Seeking Common Ground While Reserving Differences: Multiple Anatomy Collaborative Framework for Undersampled MRI Reconstruction

06/15/2022
by   Jiangpeng Yan, et al.
0

Recently, deep neural networks have greatly advanced undersampled Magnetic Resonance Image (MRI) reconstruction, wherein most studies follow the one-anatomy-one-network fashion, i.e., each expert network is trained and evaluated for a specific anatomy. Apart from inefficiency in training multiple independent models, such convention ignores the shared de-aliasing knowledge across various anatomies which can benefit each other. To explore the shared knowledge, one naive way is to combine all the data from various anatomies to train an all-round network. Unfortunately, despite the existence of the shared de-aliasing knowledge, we reveal that the exclusive knowledge across different anatomies can deteriorate specific reconstruction targets, yielding overall performance degradation. Observing this, in this study, we present a novel deep MRI reconstruction framework with both anatomy-shared and anatomy-specific parameterized learners, aiming to "seek common ground while reserving differences" across different anatomies.Particularly, the primary anatomy-shared learners are exposed to different anatomies to model flourishing shared knowledge, while the efficient anatomy-specific learners are trained with their target anatomy for exclusive knowledge. Four different implementations of anatomy-specific learners are presented and explored on the top of our framework in two MRI reconstruction networks. Comprehensive experiments on brain, knee and cardiac MRI datasets demonstrate that three of these learners are able to enhance reconstruction performance via multiple anatomy collaborative learning.

READ FULL TEXT

page 1

page 2

page 4

page 7

page 8

research
04/05/2022

Learning Optimal K-space Acquisition and Reconstruction using Physics-Informed Neural Networks

The inherent slow imaging speed of Magnetic Resonance Image (MRI) has sp...
research
03/09/2021

Universal Undersampled MRI Reconstruction

Deep neural networks have been extensively studied for undersampled MRI ...
research
10/15/2020

XPDNet for MRI Reconstruction: an Application to the fastMRI 2020 Brain Challenge

We present a modular cross-domain neural network the XPDNet and its appl...
research
03/07/2022

Undersampled MRI Reconstruction with Side Information-Guided Normalisation

Magnetic resonance (MR) images exhibit various contrasts and appearances...
research
01/14/2019

Self-Supervised Deep Active Accelerated MRI

We propose to simultaneously learn to sample and reconstruct magnetic re...
research
04/13/2023

Generalizable Deep Learning Method for Suppressing Unseen and Multiple MRI Artifacts Using Meta-learning

Magnetic Resonance (MR) images suffer from various types of artifacts du...
research
05/25/2023

Constrained Probabilistic Mask Learning for Task-specific Undersampled MRI Reconstruction

Undersampling is a common method in Magnetic Resonance Imaging (MRI) to ...

Please sign up or login with your details

Forgot password? Click here to reset