Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator

349 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep ADMM-Net for Compressive Sensing MRI (2016, methodology): “For the sampling ratio of 30%, our method (ADMMNet15) outperforms the state-of-the-art methods PANO and FDLCP by 0.71 db.”
KIKI‐net: cross‐domain convolutional neural networks for reconstructing undersampled magnetic resonance images (2018, methodology): “…7 conventional algorithms: baseline zero-filling, CS-MRI, 4 DL-MRI, 14 block-matching and 3D filtering (BM3D) MRI, 36 a CNN-based algorithm by Wang et al 19 (denoted as Wang ’ s algorithm), PANO (patch-based nonlocal operator), 18 and FDLCP (fast dictionary learning method on classified patches).”
ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing (2020, methodology): “For CS-MRI, ADMM-CSNet achieved comparable reconstruction accuracy in PSNR/SSIM using nearly 10 percent less sampled measurements and around 45 times speed-up in running time, comparedwith the traditional state-of-the-art CS-MRI methods, such as PBDW [18], PANO [14].”
Artifact Suppressed Dictionary Learning for Low-Dose CT Image Processing (2014, methodology): “So, future work in this line will include: 1) parallelizing the OMP computation in the proposed processing with GPU technique, 2) incorporating the ASDL processing into recent noiseweighted FBP reconstruction in [45], [46] in order to face very severe artifacts, 3) extending and testing the applicat”