Learned Primal Dual Splitting for Self-Supervised Noise-Adaptive MRI Reconstruction

Abstract

Magnetic resonance imaging (MRI) reconstruction has largely been dominated by deep neural networks (DNN); however, many state-of-the-art architectures use black-box structures, which hinder interpretability and improvement. Here, we propose an interpretable DNN architecture for self-supervised MRI reconstruction and denoising by directly parameterizing and learning the classical primal-dual splitting, dubbed LPDSNet. This splitting algorithm allows us to decouple the observation model from the signal prior. Experimentally, we show other interpretable architectures without this decoupling property exhibit failure in the self-supervised learning regime. We report state-of-the-art self-supervised joint MRI reconstruction and denoising performance and novel noise-level generalization capabilities, where in contrast black-box networks fail to generalize.

4 pages, 3 figures, 1 table

References in corpus (5)

• Learned Primal-dual Reconstruction
• Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference Data
• CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing
• GroupCDL: Interpretable Denoising and Compressed Sensing MRI via Learned Group-Sparsity and Circulant Attention
• Gabor is Enough: Interpretable Deep Denoising with a Gabor Synthesis Dictionary Prior

Cited by in corpus (1)

• Self-Supervised Noise Adaptive MRI Denoising via Repetition to Repetition (Rep2Rep) Learning