Deep learning accelerates MR elastography imaging

Researchers have developed a novel deep-learning method to accelerate Magnetic Resonance (MR) elastography, enabling faster, high-resolution imaging from undersampled data. This approach frames the deep neural network as a nonlinear extension of linear subspace models, reconstructing MR elastography images from limited k-space data. The method incorporates phase-contrast specific priors and a multi-level k-space consistent loss, achieving comparable stiffness estimation to fully sampled data with significantly reduced scan times. AI

IMPACT This method could lead to faster and more detailed medical imaging, improving diagnostic capabilities.

RANK_REASON Research paper published on arXiv detailing a new method for MR elastography. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• neural network
• arXiv
• deep-learning
• MR elastography
• Xi Peng

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →