GA-HQS: MRI reconstruction via a generically accelerated unfolding approach

by   Jiawei Jiang, et al.

Deep unfolding networks (DUNs) are the foremost methods in the realm of compressed sensing MRI, as they can employ learnable networks to facilitate interpretable forward-inference operators. However, several daunting issues still exist, including the heavy dependency on the first-order optimization algorithms, the insufficient information fusion mechanisms, and the limitation of capturing long-range relationships. To address the issues, we propose a Generically Accelerated Half-Quadratic Splitting (GA-HQS) algorithm that incorporates second-order gradient information and pyramid attention modules for the delicate fusion of inputs at the pixel level. Moreover, a multi-scale split transformer is also designed to enhance the global feature representation. Comprehensive experiments demonstrate that our method surpasses previous ones on single-coil MRI acceleration tasks.


A Segmentation-aware Deep Fusion Network for Compressed Sensing MRI

Compressed sensing MRI is a classic inverse problem in the field of comp...

Compressed Sensing MRI via a Multi-scale Dilated Residual Convolution Network

Magnetic resonance imaging (MRI) reconstruction is an active inverse pro...

MCPA: Multi-scale Cross Perceptron Attention Network for 2D Medical Image Segmentation

The UNet architecture, based on Convolutional Neural Networks (CNN), has...

Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers

Supervised deep learning has swiftly become a workhorse for accelerated ...

SDLFormer: A Sparse and Dense Locality-enhanced Transformer for Accelerated MR Image Reconstruction

Transformers have emerged as viable alternatives to convolutional neural...

HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction

In accelerated MRI reconstruction, the anatomy of a patient is recovered...

Please sign up or login with your details

Forgot password? Click here to reset