PulseAugur
EN
LIVE 09:24:26

New AI reconstructs high-res dMRI from single views

Researchers have developed a self-supervised Spatial-Angular Implicit Neural Representation (SA-INR) to accelerate diffusion MRI (dMRI) scans. This new method can reconstruct high-resolution dMRI from a single view per diffusion direction, significantly reducing scan times. The SA-INR framework not only achieves accurate spatial super-resolution but also enables zero-shot synthesis of unseen b-directions, improving quantitative accuracy in downstream modeling. AI

IMPACT Accelerates dMRI acquisition and improves quantitative accuracy for downstream analysis.

RANK_REASON Academic paper detailing a novel AI method for medical imaging reconstruction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Hugging Face Daily Papers →

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

New AI reconstructs high-res dMRI from single views

COVERAGE [1]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Self-Supervised Spatial And Zero-Shot Angular Super-Resolution by Spatial-Angular Implicit Representation For Rotating-View SNR-Efficient Diffusion MRI

    Rotating-view thick-slice acquisition is highly SNR-efficient for mesoscale diffusion MRI (dMRI) but requires numerous rotating views to satisfy Nyquist sampling, resulting in long scan time. We propose a self-supervised Spatial-Angular Implicit Neural Representation (SA-INR) tha…