Abstract
4D Flow MRI provides quantitative cardiac phase resolved hemodynamic assessment, however its clinical use remains limited due to long scan times. In this work, we train an unrolled deep learning network on a large dataset for 4D Flow MRI reconstruction. Our approach leverages complex convolutional blocks for improved phase reconstruction fidelity. Our models use feature-sharing across the velocity encode, cardiac phase, and slice dimension and use ACS-free sensitivity map estimation networks yielding impressive reconstruction results up to 50× acceleration factor.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/CMRxRecon2026_014.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=dt1MFO7N7c
BibTex
@InProceedings{MacAle_Spatiotemporal_MICCAISAT2026,
author = { Macintyre, Alex AND Ma, Lingceng AND Christodoulou, Anthony G.},
title = { { Spatiotemporal Context-Informed Unrolled Complex Reconstruction Networks for 4D Flow MRI } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17267},
month = {pending},
page = {pending}
}