Cargando…

Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications

SIGNIFICANCE: Deep learning (DL) models are being increasingly developed to map sensor data to the image domain directly. However, DL methodologies are data-driven and require large and diverse data sets to provide robust and accurate image formation performances. For research modalities such as 2D/...

Descripción completa

Detalles Bibliográficos
Autores principales: Nizam, Navid Ibtehaj, Ochoa, Marien, Smith, Jason T., Gao, Shan, Intes, Xavier
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/PMC9048385/
https://www.ncbi.nlm.nih.gov/pubmed/35484688
http://dx.doi.org/10.1117/1.JBO.27.8.083016
_version_ 1784695915870683136
author Nizam, Navid Ibtehaj
Ochoa, Marien
Smith, Jason T.
Gao, Shan
Intes, Xavier
author_facet Nizam, Navid Ibtehaj
Ochoa, Marien
Smith, Jason T.
Gao, Shan
Intes, Xavier
author_sort Nizam, Navid Ibtehaj
collection PubMed
description SIGNIFICANCE: Deep learning (DL) models are being increasingly developed to map sensor data to the image domain directly. However, DL methodologies are data-driven and require large and diverse data sets to provide robust and accurate image formation performances. For research modalities such as 2D/3D diffuse optical imaging, the lack of large publicly available data sets and the wide variety of instrumentation designs, data types, and applications leads to unique challenges in obtaining well-controlled data sets for training and validation. Meanwhile, great efforts over the last four decades have focused on developing accurate and computationally efficient light propagation models that are flexible enough to simulate a wide variety of experimental conditions. AIM: Recent developments in Monte Carlo (MC)-based modeling offer the unique advantage of simulating accurately light propagation spatially, temporally, and over an extensive range of optical parameters, including minimally to highly scattering tissue within a computationally efficient platform. Herein, we demonstrate how such MC platforms, namely “Monte Carlo eXtreme” and “Mesh-based Monte Carlo,” can be leveraged to generate large and representative data sets for training the DL model efficiently. APPROACH: We propose data generator pipeline strategies using these platforms and demonstrate their potential in fluorescence optical topography, fluorescence optical tomography, and single-pixel diffuse optical tomography. These applications represent a large variety in instrumentation design, sample properties, and contrast function. RESULTS: DL models trained using the MC-based in silico datasets, validated further with experimental data not used during training, show accurate and promising results. CONCLUSION: Overall, these MC-based data generation pipelines are expected to support the development of DL models for rapid, robust, and user-friendly image formation in a wide variety of applications.
format Online
Article
Text
id pubmed-9048385
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Society of Photo-Optical Instrumentation Engineers
record_format MEDLINE/PubMed
spelling pubmed-90483852022-04-29 Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications Nizam, Navid Ibtehaj Ochoa, Marien Smith, Jason T. Gao, Shan Intes, Xavier J Biomed Opt Special Section Celebrating 30 Years of Open Source Monte Carlo Codes in Biomedical Optics SIGNIFICANCE: Deep learning (DL) models are being increasingly developed to map sensor data to the image domain directly. However, DL methodologies are data-driven and require large and diverse data sets to provide robust and accurate image formation performances. For research modalities such as 2D/3D diffuse optical imaging, the lack of large publicly available data sets and the wide variety of instrumentation designs, data types, and applications leads to unique challenges in obtaining well-controlled data sets for training and validation. Meanwhile, great efforts over the last four decades have focused on developing accurate and computationally efficient light propagation models that are flexible enough to simulate a wide variety of experimental conditions. AIM: Recent developments in Monte Carlo (MC)-based modeling offer the unique advantage of simulating accurately light propagation spatially, temporally, and over an extensive range of optical parameters, including minimally to highly scattering tissue within a computationally efficient platform. Herein, we demonstrate how such MC platforms, namely “Monte Carlo eXtreme” and “Mesh-based Monte Carlo,” can be leveraged to generate large and representative data sets for training the DL model efficiently. APPROACH: We propose data generator pipeline strategies using these platforms and demonstrate their potential in fluorescence optical topography, fluorescence optical tomography, and single-pixel diffuse optical tomography. These applications represent a large variety in instrumentation design, sample properties, and contrast function. RESULTS: DL models trained using the MC-based in silico datasets, validated further with experimental data not used during training, show accurate and promising results. CONCLUSION: Overall, these MC-based data generation pipelines are expected to support the development of DL models for rapid, robust, and user-friendly image formation in a wide variety of applications. Society of Photo-Optical Instrumentation Engineers 2022-04-28 2022-08 /pmc/articles/PMC9048385/ /pubmed/35484688 http://dx.doi.org/10.1117/1.JBO.27.8.083016 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 Special Section Celebrating 30 Years of Open Source Monte Carlo Codes in Biomedical Optics
Nizam, Navid Ibtehaj
Ochoa, Marien
Smith, Jason T.
Gao, Shan
Intes, Xavier
Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications
title Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications
title_full Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications
title_fullStr Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications
title_full_unstemmed Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications
title_short Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications
title_sort monte carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications
topic Special Section Celebrating 30 Years of Open Source Monte Carlo Codes in Biomedical Optics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9048385/
https://www.ncbi.nlm.nih.gov/pubmed/35484688
http://dx.doi.org/10.1117/1.JBO.27.8.083016
work_keys_str_mv AT nizamnavidibtehaj montecarlobaseddatagenerationforefficientdeeplearningreconstructionofmacroscopicdiffuseopticaltomographyandtopographyapplications
AT ochoamarien montecarlobaseddatagenerationforefficientdeeplearningreconstructionofmacroscopicdiffuseopticaltomographyandtopographyapplications
AT smithjasont montecarlobaseddatagenerationforefficientdeeplearningreconstructionofmacroscopicdiffuseopticaltomographyandtopographyapplications
AT gaoshan montecarlobaseddatagenerationforefficientdeeplearningreconstructionofmacroscopicdiffuseopticaltomographyandtopographyapplications
AT intesxavier montecarlobaseddatagenerationforefficientdeeplearningreconstructionofmacroscopicdiffuseopticaltomographyandtopographyapplications