Coil-Agnostic Attention-Based Network for Parallel MRI Reconstruction

Jingshuai Liu, Chen Qin, Mehrdad Yaghoobi Vaighan

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Magnetic resonance imaging (MRI) is widely used in clinical diagnosis. However, as a slow imaging modality, the long scan time hinders its development in time-critical applications. The acquisition process can be accelerated by types of under-sampling strategies in k-space and reconstructing images from a few measurements. To reconstruct the image, many parallel imaging methods use the coil sensitivity maps to fold multiple coil images with model-based or deep learning-based estimation methods. However, they can potentially suffer from the inaccuracy of sensitivity estimation. In this work, we propose a novel coil-agnostic attention-based framework for multi-coil MRI reconstruction which completely avoids the sensitivity estimation and performs data consistency (DC) via a sensitivity-agnostic data aggregation consistency block (DACB). Experiments were performed on the FastMRI knee dataset and show that the proposed DACB and attention module-integrated framework outperforms other deep learning-based algorithms in terms of image quality and reconstruction accuracy. Ablation studies also indicate the superiority of DACB over conventional DC methods.
Original languageEnglish
Title of host publicationComputer Vision – ACCV 2022
Subtitle of host publication16th Asian Conference on Computer Vision, Macao, China, December 4–8, 2022, Proceedings, Part VI
ISBN (Electronic)978-3-031-26351-4
ISBN (Print)978-3-031-26350-7
Publication statusPublished - 26 Feb 2023
EventThe 16th Asian Conference on Computer Vision - Macau, China
Duration: 4 Dec 20228 Dec 2022

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceThe 16th Asian Conference on Computer Vision
Abbreviated titleACCV2022
Internet address


  • MRI Reconstruction
  • coil agnostic
  • Attention network


Dive into the research topics of 'Coil-Agnostic Attention-Based Network for Parallel MRI Reconstruction'. Together they form a unique fingerprint.

Cite this