Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning

TL;DR

Patch2Self is a self-supervised learning method that denoises diffusion MRI data by leveraging the entire volume and oversampled q-space, improving microstructure analysis without explicit noise models.

Contribution

The paper introduces Patch2Self, a novel self-supervised denoising technique for diffusion MRI that does not require explicit noise modeling and utilizes the full data volume.

Findings

Significant noise reduction in DWI data.

Improved microstructure modeling and fiber tracking.

Outperforms existing unsupervised denoising methods.

Abstract

Diffusion-weighted magnetic resonance imaging (DWI) is the only noninvasive method for quantifying microstructure and reconstructing white-matter pathways in the living human brain. Fluctuations from multiple sources create significant additive noise in DWI data which must be suppressed before subsequent microstructure analysis. We introduce a self-supervised learning method for denoising DWI data, Patch2Self, which uses the entire volume to learn a full-rank locally linear denoiser for that volume. By taking advantage of the oversampled q-space of DWI data, Patch2Self can separate structure from noise without requiring an explicit model for either. We demonstrate the effectiveness of Patch2Self via quantitative and qualitative improvements in microstructure modeling, tracking (via fiber bundle coherency) and model estimation relative to other unsupervised methods on real and simulated data.