Image reconstruction: From sparsity to data-adaptive methods and machine learning

S Ravishankar, JC Ye, JA Fessler - Proceedings of the IEEE, 2019 - ieeexplore.ieee.org
The field of medical image reconstruction has seen roughly four types of methods. The first
type tended to be analytical methods, such as filtered backprojection (FBP) for X-ray …

Structured overcomplete sparsifying transform learning with convergence guarantees and applications

B Wen, S Ravishankar, Y Bresler - International Journal of Computer …, 2015 - Springer
In recent years, sparse signal modeling, especially using the synthesis model has been
popular. Sparse coding in the synthesis model is however, NP-hard. Recently, interest has …

PWLS-ULTRA: An efficient clustering and learning-based approach for low-dose 3D CT image reconstruction

X Zheng, S Ravishankar, Y Long… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
The development of computed tomography (CT) image reconstruction methods that
significantly reduce patient radiation exposure, while maintaining high image quality is an …

Efficient blind compressed sensing using sparsifying transforms with convergence guarantees and application to magnetic resonance imaging

S Ravishankar, Y Bresler - SIAM Journal on Imaging Sciences, 2015 - SIAM
Natural signals and images are well known to be approximately sparse in transform
domains such as wavelets and discrete cosine transform. This property has been heavily …

Sparsifying transform learning with efficient optimal updates and convergence guarantees

S Ravishankar, Y Bresler - IEEE Transactions on Signal …, 2015 - ieeexplore.ieee.org
Many applications in signal processing benefit from the sparsity of signals in a certain
transform domain or dictionary. Synthesis sparsifying dictionaries that are directly adapted to …

Online sparsifying transform learning—Part I: Algorithms

S Ravishankar, B Wen, Y Bresler - IEEE Journal of Selected …, 2015 - ieeexplore.ieee.org
Techniques exploiting the sparsity of signals in a transform domain or dictionary have been
popular in signal processing. Adaptive synthesis dictionaries have been shown to be useful …

Data-driven learning of a union of sparsifying transforms model for blind compressed sensing

S Ravishankar, Y Bresler - IEEE Transactions on Computational …, 2016 - ieeexplore.ieee.org
Compressed sensing is a powerful tool in applications such as magnetic resonance imaging
(MRI). It enables accurate recovery of images from highly undersampled measurements by …

Sparse-view cone beam CT reconstruction using data-consistent supervised and adversarial learning from scarce training data

A Lahiri, G Maliakal, ML Klasky… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Reconstruction of CT images from a limited set of projections through an object is important
in several applications ranging from medical imaging to industrial settings. As the number of …

Patch-based models and algorithms for image processing: a review of the basic principles and methods, and their application in computed tomography

D Karimi, RK Ward - International journal of computer assisted radiology …, 2016 - Springer
Purpose Image models are central to all image processing tasks. The great advancements
in digital image processing would not have been made possible without powerful models …

VIDOSAT: High-dimensional sparsifying transform learning for online video denoising

B Wen, S Ravishankar, Y Bresler - IEEE Transactions on Image …, 2018 - ieeexplore.ieee.org
Techniques exploiting the sparsity of images in a transform domain are effective for various
applications in image and video processing. In particular, transform learning methods …