Off-the-grid model based deep learning (o-modl)

Aniket Pramanik; Hemant Aggarwal; Mathews Jacob

doi:10.1109/ISBI.2019.8759403

Off-the-grid model based deep learning (o-modl)

Aniket Pramanik, Hemant Aggarwal, Mathews Jacob

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

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.

Original language	English
Title of host publication	ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
Publisher	IEEE Computer Society
Pages	1395-1398
Number of pages	4
ISBN (Electronic)	9781538636411
DOIs	https://doi.org/10.1109/ISBI.2019.8759403
State	Published - Apr 2019
Externally published	Yes
Event	16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy Duration: Apr 8 2019 → Apr 11 2019

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2019-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
Country/Territory	Italy
City	Venice
Period	04/8/19 → 04/11/19

Funding

This work is supported by NIH 1R01EB019961-01A1.

Keywords

CNN
MRI
Off-the-grid

Access to Document

10.1109/ISBI.2019.8759403

Cite this

@inproceedings{621c312631b74c5eb23a58beb30e42cb,

title = "Off-the-grid model based deep learning (o-modl)",

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.",

keywords = "CNN, MRI, Off-the-grid",

author = "Aniket Pramanik and Hemant Aggarwal and Mathews Jacob",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 ; Conference date: 08-04-2019 Through 11-04-2019",

year = "2019",

month = apr,

doi = "10.1109/ISBI.2019.8759403",

language = "English",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "1395--1398",

booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

}

Pramanik, A, Aggarwal, H & Jacob, M 2019, Off-the-grid model based deep learning (o-modl). in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging., 8759403, Proceedings - International Symposium on Biomedical Imaging, vol. 2019-April, IEEE Computer Society, pp. 1395-1398, 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, Venice, Italy, 04/8/19. https://doi.org/10.1109/ISBI.2019.8759403

Off-the-grid model based deep learning (o-modl). / Pramanik, Aniket; Aggarwal, Hemant; Jacob, Mathews.
ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. p. 1395-1398 8759403 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Off-the-grid model based deep learning (o-modl)

AU - Pramanik, Aniket

AU - Aggarwal, Hemant

AU - Jacob, Mathews

PY - 2019/4

Y1 - 2019/4

N2 - 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.

AB - 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.

KW - CNN

KW - MRI

KW - Off-the-grid

UR - http://www.scopus.com/inward/record.url?scp=85073897861&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759403

DO - 10.1109/ISBI.2019.8759403

M3 - Conference contribution

AN - SCOPUS:85073897861

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1395

EP - 1398

BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

T2 - 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019

Y2 - 8 April 2019 through 11 April 2019

ER -

Off-the-grid model based deep learning (o-modl)

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this