Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity

Natalie Durgin; Rachel Grotheer; Chenxi Huang; Shuang Li; Anna Ma; Deanna Needell; Jing Qin

doi:10.1109/EMBC.2019.8857069

Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity

Natalie Durgin, Rachel Grotheer, Chenxi Huang, Shuang Li, Anna Ma, Deanna Needell, Jing Qin

Mathematics

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

4 Scopus citations

Abstract

Diffuse optical tomography (DOT) is an important functional imaging modality in clinical diagnosis and treatment. As the number of wavelengths in the acquired DOT data grows, it becomes very challenging to reconstruct diffusion and absorption coefficients of tissue, i.e., a DOT image. In this paper, we consider the hyperspectral DOT (hyDOT) inverse problem as a multiple-measurement vector (MMV) problem by exploiting the joint sparsity of the images to be reconstructed. Then we propose a fast stochastic greedy algorithm based on the MMV stochastic gradient matching pursuit (MStoGradMP) and the mini-batching technique. Numerical results show that the proposed algorithm can achieve higher reconstruction accuracy with significantly reduced running time than the related gradient descent method with sparsity regularization.

Original language	English
Title of host publication	2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
Pages	4758-4761
Number of pages	4
ISBN (Electronic)	9781538613115
DOIs	https://doi.org/10.1109/EMBC.2019.8857069
State	Published - Jul 2019
Event	41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 - Berlin, Germany Duration: Jul 23 2019 → Jul 27 2019

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)	1557-170X

Conference

Conference	41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
Country/Territory	Germany
City	Berlin
Period	7/23/19 → 7/27/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Diffuse optical tomography (DOT)
joint sparsity
multiple-measurement vector (MMV)
stochastic greedy algorithm

ASJC Scopus subject areas

Signal Processing
Biomedical Engineering
Computer Vision and Pattern Recognition
Health Informatics

Access to Document

10.1109/EMBC.2019.8857069

Cite this

Durgin, N., Grotheer, R., Huang, C., Li, S., Ma, A., Needell, D., & Qin, J. (2019). Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 (pp. 4758-4761). Article 8857069 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/EMBC.2019.8857069

Durgin, Natalie ; Grotheer, Rachel ; Huang, Chenxi et al. / Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. 2019. pp. 4758-4761 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{a71a3f681ddc41d29b72a77c98518221,

title = "Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity",

abstract = "Diffuse optical tomography (DOT) is an important functional imaging modality in clinical diagnosis and treatment. As the number of wavelengths in the acquired DOT data grows, it becomes very challenging to reconstruct diffusion and absorption coefficients of tissue, i.e., a DOT image. In this paper, we consider the hyperspectral DOT (hyDOT) inverse problem as a multiple-measurement vector (MMV) problem by exploiting the joint sparsity of the images to be reconstructed. Then we propose a fast stochastic greedy algorithm based on the MMV stochastic gradient matching pursuit (MStoGradMP) and the mini-batching technique. Numerical results show that the proposed algorithm can achieve higher reconstruction accuracy with significantly reduced running time than the related gradient descent method with sparsity regularization.",

keywords = "Diffuse optical tomography (DOT), joint sparsity, multiple-measurement vector (MMV), stochastic greedy algorithm",

author = "Natalie Durgin and Rachel Grotheer and Chenxi Huang and Shuang Li and Anna Ma and Deanna Needell and Jing Qin",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 ; Conference date: 23-07-2019 Through 27-07-2019",

year = "2019",

month = jul,

doi = "10.1109/EMBC.2019.8857069",

language = "English",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

pages = "4758--4761",

booktitle = "2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019",

}

Durgin, N, Grotheer, R, Huang, C, Li, S, Ma, A, Needell, D & Qin, J 2019, Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity. in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019., 8857069, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 4758-4761, 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019, Berlin, Germany, 7/23/19. https://doi.org/10.1109/EMBC.2019.8857069

Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity. / Durgin, Natalie; Grotheer, Rachel; Huang, Chenxi et al.
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. 2019. p. 4758-4761 8857069 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

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

TY - GEN

T1 - Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity

AU - Durgin, Natalie

AU - Grotheer, Rachel

AU - Huang, Chenxi

AU - Li, Shuang

AU - Ma, Anna

AU - Needell, Deanna

AU - Qin, Jing

PY - 2019/7

Y1 - 2019/7

N2 - Diffuse optical tomography (DOT) is an important functional imaging modality in clinical diagnosis and treatment. As the number of wavelengths in the acquired DOT data grows, it becomes very challenging to reconstruct diffusion and absorption coefficients of tissue, i.e., a DOT image. In this paper, we consider the hyperspectral DOT (hyDOT) inverse problem as a multiple-measurement vector (MMV) problem by exploiting the joint sparsity of the images to be reconstructed. Then we propose a fast stochastic greedy algorithm based on the MMV stochastic gradient matching pursuit (MStoGradMP) and the mini-batching technique. Numerical results show that the proposed algorithm can achieve higher reconstruction accuracy with significantly reduced running time than the related gradient descent method with sparsity regularization.

AB - Diffuse optical tomography (DOT) is an important functional imaging modality in clinical diagnosis and treatment. As the number of wavelengths in the acquired DOT data grows, it becomes very challenging to reconstruct diffusion and absorption coefficients of tissue, i.e., a DOT image. In this paper, we consider the hyperspectral DOT (hyDOT) inverse problem as a multiple-measurement vector (MMV) problem by exploiting the joint sparsity of the images to be reconstructed. Then we propose a fast stochastic greedy algorithm based on the MMV stochastic gradient matching pursuit (MStoGradMP) and the mini-batching technique. Numerical results show that the proposed algorithm can achieve higher reconstruction accuracy with significantly reduced running time than the related gradient descent method with sparsity regularization.

KW - Diffuse optical tomography (DOT)

KW - joint sparsity

KW - multiple-measurement vector (MMV)

KW - stochastic greedy algorithm

UR - http://www.scopus.com/inward/record.url?scp=85077891280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077891280&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2019.8857069

DO - 10.1109/EMBC.2019.8857069

M3 - Conference contribution

C2 - 31946925

AN - SCOPUS:85077891280

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 4758

EP - 4761

BT - 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019

T2 - 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019

Y2 - 23 July 2019 through 27 July 2019

ER -

Durgin N, Grotheer R, Huang C, Li S, Ma A, Needell D et al. Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. 2019. p. 4758-4761. 8857069. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC.2019.8857069

Fast Hyperspectral Diffuse Optical Imaging Method with Joint Sparsity

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this