no code implementations • 24 Apr 2024 • Reinhard Heckel, Mathews Jacob, Akshay Chaudhari, Or Perlman, Efrat Shimron
Deep learning (DL) has recently emerged as a pivotal technology for enhancing magnetic resonance imaging (MRI), a critical tool in diagnostic radiology.
no code implementations • 8 Feb 2024 • Jyothi Rikhab Chand, Mathews Jacob
The CNN weights are learned from training data in an E2E fashion using maximum likelihood optimization.
no code implementations • 19 Dec 2023 • Fahim Ahmed Zaman, Mathews Jacob, Amanda Chang, Kan Liu, Milan Sonka, Xiaodong Wu
Diffusion models have shown impressive performance for image generation, often times outperforming other generative models.
no code implementations • 1 Dec 2023 • Maneesh John, Jyothi Rikhab Chand, Mathews Jacob
Inspired by convex-non-convex regularization strategies, we now impose the monotone constraint on the sum of the gradient of the data term and the CNN block, rather than constrain the CNN itself to be a monotone operator.
no code implementations • 8 Sep 2023 • Joseph Kettelkamp, Ludovica Romanin, Davide Piccini, Sarv Priya, Mathews Jacob
The deformation maps and the template are then jointly estimated from the measured data.
no code implementations • 8 May 2023 • Jyothi Rikhab Chand, Mathews Jacob
We introduce a multi-scale optimization strategy, where a sequence of smooth approximations of the true prior is used in the optimization process.
no code implementations • 21 Apr 2023 • Aniket Pramanik, Sampada Bhave, Saurav Sajib, Samir D. Sharma, Mathews Jacob
Purpose: The aim of this work is to introduce a single model-based deep network that can provide high-quality reconstructions from undersampled parallel MRI data acquired with multiple sequences, acquisition settings and field strengths.
no code implementations • 3 Apr 2023 • Aniket Pramanik, Mathews Jacob
Model-based deep learning methods that combine imaging physics with learned regularization priors have been emerging as powerful tools for parallel MRI acceleration.
no code implementations • 31 Mar 2023 • Yan Chen, James H. Holmes, Curtis Corum, Vincent Magnotta, Mathews Jacob
Recent quantitative parameter mapping methods including MR fingerprinting (MRF) collect a time series of images that capture the evolution of magnetization.
no code implementations • 15 Feb 2023 • Jyothi Rikabh Chand, Mathews Jacob
We introduce a novel energy formulation for Plug- and-Play (PnP) image recovery.
1 code implementation • 6 Sep 2022 • Rushdi Zahid Rusho, Abdul Haseeb Ahmed, Stanley Kruger, Wahidul Alam, David Meyer, David Howard, Brad Story, Mathews Jacob, Sajan Goud Lingala
Our scheme provided improved reconstruction over the others.
no code implementations • 6 Jun 2022 • Aniket Pramanik, M. Bridget Zimmerman, Mathews Jacob
The proposed iterative algorithm alternates between a gradient descent involving the score function and a conjugate gradient algorithm to encourage data consistency.
no code implementations • 16 May 2022 • Qing Zou, Mathews Jacob
Once the network is trained, we can excite the latent vectors (the estimated motion signals and the contrast signal) in any way as we wanted to generate the image frames in the time series.
no code implementations • 6 Dec 2021 • Qing Zou, Luis A. Torres, Sean B. Fain, Nara S. Higano, Alister J. Bates, Mathews Jacob
The template image volume, the parameters of the generator, and the latent vectors are learned directly from the k-t space data in an unsupervised fashion.
no code implementations • 22 Nov 2021 • Aniket Pramanik, Mathews Jacob
Model-based deep learning (MoDL) algorithms that rely on unrolling are emerging as powerful tools for image recovery.
no code implementations • 21 Nov 2021 • Qing Zou, Luis A. Torres, Sean B. Fain, Mathews Jacob
The images at each time instant are modeled as the deformed version of an image template using the above motion fields.
no code implementations • 21 Nov 2021 • Qing Zou, Abdul Haseeb Ahmed, Prashant Nagpal, Sarv Priya, Rolf F Schulte, Mathews Jacob
Free-breathing cardiac MRI schemes are emerging as competitive alternatives to breath-held cine MRI protocols, enabling applicability to pediatric and other population groups that cannot hold their breath.
no code implementations • 21 Nov 2021 • Maneesh John, Hemant Kumar Aggarwal, Qing Zou, Mathews Jacob
The deep image prior (DIP) algorithm was introduced for single-shot image recovery, completely eliminating the need for training data.
no code implementations • 30 Jun 2021 • Abdul Haseeb Ahmed, Prashant Nagpal, Mathews Jacob
Bilinear models that decompose dynamic data to spatial and temporal factors are powerful and memory-efficient tools for the recovery of dynamic MRI data.
no code implementations • 19 May 2021 • Aniket Pramanik, Xiaodong Wu, Mathews Jacob
We introduce a novel image domain deep-learning framework for calibrationless parallel MRI reconstruction, coupled with a segmentation network to improve image quality and to reduce the vulnerability of current segmentation algorithms to image artifacts resulting from acceleration.
no code implementations • 1 Feb 2021 • Aniket Pramanik, Mathews Jacob
We introduce an image domain deep network for calibrationless recovery of undersampled PMRI data.
no code implementations • 29 Jan 2021 • Qing Zou, Abdul Haseeb Ahmed, Prashant Nagpal, Stanley Kruger, Mathews Jacob
Unlike the popular CNN approaches that require extensive fully-sampled training data that is not available in this setting, the parameters of the CNN generator as well as the latent vectors are jointly estimated from the undersampled measurements using stochastic gradient descent.
no code implementations • 29 Jan 2021 • Qing Zou, Abdul Haseeb Ahmed, Prashant Nagpal, Stanley Kruger, Mathews Jacob
The proposed scheme brings in the spatial regularization provided by the convolutional network.
no code implementations • 29 Jan 2021 • Hemant Kumar Aggarwal, Mathews Jacob
Deep learning image reconstruction algorithms often suffer from model mismatches when the acquisition scheme differs significantly from the forward model used during training.
no code implementations • 20 Jan 2021 • Qing Zou, Abdul Haseeb Ahmed, Prashant Nagpal, Sarv Priya, Rolf Schulte, Mathews Jacob
Most of the current self-gating and manifold cardiac MRI approaches consider the independent recovery of images from each slice; these methods are not capable of exploiting the inter-slice redundancies in the datasets and require sophisticated post-processing or manual approaches to align the images from different slices.
no code implementations • 20 Oct 2020 • Hemant Kumar Aggarwal, Aniket Pramanik, Maneesh John, Mathews Jacob
We introduce a novel metric termed the ENsemble Stein's Unbiased Risk Estimate (ENSURE) framework, which can be used to train deep image reconstruction algorithms without fully sampled and noise-free images.
no code implementations • 26 May 2020 • Qing Zou, Mathews Jacob
The low-rank property of the features is used to determine the number of measurements needed to recover the surface.
1 code implementation • 7 Dec 2019 • Aniket Pramanik, Hemant Aggarwal, Mathews Jacob
The main challenge with this strategy is the high computational complexity of matrix completion.
no code implementations • 27 Nov 2019 • Aniket Pramanik, Hemant Aggarwal, Mathews Jacob
We introduce a fast model based deep learning approach for calibrationless parallel MRI reconstruction.
1 code implementation • 6 Nov 2019 • Hemant Kumar Aggarwal, Mathews Jacob
This approach facilitates the joint and continuous optimization of the sampling pattern and the CNN parameters to improve image quality.
1 code implementation • 27 Oct 2019 • Mathews Jacob, Merry P. Mani, Jong Chul Ye
In this survey, we provide a detailed review of recent advances in the recovery of continuous domain multidimensional signals from their few non-uniform (multichannel) measurements using structured low-rank matrix completion formulation.
2 code implementations • 16 Jan 2019 • Abdul Haseeb Ahmed, Yasir Mohsin, Ruixi Zhou, Yang Yang, Michael Salerno, Prashant Nagpal, Mathews Jacob
An iterative kernel low-rank algorithm is introduced to estimate the manifold structure of the images, or equivalently the manifold Laplacian matrix, from the central k-space regions.
no code implementations • 27 Dec 2018 • Aniket Pramanik, Hemant Kumar Aggarwal, Mathews Jacob
We introduce a model based off-the-grid image reconstruction algorithm using deep learned priors.
1 code implementation • 19 Dec 2018 • Hemant Kumar Aggarwal, Merry P. Mani, Mathews Jacob
In this work, we show that an iterative re-weighted least-squares implementation of MUSSELS alternates between a multichannel filter bank and the enforcement of data consistency.
no code implementations • 10 Jul 2018 • Sampurna Biswas, Hemant K. Aggarwal, Sunrita Poddar, Mathews Jacob
We introduce a model-based reconstruction framework with deep learned (DL) and smoothness regularization on manifolds (STORM) priors to recover free breathing and ungated (FBU) cardiac MRI from highly undersampled measurements.
no code implementations • 20 Apr 2018 • Arvind Balachandrasekaran, Merry Mani, Mathews Jacob
We introduce a structured low rank algorithm for the calibration-free compensation of field inhomogeneity artifacts in Echo Planar Imaging (EPI) MRI data.
no code implementations • 24 Feb 2018 • Sunrita Poddar, Yasir Mohsin, Deidra Ansah, Bijoy Thattaliyath, Ravi Ashwath, Mathews Jacob
We introduce a novel bandlimited manifold framework and an algorithm to recover freebreathing and ungated cardiac MR images from highly undersampled measurements.
no code implementations • 3 Jan 2018 • Sunrita Poddar, Mathews Jacob
We introduce a continuous domain framework for the recovery of points on a surface in high dimensional space, represented as the zero-level set of a bandlimited function.
no code implementations • 3 Jan 2018 • Sunrita Poddar, Mathews Jacob
The analysis of large datasets is often complicated by the presence of missing entries, mainly because most of the current machine learning algorithms are designed to work with full data.
no code implementations • 3 Jan 2018 • Sunrita Poddar, Mathews Jacob
We introduce a framework for the recovery of points on a smooth surface in high-dimensional space, with application to dynamic imaging.
3 code implementations • 7 Dec 2017 • Hemant Kumar Aggarwal, Merry P. Mani, Mathews Jacob
Since the forward model is explicitly accounted for, a smaller network with fewer parameters is sufficient to capture the image information compared to black-box deep learning approaches, thus reducing the demand for training data and training time.
no code implementations • 4 Nov 2017 • Weiyu Xu, Jirong Yi, Soura Dasgupta, Jian-Feng Cai, Mathews Jacob, Myung Cho
However, it is known that in order for TV minimization and atomic norm minimization to recover the missing data or the frequencies, the underlying $R$ frequencies are required to be well-separated, even when the measurements are noiseless.
no code implementations • 6 Sep 2017 • Sunrita Poddar, Mathews Jacob
Traditional algorithms for clustering data assume that all the feature values are known for every data point.
no code implementations • 14 Apr 2017 • Arvind Balachandrasekaran, Vincent Magnotta, Mathews Jacob
We introduce a structured low rank matrix completion algorithm to recover a series of images from their under-sampled measurements, where the signal along the parameter dimension at every pixel is described by a linear combination of exponentials.
no code implementations • 29 Mar 2017 • Arvind Balachandrasekaran, Mathews Jacob
We propose a structured low rank matrix completion algorithm to recover a time series of images consisting of linear combination of exponential parameters at every pixel, from under-sampled Fourier measurements.
3 code implementations • 23 Sep 2016 • Greg Ongie, Mathews Jacob
Fourier domain structured low-rank matrix priors are emerging as powerful alternatives to traditional image recovery methods such as total variation and wavelet regularization.
Numerical Analysis Optimization and Control
no code implementations • 1 Oct 2015 • Greg Ongie, Mathews Jacob
In the first stage we estimate a continuous domain representation of the edge set of the image.
no code implementations • 3 Feb 2015 • Greg Ongie, Mathews Jacob
We introduce a Prony-like method to recover a continuous domain 2-D piecewise smooth image from few of its Fourier samples.
no code implementations • 8 Jan 2015 • Greg Ongie, Mathews Jacob
We propose a two-stage algorithm for the super-resolution of MR images from their low-frequency k-space samples.
no code implementations • 5 Dec 2014 • Sampurna Biswas, Sunrita Poddar, Soura Dasgupta, Raghuraman Mudumbai, Mathews Jacob
We consider the recovery of a low rank and jointly sparse matrix from under sampled measurements of its columns.
no code implementations • 5 Dec 2014 • Sampurna Biswas, Sunrita Poddar, Soura Dasgupta, Raghuraman Mudumbai, Mathews Jacob
We introduce a two step algorithm with theoretical guarantees to recover a jointly sparse and low-rank matrix from undersampled measurements of its columns.
no code implementations • 29 May 2014 • Sajan Goud Lingala, Edward DiBella, Mathews Jacob
Through experiments on numerical phantom and in vivo myocardial perfusion MRI datasets, we demonstrate the utility of the proposed DC-CS scheme in providing robust reconstructions with reduced motion artifacts over classical compressed sensing schemes that utilize the compact priors on the original deformation un-corrected signal.
no code implementations • 15 May 2014 • Yasir Q. Moshin, Greg Ongie, Mathews Jacob
This approach is enabled by the reformulation of current non-local schemes as an alternating algorithm to minimize a global criterion.