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

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

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish (US)
Title of host publicationNovel Techniques in Microscopy, NTM 2023
PublisherOptical Society of America
ISBN (Electronic)9781957171210
DOIs
StatePublished - 2023
EventNovel Techniques in Microscopy, NTM 2023 - Part of Optica Biophotonics Congress: Optics in the Life Sciences 2023 - Vancouver, Canada
Duration: Apr 24 2023Apr 27 2023

Publication series

NameNovel Techniques in Microscopy, NTM 2023

Conference

ConferenceNovel Techniques in Microscopy, NTM 2023 - Part of Optica Biophotonics Congress: Optics in the Life Sciences 2023
Country/TerritoryCanada
CityVancouver
Period4/24/234/27/23

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Deep Learning for Time-Domain Diffuse Optical Tomography Reconstructions by Unrolling a Sensitivity Equation-based Algorithm'. Together they form a unique fingerprint.

Cite this