DMSM proposes a self-supervised dual-domain multi-path diffusion framework for accelerated MRI reconstruction that removes the need for fully sampled training data while providing uncertainty maps.
Complex fully convolutional neural networks for mr image reconstruction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstruction
DMSM proposes a self-supervised dual-domain multi-path diffusion framework for accelerated MRI reconstruction that removes the need for fully sampled training data while providing uncertainty maps.