonstrate RNST's ability to reconstruct high-quality images across diverse anatomical planes (axial, coronal, sagittal) and noise levels, achieving superior clarity, contrast, and structural fidelity compared to lower-field references. Crucially, RNST maintains robustness even when style and content images lack exact alignment, broadening its applicability in clinical environments where precise reference matches are unavailable. By combining the strengths of NST and denoising, RNST offers a scalable, data-efficient solution for MRI field-transfer reconstruction, demonstrating significant potential for resource-limited settings.