Second order total generalized variation (TGV) for MRI

By Florian Knoll, Kristian Bredies, Thomas Pock, Rudolf Stollberger. Magnetic Resonance in Medicine, 2011

630 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/0dc15e00674f97efa28d6d49aefb21e959874e44

How researchers see this paper

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

In Computational Mechanics

1. Carola-Bibiane Schönlieb
2. Tuomo Valkonen
3. J. D. L. Reyes
4. Florian Knoll
5. Daniel K. Sodickson
6. Kerstin Hammernik
7. Luca Calatroni
8. Cao Van Chung

In Computer Vision and Pattern Recognition

1. Carola-Bibiane Schönlieb
2. Tuomo Valkonen
3. J. D. L. Reyes
4. Florian Knoll
5. Luca Calatroni
6. Cao Van Chung
7. Daniel K. Sodickson
8. Kerstin Hammernik

In Radiology, Nuclear Medicine and Imaging

1. Daan Christiaens
2. Carola-Bibiane Schönlieb
3. Steen Moeller
4. Mehmet Akçakaya
5. Daniel K. Sodickson
6. Kerstin Hammernik
7. Florian Knoll
8. Tuomo Valkonen

Citations in the corpus

• Medical image processing on the GPU - Past, present and future (2013, methodology): “Knoll et al. (2011) reconstructed radially sampled data by combining total generalized variation regularization with a GPU implementation.”
• Denoising of diffusion MRI using random matrix theory (2016, background): “Indeed, fine anatomical details might be removed as well by this non-selective technique (Block et al., 2008; Knoll et al., 2011; Veraart et al., 2015; Perrone et al., 2015).”
• Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator (2014, methodology): “, 2010b) and finite difference may introduce staircase artifacts (Knoll et al., 2011; Ying and Jim, 2011) at high undersampling factors.”
• DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction (2018, neutral): “Classic fast CS-MRI uses predefined and fixed sparsifying transforms, e.g., total variation (TV) [17]–[19], discrete cosine transforms [20]–[22] and discrete wavelet transforms [23]–[25].”
• Learning a Variational Network for Reconstruction of Accelerated MRI Data (2017, methodology): “This stands in contrast to models like TV or TGV that are based on gradient filters in a small neighborhood (e.g., only forward differences in the x and y direction are considered).”
• Deep-Learning Methods for Parallel Magnetic Resonance Imaging Reconstruction: A Survey of the Current Approaches, Trends, and Issues (2019, methodology): “Figure 3 shows an example of a nonlinear combined parallel imaging and compressed sensing reconstruction with a Total Generalized Variation [10] constraint.”
• Bilevel approaches for learning of variational imaging models (2015, background): “We focus on second-order TV regularisation only since this is the one which seems to be most relevant in imaging applications [52, 9].”