Off-The-Grid Model Based Deep Learning (O-Modl)

Aniket Pramanik; Hemant Aggarwal; Mathews Jacob

doi:10.1109/ISBI.2019.8759403

Back

Conference proceeding

Off-The-Grid Model Based Deep Learning (O-Modl)

Aniket Pramanik, Hemant Aggarwal and Mathews Jacob

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp.1395-1398

04/2019

DOI: 10.1109/ISBI.2019.8759403

Files and links (1)

url

https://arxiv.org/pdf/1812.10747View

Open Access

Abstract

We introduce a model based off-the grid image reconstruction algorithm using deep learned priors. The main difference of the proposed scheme with current deep learning strategies is the learning of non-linear annihilation relations in Fourier space. We rely on a model based framework, which allows us to use a significantly smaller deep network, compared to direct approaches that also learn how to invert the forward model. Preliminary comparisons against image domain MoDL approach demonstrates the potential of the off-the-grid formulation. The main benefit of the proposed scheme compared to structured low-rank methods is the quite significant reduction in computational complexity.

Deep learning

Training

Deconvolution

CNN

Convolution

Noise reduction

off-the-grid

MRI

Acceleration

Image reconstruction

Details

Title: Subtitle: Off-The-Grid Model Based Deep Learning (O-Modl)
Creators: Aniket Pramanik - University of Iowa, Iowa, USA
Hemant Aggarwal - University of Iowa, Iowa, USA
Mathews Jacob - University of Iowa, Iowa, USA
Resource Type: Conference proceeding
Publication Details: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp.1395-1398
DOI: 10.1109/ISBI.2019.8759403
eISSN: 1945-8452
Publisher: IEEE
Language: English
Date published: 04/2019
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Iowa Neuroscience Institute; Radiation Oncology
Record Identifier: 9984070788902771

Metrics

29 Record Views