Search Results for author: Mathews Jacob

Found 52 papers, 8 papers with code

Memory-efficient deep end-to-end posterior network (DEEPEN) for inverse problems

no code implementations8 Feb 2024 Jyothi Rikhab Chand, Mathews Jacob

The CNN weights are learned from training data in an E2E fashion using maximum likelihood optimization.

Image Reconstruction

Surf-CDM: Score-Based Surface Cold-Diffusion Model For Medical Image Segmentation

no code implementations19 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.

Image Denoising Image Generation +4

Local monotone operator learning using non-monotone operators: MnM-MOL

no code implementations1 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.

Operator learning

Motion Compensated Unsupervised Deep Learning for 5D MRI

no code implementations8 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.

Multi-Scale Energy (MuSE) plug and play framework for inverse problems

no code implementations8 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.

Denoising

Adapting model-based deep learning to multiple acquisition conditions: Ada-MoDL

no code implementations21 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.

Accelerated parallel MRI using memory efficient and robust monotone operator learning (MOL)

no code implementations3 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.

Compressive Sensing Operator learning

Deep Factor Model: A Novel Approach for Motion Compensated Multi-Dimensional MRI

no code implementations31 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.

Motion Estimation Time Series

Plug-and-Play Deep Energy Model for Inverse problems

no code implementations15 Feb 2023 Jyothi Rikabh Chand, Mathews Jacob

We introduce a novel energy formulation for Plug- and-Play (PnP) image recovery.

Image Reconstruction

Memory-efficient model-based deep learning with convergence and robustness guarantees

no code implementations6 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.

Compressive Sensing Operator learning

Joint cardiac $T_1$ mapping and cardiac function estimation using a deep manifold framework

no code implementations16 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.

Image Reconstruction Motion Estimation +2

Dynamic imaging using Motion-Compensated SmooThness Regularization on Manifolds (MoCo-SToRM)

no code implementations6 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.

Time Series Time Series Analysis

Improved Model based Deep Learning using Monotone Operator Learning (MOL)

no code implementations22 Nov 2021 Aniket Pramanik, Mathews Jacob

Model-based deep learning (MoDL) algorithms that rely on unrolling are emerging as powerful tools for image recovery.

Operator learning Rolling Shutter Correction

Joint alignment and reconstruction of multislice dynamic MRI using variational manifold learning

no code implementations21 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.

Dynamic imaging using motion-compensated smoothness regularization on manifolds (MoCo-SToRM)

no code implementations21 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.

Deep Image Prior using Stein's Unbiased Risk Estimator: SURE-DIP

no code implementations21 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.

Rolling Shutter Correction

Dynamic Imaging using Deep Bi-linear Unsupervised Regularization (DEBLUR)

no code implementations30 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.

Joint Calibrationless Reconstruction and Segmentation of Parallel MRI

no code implementations19 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.

MRI Reconstruction Segmentation

Reconstruction and Segmentation of Parallel MR Data using Image Domain DEEP-SLR

no code implementations1 Feb 2021 Aniket Pramanik, Mathews Jacob

We introduce an image domain deep network for calibrationless recovery of undersampled PMRI data.

Segmentation

Deep Generative SToRM model for dynamic imaging

no code implementations29 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.

Time Series Time Series Analysis

Model Adaptation for Image Reconstruction using Generalized Stein's Unbiased Risk Estimator

no code implementations29 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.

Image Reconstruction

Variational manifold learning from incomplete data: application to multislice dynamic MRI

no code implementations20 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.

Imputation

ENSURE: A General Approach for Unsupervised Training of Deep Image Reconstruction Algorithms

no code implementations20 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.

Image Denoising Image Reconstruction

Recovery of surfaces and functions in high dimensions: sampling theory and links to neural networks

no code implementations26 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.

Image Denoising Time Series +1

Calibrationless Parallel MRI using Model based Deep Learning (C-MODL)

no code implementations27 Nov 2019 Aniket Pramanik, Hemant Aggarwal, Mathews Jacob

We introduce a fast model based deep learning approach for calibrationless parallel MRI reconstruction.

MRI Reconstruction

J-MoDL: Joint Model-Based Deep Learning for Optimized Sampling and Reconstruction

1 code implementation6 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.

Image Reconstruction

Structured Low-Rank Algorithms: Theory, MR Applications, and Links to Machine Learning

1 code implementation27 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.

BIG-bench Machine Learning Low-Rank Matrix Completion

Free-breathing and ungated cardiac cine using navigator-less spiral SToRM

2 code implementations16 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.

Off-the-grid model based deep learning (O-MODL)

no code implementations27 Dec 2018 Aniket Pramanik, Hemant Kumar Aggarwal, Mathews Jacob

We introduce a model based off-the-grid image reconstruction algorithm using deep learned priors.

Image Reconstruction

MoDL-MUSSELS: Model-Based Deep Learning for Multi-Shot Sensitivity Encoded Diffusion MRI

1 code implementation19 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.

Model-based free-breathing cardiac MRI reconstruction using deep learned \& STORM priors: MoDL-STORM

no code implementations10 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.

MRI Reconstruction

Calibration-free B0 correction of EPI data using structured low rank matrix recovery

no code implementations20 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.

Time Series Time Series Analysis

Free-breathing cardiac MRI using bandlimited manifold modelling

no code implementations24 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.

Recovery of Noisy Points on Band-limited Surfaces: Kernel Methods Re-explained

no code implementations3 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.

Recovery of Point Clouds on Surfaces: Application to Image Reconstruction

no code implementations3 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.

Image Reconstruction

Clustering of Data with Missing Entries

no code implementations3 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.

Clustering

MoDL: Model Based Deep Learning Architecture for Inverse Problems

3 code implementations7 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.

Image Reconstruction

Separation-Free Super-Resolution from Compressed Measurements is Possible: an Orthonormal Atomic Norm Minimization Approach

no code implementations4 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.

Super-Resolution

Clustering of Data with Missing Entries using Non-convex Fusion Penalties

no code implementations6 Sep 2017 Sunrita Poddar, Mathews Jacob

Traditional algorithms for clustering data assume that all the feature values are known for every data point.

Clustering

Recovery of damped exponentials using structured low rank matrix completion

no code implementations14 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.

Low-Rank Matrix Completion Relation

Novel Structured Low-rank algorithm to recover spatially smooth exponential image time series

no code implementations29 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.

Low-Rank Matrix Completion Relation +2

A Fast Algorithm for Convolutional Structured Low-Rank Matrix Recovery

3 code implementations23 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

Off-the-Grid Recovery of Piecewise Constant Images from Few Fourier Samples

no code implementations1 Oct 2015 Greg Ongie, Mathews Jacob

In the first stage we estimate a continuous domain representation of the edge set of the image.

Image Super-Resolution Relation

Recovery of Piecewise Smooth Images from Few Fourier Samples

no code implementations3 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.

Matrix Completion Relation

Super-resolution MRI Using Finite Rate of Innovation Curves

no code implementations8 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.

Super-Resolution

Two step recovery of jointly sparse and low-rank matrices: theoretical guarantees

no code implementations5 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.

Subspace based low rank and joint sparse matrix recovery

no code implementations5 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.

Time Series Time Series Analysis

Deformation corrected compressed sensing (DC-CS): a novel framework for accelerated dynamic MRI

no code implementations29 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.

Denoising

Iterative Non-Local Shrinkage Algorithm for MR Image Reconstruction

no code implementations15 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.

Image Reconstruction

Cannot find the paper you are looking for? You can Submit a new open access paper.