Deep Learning for Time-Domain Diffuse Optical Tomography Reconstructions by Unrolling a Sensitivity Equation-based Algorithm

Fay Wang; Andreas H. Hielscher; Stephen H. Kim

doi:10.1364/OMA.2023.JTu4B.7

Deep Learning for Time-Domain Diffuse Optical Tomography Reconstructions by Unrolling a Sensitivity Equation-based Algorithm

Fay Wang, Andreas H. Hielscher, Stephen H. Kim

Biomedical Engineering

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

Abstract

We have developed a neural network based on algorithm unrolling techniques to overcome challenges in the DOT inverse problem. Results from numerical and phantom experiments show the network’s capability for high-speed and accurate DOT reconstructions.

Original language	English (US)
Title of host publication	Optical Manipulation and Its Applications, OMA 2023
Publisher	Optical Society of America
ISBN (Electronic)	9781957171210
DOIs	https://doi.org/10.1364/OMA.2023.JTu4B.7
State	Published - 2023
Event	Optical Manipulation and Its Applications, OMA 2023 - Part of Optica Biophotonics Congress: Optics in the Life Sciences 2023 - Vancouver, Canada Duration: Apr 24 2023 → Apr 27 2023

Publication series

Name	Optical Manipulation and Its Applications, OMA 2023

Conference

Conference	Optical Manipulation and Its Applications, OMA 2023 - Part of Optica Biophotonics Congress: Optics in the Life Sciences 2023
Country/Territory	Canada
City	Vancouver
Period	4/24/23 → 4/27/23

ASJC Scopus subject areas

Atomic and Molecular Physics, and Optics
Space and Planetary Science
Instrumentation
General Computer Science
Electronic, Optical and Magnetic Materials
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1364/OMA.2023.JTu4B.7

Cite this

Deep Learning for Time-Domain Diffuse Optical Tomography Reconstructions by Unrolling a Sensitivity Equation-based Algorithm. / Wang, Fay; Hielscher, Andreas H.; Kim, Stephen H.
Optical Manipulation and Its Applications, OMA 2023. Optical Society of America, 2023. (Optical Manipulation and Its Applications, OMA 2023).

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

Wang, F, Hielscher, AH & Kim, SH 2023, Deep Learning for Time-Domain Diffuse Optical Tomography Reconstructions by Unrolling a Sensitivity Equation-based Algorithm. in Optical Manipulation and Its Applications, OMA 2023. Optical Manipulation and Its Applications, OMA 2023, Optical Society of America, Optical Manipulation and Its Applications, OMA 2023 - Part of Optica Biophotonics Congress: Optics in the Life Sciences 2023, Vancouver, Canada, 4/24/23. https://doi.org/10.1364/OMA.2023.JTu4B.7

@inproceedings{772f1cbdafc94b2f9870c87e6bc205fa,

title = "Deep Learning for Time-Domain Diffuse Optical Tomography Reconstructions by Unrolling a Sensitivity Equation-based Algorithm",

abstract = "We have developed a neural network based on algorithm unrolling techniques to overcome challenges in the DOT inverse problem. Results from numerical and phantom experiments show the network{\textquoteright}s capability for high-speed and accurate DOT reconstructions.",

author = "Fay Wang and Hielscher, {Andreas H.} and Kim, {Stephen H.}",

note = "Publisher Copyright: {\textcopyright} 2023 The Author(s).; Optical Manipulation and Its Applications, OMA 2023 - Part of Optica Biophotonics Congress: Optics in the Life Sciences 2023 ; Conference date: 24-04-2023 Through 27-04-2023",

year = "2023",

doi = "10.1364/OMA.2023.JTu4B.7",

language = "English (US)",

series = "Optical Manipulation and Its Applications, OMA 2023",

publisher = "Optical Society of America",

booktitle = "Optical Manipulation and Its Applications, OMA 2023",

}

TY - GEN

T1 - Deep Learning for Time-Domain Diffuse Optical Tomography Reconstructions by Unrolling a Sensitivity Equation-based Algorithm

AU - Wang, Fay

AU - Hielscher, Andreas H.

AU - Kim, Stephen H.

PY - 2023

Y1 - 2023

N2 - We have developed a neural network based on algorithm unrolling techniques to overcome challenges in the DOT inverse problem. Results from numerical and phantom experiments show the network’s capability for high-speed and accurate DOT reconstructions.

AB - We have developed a neural network based on algorithm unrolling techniques to overcome challenges in the DOT inverse problem. Results from numerical and phantom experiments show the network’s capability for high-speed and accurate DOT reconstructions.

UR - http://www.scopus.com/inward/record.url?scp=85191320833&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85191320833&partnerID=8YFLogxK

U2 - 10.1364/OMA.2023.JTu4B.7

DO - 10.1364/OMA.2023.JTu4B.7

M3 - Conference contribution

AN - SCOPUS:85191320833

T3 - Optical Manipulation and Its Applications, OMA 2023

BT - Optical Manipulation and Its Applications, OMA 2023

PB - Optical Society of America

T2 - Optical Manipulation and Its Applications, OMA 2023 - Part of Optica Biophotonics Congress: Optics in the Life Sciences 2023

Y2 - 24 April 2023 through 27 April 2023

ER -

Deep Learning for Time-Domain Diffuse Optical Tomography Reconstructions by Unrolling a Sensitivity Equation-based Algorithm

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this