Learned k-space Partitioning for Optimized Self-Supervised MRI Reconstruction

Self-supervised magnetic resonance imaging (MRI) reconstruction methods train deep learning networks without the need for fully sampled reference data. One such approach, self-supervised via data under-sampling (SSDU), partitions under-sampled k-space into two disjoint sets, with a neural network mapping between them. However, SSDU and its variants rely on heuristic k-space partitioning, which may lead to suboptimal performance and necessitates new partitioning schemes when initial under-sampling patterns change. In this work, we propose a novel approach to learn optimal k-space partitioning by modeling a probability distribution which we use for partitioning. Specifically, we employ the LOUPE framework to learn an optimal partitioning probability distribution. Furthermore, we introduce a weighted dual-domain self-supervised loss function that incorporates both k-space and image-space loss terms. Evaluations on the fastMRI dataset demonstrate that our dual-domain learned partitioning method outperforms existing partitioning strategies and adapts to new sampling patterns without requiring hand-picked partitioning methods.Clinical Relevance- Typical clinical MRI protocols are under-sampled and reconstructed using parallel imaging. Self-supervised reconstruction can train directly on under-sampled clinical data, eliminating the need for separately acquired fully sampled datasets.