K-band: Self-supervised MRI Reconstruction via Stochastic Gradient Descent over K-space Subsets

arXiv:2308.02958v2 Announce Type: replace-cross
Abstract: Although deep learning (DL) methods are powerful for solving inverse problems, their reliance on high-quality training data is a major hurdle. This is significant in high-dimensional (dynamic/volumetric) magnetic resonance imaging (MRI), where acquisition of high-resolution fully sampled k-space data is impractical. We introduce a novel mathematical framework, dubbed k-band, that enables training DL models using only partial, limited-resolution k-space data. Specifically, we introduce training with stochastic gradient descent (SGD) over k-space subsets. In each training …

abstract acquisition arxiv cs.cv cs.lg data deep learning dynamic eess.iv eess.sp gradient imaging major mri physics.med-ph quality reliance resolution space stochastic subsets training training data type via