PulseAugur
EN
LIVE 06:30:50

New deep-learning framework Eddeep speeds up MRI distortion correction

Researchers have developed Eddeep, a novel deep-learning framework designed to rapidly correct geometric distortions in diffusion MRI (dMRI) data. These distortions, caused by eddy currents, can significantly impact the accuracy of downstream microstructural analyses. Eddeep employs a two-stage process: an image translation network to standardize image appearance and an unsupervised registration network to estimate distortion and motion parameters. This approach achieves correction quality comparable to existing methods like FSL Eddy but with a substantial reduction in processing time, making it suitable for large-scale studies and clinical applications. AI

IMPACT Accelerates processing for large-scale diffusion MRI studies and clinical deployment by enabling faster, accurate distortion correction.

RANK_REASON Publication of a research paper detailing a new deep-learning framework for a specific scientific application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

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

New deep-learning framework Eddeep speeds up MRI distortion correction

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Antoine Legouhy, Ross Callaghan, Yuchuan Qiao, Whitney Stee, Philippe Peigneux, Hojjat Azadbakht, Hui Zhang ·

    Eddeep: a deep-learning framework for fast eddy-current distortion correction in diffusion MRI

    arXiv:2607.26292v1 Announce Type: new Abstract: Diffusion MRI (dMRI) relies on diffusion-weighted echo-planar imaging, which is highly susceptible to eddy-current-induced geometric distortions. These distortions vary across diffusion volumes according to gradient strength and dir…