HIWDNet: A hybrid image-wavelet domain network for fast magnetic resonance image reconstruction

Article Biology

MR image reconstruction using densely connected residual convolutional networks

Amir Aghabiglou et al.

Summary: MRI image reconstruction techniques based on deep learning have shown great potential in reducing MRI acquisition time and improving performance compared to analytical methods. Despite challenges in training large networks, novel methodologies have enhanced the capability for real-time clinical-grade MR image reconstruction. The efficiency of deep networks can be improved by using short connections between layers, with studies showing significant improvements in reconstruction performance by introducing densely connected residual blocks in MRI reconstruction settings.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

添加到收藏夹

Article Biology

Transfer learning enhanced generative adversarial networks for multi-channel MRI reconstruction

Jun Lv et al.

Summary: This study explored novel applications based on transfer learning using parallel imaging combined with the GAN model (PI-GAN), showing that transfer learning on brain tumor datasets could remove artifacts and yield smoother brain edges. Transfer learning results for knee and liver datasets were superior to those of the PI-GAN model trained with fewer training samples, although the learning process was slower in knee datasets compared to brain tumor datasets. Transfer learning improved reconstruction performance in models with acceleration factors of 2 and 6, with the AF=2 model showing better results. Transfer learning with pre-trained models helped address inconsistencies between training and test datasets and facilitated generalization to unseen data.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

DONet: Dual-Octave Network for Fast MR Image Reconstruction

Chun-Mei Feng et al.

Summary: In this article, a novel dual-octave network (DONet) for parallel fast MR image reconstruction is proposed, which can learn multiscale spatial-frequency features from MR data to achieve efficient image reconstruction by encouraging information interaction and feature reuse between the real and imaginary components. Extensive experiments demonstrate the superiority of DONet in accelerated parallel MR image reconstruction under different undersampling patterns and acceleration factors.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

添加到收藏夹

Article Radiology, Nuclear Medicine & Medical Imaging