Cargando…
Deep learning in macroscopic diffuse optical imaging
SIGNIFICANCE: Biomedical optics system design, image formation, and image analysis have primarily been guided by classical physical modeling and signal processing methodologies. Recently, however, deep learning (DL) has become a major paradigm in computational modeling and has demonstrated utility i...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Society of Photo-Optical Instrumentation Engineers
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8881080/ https://www.ncbi.nlm.nih.gov/pubmed/35218169 http://dx.doi.org/10.1117/1.JBO.27.2.020901 |
_version_ | 1784659383161978880 |
---|---|
author | Smith, Jason T. Ochoa, Marien Faulkner, Denzel Haskins, Grant Intes, Xavier |
author_facet | Smith, Jason T. Ochoa, Marien Faulkner, Denzel Haskins, Grant Intes, Xavier |
author_sort | Smith, Jason T. |
collection | PubMed |
description | SIGNIFICANCE: Biomedical optics system design, image formation, and image analysis have primarily been guided by classical physical modeling and signal processing methodologies. Recently, however, deep learning (DL) has become a major paradigm in computational modeling and has demonstrated utility in numerous scientific domains and various forms of data analysis. AIM: We aim to comprehensively review the use of DL applied to macroscopic diffuse optical imaging (DOI). APPROACH: First, we provide a layman introduction to DL. Then, the review summarizes current DL work in some of the most active areas of this field, including optical properties retrieval, fluorescence lifetime imaging, and diffuse optical tomography. RESULTS: The advantages of using DL for DOI versus conventional inverse solvers cited in the literature reviewed herein are numerous. These include, among others, a decrease in analysis time (often by many orders of magnitude), increased quantitative reconstruction quality, robustness to noise, and the unique capability to learn complex end-to-end relationships. CONCLUSIONS: The heavily validated capability of DL’s use across a wide range of complex inverse solving methodologies has enormous potential to bring novel DOI modalities, otherwise deemed impractical for clinical translation, to the patient’s bedside. |
format | Online Article Text |
id | pubmed-8881080 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Society of Photo-Optical Instrumentation Engineers |
record_format | MEDLINE/PubMed |
spelling | pubmed-88810802022-02-27 Deep learning in macroscopic diffuse optical imaging Smith, Jason T. Ochoa, Marien Faulkner, Denzel Haskins, Grant Intes, Xavier J Biomed Opt Review Papers SIGNIFICANCE: Biomedical optics system design, image formation, and image analysis have primarily been guided by classical physical modeling and signal processing methodologies. Recently, however, deep learning (DL) has become a major paradigm in computational modeling and has demonstrated utility in numerous scientific domains and various forms of data analysis. AIM: We aim to comprehensively review the use of DL applied to macroscopic diffuse optical imaging (DOI). APPROACH: First, we provide a layman introduction to DL. Then, the review summarizes current DL work in some of the most active areas of this field, including optical properties retrieval, fluorescence lifetime imaging, and diffuse optical tomography. RESULTS: The advantages of using DL for DOI versus conventional inverse solvers cited in the literature reviewed herein are numerous. These include, among others, a decrease in analysis time (often by many orders of magnitude), increased quantitative reconstruction quality, robustness to noise, and the unique capability to learn complex end-to-end relationships. CONCLUSIONS: The heavily validated capability of DL’s use across a wide range of complex inverse solving methodologies has enormous potential to bring novel DOI modalities, otherwise deemed impractical for clinical translation, to the patient’s bedside. Society of Photo-Optical Instrumentation Engineers 2022-02-25 2022-02 /pmc/articles/PMC8881080/ /pubmed/35218169 http://dx.doi.org/10.1117/1.JBO.27.2.020901 Text en © 2022 The Authors https://creativecommons.org/licenses/by/4.0/Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. |
spellingShingle | Review Papers Smith, Jason T. Ochoa, Marien Faulkner, Denzel Haskins, Grant Intes, Xavier Deep learning in macroscopic diffuse optical imaging |
title | Deep learning in macroscopic diffuse optical imaging |
title_full | Deep learning in macroscopic diffuse optical imaging |
title_fullStr | Deep learning in macroscopic diffuse optical imaging |
title_full_unstemmed | Deep learning in macroscopic diffuse optical imaging |
title_short | Deep learning in macroscopic diffuse optical imaging |
title_sort | deep learning in macroscopic diffuse optical imaging |
topic | Review Papers |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8881080/ https://www.ncbi.nlm.nih.gov/pubmed/35218169 http://dx.doi.org/10.1117/1.JBO.27.2.020901 |
work_keys_str_mv | AT smithjasont deeplearninginmacroscopicdiffuseopticalimaging AT ochoamarien deeplearninginmacroscopicdiffuseopticalimaging AT faulknerdenzel deeplearninginmacroscopicdiffuseopticalimaging AT haskinsgrant deeplearninginmacroscopicdiffuseopticalimaging AT intesxavier deeplearninginmacroscopicdiffuseopticalimaging |