no code implementations • 10 Mar 2024 • Xiang Li, Soo Min Kwon, Ismail R. Alkhouri, Saiprasad Ravishankar, Qing Qu
To solve image restoration problems, many existing techniques achieve data consistency by incorporating additional likelihood gradient steps into the reverse sampling process of diffusion models.
no code implementations • 6 Feb 2024 • Shijun Liang, Evan Bell, Qing Qu, Rongrong Wang, Saiprasad Ravishankar
In this work, we first provide an analysis of how DIP recovers information from undersampled imaging measurements by analyzing the training dynamics of the underlying networks in the kernel regime for different architectures.
no code implementations • 14 Dec 2023 • Huijie Zhang, Yifu Lu, Ismail Alkhouri, Saiprasad Ravishankar, Dogyoon Song, Qing Qu
This is due to the necessity of tracking extensive forward and reverse diffusion trajectories, and employing a large model with numerous parameters across multiple timesteps (i. e., noise levels).
no code implementations • 13 Dec 2023 • Siddhant Gautam, Angqi Li, Saiprasad Ravishankar
In this work, we propose a novel patient-adaptive MRI sampling algorithm based on grouping scans within a training set.
1 code implementation • 12 Dec 2023 • Shijun Liang, Van Hoang Minh Nguyen, Jinghan Jia, Ismail Alkhouri, Sijia Liu, Saiprasad Ravishankar
To address this problem, we propose a novel image reconstruction framework, termed Smoothed Unrolling (SMUG), which advances a deep unrolling-based MRI reconstruction model using a randomized smoothing (RS)-based robust learning approach.
no code implementations • 19 Nov 2023 • Ling Chen, Zhishen Huang, Yong Long, Saiprasad Ravishankar
In our experiments, we study combinations of supervised deep network reconstructors and MBIR solver with learned sparse representation-based priors or analytical priors.
1 code implementation • 11 Sep 2023 • Ismail Alkhouri, Shijun Liang, Rongrong Wang, Qing Qu, Saiprasad Ravishankar
In particular, we present a robustification strategy that improves the resilience of DL-based MRI reconstruction methods by utilizing pretrained diffusion models as noise purifiers.
2 code implementations • 14 Mar 2023 • Hui Li, Jinghan Jia, Shijun Liang, Yuguang Yao, Saiprasad Ravishankar, Sijia Liu
To address this problem, we propose a novel image reconstruction framework, termed SMOOTHED UNROLLING (SMUG), which advances a deep unrolling-based MRI reconstruction model using a randomized smoothing (RS)-based robust learning operation.
no code implementations • 25 Jul 2022 • Chong Wang, Rongkai Zhang, Saiprasad Ravishankar, Bihan Wen
To this end, we propose a novel deep reinforcement learning (DRL) based PnP framework, dubbed RePNP, by leveraging a light-weight DRL-based denoiser for robust image restoration tasks.
no code implementations • 18 Jul 2022 • Avrajit Ghosh, Michael T. McCann, Madeline Mitchell, Saiprasad Ravishankar
We present a method for supervised learning of sparsity-promoting regularizers for denoising signals and images.
no code implementations • 1 Jun 2022 • Shijun Liang, Anish Lahiri, Saiprasad Ravishankar
In brief, our algorithm alternates between searching for neighbors in a data set that are similar to the test reconstruction, and training a local network on these neighbors followed by updating the test reconstruction.
no code implementations • 19 May 2022 • Ling Chen, Zhishen Huang, Yong Long, Saiprasad Ravishankar
Recent application of deep learning methods for image reconstruction provides a successful data-driven approach to addressing the challenges when reconstructing images with measurement undersampling or various types of noise.
no code implementations • 22 Mar 2022 • Xikai Yang, Zhishen Huang, Yong Long, Saiprasad Ravishankar
In this study, we propose a network-structured sparsifying transform learning approach for X-ray computed tomography (CT), which we refer to as multi-layer clustering-based residual sparsifying transform (MCST) learning.
1 code implementation • 17 Mar 2022 • Zhiyuan Zha, Bihan Wen, Xin Yuan, Saiprasad Ravishankar, Jiantao Zhou, Ce Zhu
Furthermore, we present a unified framework for incorporating various GSR and LR models and discuss the relationship between GSR and LR models.
no code implementations • 23 Jan 2022 • Anish Lahiri, Marc Klasky, Jeffrey A. Fessler, Saiprasad Ravishankar
This work focuses on image reconstruction in such settings, i. e., when both the number of available CT projections and the training data is extremely limited.
no code implementations • 21 Nov 2021 • Avrajit Ghosh, Michael T. McCann, Saiprasad Ravishankar
We present a method for supervised learning of sparsity-promoting regularizers, a key ingredient in many modern signal reconstruction problems.
1 code implementation • 17 Nov 2021 • Zhishen Huang, Saiprasad Ravishankar
There is much recent interest in techniques to accelerate the data acquisition process in MRI by acquiring limited measurements.
1 code implementation • 28 Oct 2021 • Zhishen Huang, Marc Klasky, Trevor Wilcox, Saiprasad Ravishankar
Object density reconstruction from projections containing scattered radiation and noise is of critical importance in many applications.
no code implementations • 15 Oct 2021 • Alexander N. Sietsema, Michael T. McCann, Marc L. Klasky, Saiprasad Ravishankar
In this paper, we compare idealized versions of these two approaches with synthetic experiments.
2 code implementations • 11 Apr 2021 • Anish Lahiri, Guanhua Wang, Saiprasad Ravishankar, Jeffrey A. Fessler
We also compare the proposed method to alternative approaches for combining dictionary-based methods with supervised learning in MR image reconstruction.
no code implementations • 26 Mar 2021 • Zhishen Huang, Siqi Ye, Michael T. McCann, Saiprasad Ravishankar
Many techniques have been proposed for image reconstruction in medical imaging that aim to recover high-quality images especially from limited or corrupted measurements.
no code implementations • 11 Dec 2020 • Michael T. McCann, Marc L. Klasky, Jennifer L. Schei, Saiprasad Ravishankar
To estimate scatter for a new radiograph, we adaptively fit a scatter model to a small subset of the training data containing the radiographs most similar to it.
no code implementations • 1 Nov 2020 • Xikai Yang, Yong Long, Saiprasad Ravishankar
Achieving high-quality reconstructions from low-dose computed tomography (LDCT) measurements is of much importance in clinical settings.
no code implementations • 10 Oct 2020 • Xikai Yang, Yong Long, Saiprasad Ravishankar
In this work, we develop a new image reconstruction approach based on a novel multi-layer model learned in an unsupervised manner by combining both sparse representations and deep models.
no code implementations • 6 Oct 2020 • Siqi Ye, Zhipeng Li, Michael T. McCann, Yong Long, Saiprasad Ravishankar
The proposed learning formulation combines both unsupervised learning-based priors (or even simple analytical priors) together with (supervised) deep network-based priors in a unified MBIR framework based on a fixed point iteration analysis.
1 code implementation • 24 Jun 2020 • Lanqing Guo, Zhiyuan Zha, Saiprasad Ravishankar, Bihan Wen
Experimental results demonstrate that (1) Self-Convolution can significantly speed up most of the popular non-local image restoration algorithms, with two-fold to nine-fold faster block matching, and (2) the proposed multi-modality image restoration scheme achieves superior denoising results in both efficiency and effectiveness on RGB-NIR images.
no code implementations • 9 Jun 2020 • Michael T. McCann, Saiprasad Ravishankar
We present a method for supervised learning of sparsity-promoting regularizers for image denoising.
no code implementations • 8 May 2020 • Xikai Yang, Xuehang Zheng, Yong Long, Saiprasad Ravishankar
Signal models based on sparse representation have received considerable attention in recent years.
no code implementations • 26 Oct 2019 • Zhipeng Li, Siqi Ye, Yong Long, Saiprasad Ravishankar
Recent works have shown the promising reconstruction performance of methods such as PWLS-ULTRA that rely on clustering the underlying (reconstructed) image patches into a learned union of transforms.
no code implementations • 1 Jun 2019 • Xuehang Zheng, Saiprasad Ravishankar, Yong Long, Marc Louis Klasky, Brendt Wohlberg
Signal models based on sparsity, low-rank and other properties have been exploited for image reconstruction from limited and corrupted data in medical imaging and other computational imaging applications.
no code implementations • 4 Apr 2019 • Saiprasad Ravishankar, Jong Chul Ye, Jeffrey A. Fessler
This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques.
no code implementations • 25 Mar 2019 • Bihan Wen, Saiprasad Ravishankar, Luke Pfister, Yoram Bresler
The model could be pre-learned from datasets, or learned simultaneously with the reconstruction, i. e., blind CS (BCS).
no code implementations • 1 Jan 2019 • Zhipeng Li, Saiprasad Ravishankar, Yong Long, Jeffrey A. Fessler
Dual energy computed tomography (DECT) imaging plays an important role in advanced imaging applications due to its material decomposition capability.
no code implementations • 19 Oct 2018 • Saiprasad Ravishankar, Brendt Wohlberg
Learned data models based on sparsity are widely used in signal processing and imaging applications.
no code implementations • 6 Sep 2018 • Brian E. Moore, Saiprasad Ravishankar, Raj Rao Nadakuditi, Jeffrey A. Fessler
Sparsity and low-rank models have been popular for reconstructing images and videos from limited or corrupted measurements.
1 code implementation • 27 Aug 2018 • Siqi Ye, Saiprasad Ravishankar, Yong Long, Jeffrey A. Fessler
The SPULTRA algorithm has a similar computational cost per iteration as its recent counterpart PWLS-ULTRA that uses post-log measurements, and it provides better image reconstruction quality than PWLS-ULTRA, especially in low-dose scans.
Signal Processing Image and Video Processing Optimization and Control Medical Physics
no code implementations • 31 May 2018 • Saiprasad Ravishankar, Anna Ma, Deanna Needell
Sparsity-based models and techniques have been exploited in many signal processing and imaging applications.
no code implementations • 1 Feb 2018 • Saiprasad Ravishankar, Anna Ma, Deanna Needell
Alternating minimization algorithms have been particularly popular in dictionary or transform learning.
1 code implementation • 3 Oct 2017 • Bihan Wen, Saiprasad Ravishankar, Yoram Bresler
Transform learning methods involve cheap computations and have been demonstrated to perform well in applications such as image denoising and medical image reconstruction.
no code implementations • 10 Jul 2017 • Xuehang Zheng, Zening Lu, Saiprasad Ravishankar, Yong Long, Jeffrey A. Fessler
A major challenge in computed tomography (CT) is to reduce X-ray dose to a low or even ultra-low level while maintaining the high quality of reconstructed images.
1 code implementation • 27 Mar 2017 • Xuehang Zheng, Saiprasad Ravishankar, Yong Long, Jeffrey A. Fessler
PWLS with regularization based on a union of learned transforms leads to better image reconstructions than using a single learned square transform.
no code implementations • 13 Nov 2016 • Saiprasad Ravishankar, Brian E. Moore, Raj Rao Nadakuditi, Jeffrey A. Fessler
For example, the patches of the underlying data are modeled as sparse in an adaptive dictionary domain, and the resulting image and dictionary estimation from undersampled measurements is called dictionary-blind compressed sensing, or the dynamic image sequence is modeled as a sum of low-rank and sparse (in some transform domain) components (L+S model) that are estimated from limited measurements.
no code implementations • 27 Nov 2015 • Saiprasad Ravishankar, Raj Rao Nadakuditi, Jeffrey A. Fessler
The proposed block coordinate descent algorithm involves efficient closed-form solutions.
1 code implementation • 19 Nov 2015 • Saiprasad Ravishankar, Raj Rao Nadakuditi, Jeffrey A. Fessler
This paper exploits the ideas that drive algorithms such as K-SVD, and investigates in detail efficient methods for aggregate sparsity penalized dictionary learning by first approximating the data with a sum of sparse rank-one matrices (outer products) and then using a block coordinate descent approach to estimate the unknowns.
no code implementations • 19 Nov 2015 • Bihan Wen, Saiprasad Ravishankar, Yoram Bresler
Features based on sparse representation, especially using the synthesis dictionary model, have been heavily exploited in signal processing and computer vision.
no code implementations • 4 Nov 2015 • Saiprasad Ravishankar, Yoram Bresler
In this work, we focus on blind compressed sensing (BCS), where the underlying sparse signal model is a priori unknown, and propose a framework to simultaneously reconstruct the underlying image as well as the unknown model from highly undersampled measurements.
no code implementations • 13 Jan 2015 • Saiprasad Ravishankar, Yoram Bresler
Natural signals and images are well-known to be approximately sparse in transform domains such as Wavelets and DCT.
no code implementations • 13 Jan 2015 • Saiprasad Ravishankar, Yoram Bresler
Many applications in signal processing benefit from the sparsity of signals in a certain transform domain or dictionary.