GRAPPA-GANs for Parallel MRI Reconstruction
arXiv:2101.03135
Abstract
k-space undersampling is a standard technique to accelerate MR image acquisitions. Reconstruction techniques including GeneRalized Autocalibrating Partial Parallel Acquisition(GRAPPA) and its variants are utilized extensively in clinical and research settings. A reconstruction model combining GRAPPA with a conditional generative adversarial network (GAN) was developed and tested on multi-coil human brain images from the fastMRI dataset. For various acceleration rates, GAN and GRAPPA reconstructions were compared in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). For an acceleration rate of R=4, PSNR improved from 33.88 using regularized GRAPPA to 37.65 using GAN. GAN consistently outperformed GRAPPA for various acceleration rates.
References in corpus (6)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
- Natural Language Processing Advancements By Deep Learning: A Survey
- Design and Implementation of a Maxi-Sized Mobile Robot (Karo) for Rescue Missions
- Analysis and Control of Fiber-Reinforced Elastomeric Enclosures (FREEs)
- Attention-Guided Generative Adversarial Network to Address Atypical Anatomy in Modality Transfer