Modeling and synthesis of breast cancer optical property signatures with generative models

Is it possible to find deterministic relationships between optical measurements and pathophysiology in an unsupervised manner and based on data alone? Optical property quantification is a rapidly growing biomedical imaging technique for characterizing biological tissues that shows promise in a range...

Descripción completa

Detalles Bibliográficos
Autores: Pardo Franco, Arturo|||0000-0003-3362-3485, Streeter, Samuel S., Maloney, Benjamin W., Gutiérrez Gutiérrez, José Alberto|||0000-0002-9822-9406, McClatchy, David M., Wells, Wendy A., Paulsen, Keith D., López Higuera, José Miguel|||0000-0002-8615-8487, Pogue, Brian William, Conde Portilla, Olga María|||0000-0002-2471-3051
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universidad de Cantabria (UC)
Repositorio:UCrea Repositorio Abierto de la Universidad de Cantabria
Idioma:inglés
OAI Identifier:oai:repositorio.unican.es:10902/21833
Acceso en línea:http://hdl.handle.net/10902/21833
Access Level:acceso abierto
Palabra clave:Biomedical optical imaging
Breast cancer
Tissue optical properties
Modeling
Pathology
Deep learning
Dimensionality reduction
Variational autoencoder
Convolutional neural networks
id ES_a0f7cabb6df75ef8e89eb404c7a78115
oai_identifier_str oai:repositorio.unican.es:10902/21833
network_acronym_str ES
network_name_str España
repository_id_str
spelling Modeling and synthesis of breast cancer optical property signatures with generative modelsPardo Franco, Arturo|||0000-0003-3362-3485Streeter, Samuel S.Maloney, Benjamin W.Gutiérrez Gutiérrez, José Alberto|||0000-0002-9822-9406McClatchy, David M.Wells, Wendy A.Paulsen, Keith D.López Higuera, José Miguel|||0000-0002-8615-8487Pogue, Brian WilliamConde Portilla, Olga María|||0000-0002-2471-3051Biomedical optical imagingBreast cancerTissue optical propertiesModelingPathologyDeep learningDimensionality reductionVariational autoencoderConvolutional neural networksIs it possible to find deterministic relationships between optical measurements and pathophysiology in an unsupervised manner and based on data alone? Optical property quantification is a rapidly growing biomedical imaging technique for characterizing biological tissues that shows promise in a range of clinical applications, such as intraoperative breast-conserving surgery margin assessment. However, translating tissue optical properties to clinical pathology information is still a cumbersome problem due to, amongst other things, inter- and intrapatient variability, calibration, and ultimately the nonlinear behavior of light in turbid media. These challenges limit the ability of standard statistical methods to generate a simple model of pathology, requiring more advanced algorithms. We present a data-driven, nonlinear model of breast cancer pathology for real-time margin assessment of resected samples using optical properties derived from spatial frequency domain imaging data. A series of deep neural network models are employed to obtain sets of latent embeddings that relate optical data signatures to the underlying tissue pathology in a tractable manner. These self-explanatory models can translate absorption and scattering properties measured from pathology, while also being able to synthesize new data. The method was tested on a total of 70 resected breast tissue samples containing 137 regions of interest, achieving rapid optical property modeling with errors only limited by current semi-empirical models, allowing for mass sample synthesis and providing a systematic understanding of dataset properties, paving the way for deep automated margin assessment algorithms using structured light imaging or, in principle, any other optical imaging technique seeking modeling. Code is available.This work was supported in part by the National Cancer Institute, US National Institutes of Health, under grants R01 CA192803 and F31 CA196308, by the Spanish Ministry of Science and Innovation under grant FIS2010-19860, by the Spanish Ministry of Science, Innovation and Universities under grants TEC2016-76021-C2-2-R and PID2019-107270RB-C21, by the Spanish Minstry of Economy, Industry and Competitiveness and Instituto de Salud Carlos III via DTS17-00055, by IDIVAL under grants INNVAL 16/02, and INNVAL 18/23, and by the Spanish Ministry of Education, Culture, and Sports with PhD grant FPU16/05705, as well as FEDER funds.Institute of Electrical and Electronics Engineers Inc.Universidad de Cantabria20212021-06-01journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articlehttp://hdl.handle.net/10902/21833IEEE Transactions on Medical Imaging, 2021, 40(6), 1687-1701reponame:UCrea Repositorio Abierto de la Universidad de Cantabriainstname:Universidad de Cantabria (UC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:repositorio.unican.es:10902/218332026-06-02T12:39:31Z
dc.title.none.fl_str_mv Modeling and synthesis of breast cancer optical property signatures with generative models
title Modeling and synthesis of breast cancer optical property signatures with generative models
spellingShingle Modeling and synthesis of breast cancer optical property signatures with generative models
Pardo Franco, Arturo|||0000-0003-3362-3485
Biomedical optical imaging
Breast cancer
Tissue optical properties
Modeling
Pathology
Deep learning
Dimensionality reduction
Variational autoencoder
Convolutional neural networks
title_short Modeling and synthesis of breast cancer optical property signatures with generative models
title_full Modeling and synthesis of breast cancer optical property signatures with generative models
title_fullStr Modeling and synthesis of breast cancer optical property signatures with generative models
title_full_unstemmed Modeling and synthesis of breast cancer optical property signatures with generative models
title_sort Modeling and synthesis of breast cancer optical property signatures with generative models
dc.creator.none.fl_str_mv Pardo Franco, Arturo|||0000-0003-3362-3485
Streeter, Samuel S.
Maloney, Benjamin W.
Gutiérrez Gutiérrez, José Alberto|||0000-0002-9822-9406
McClatchy, David M.
Wells, Wendy A.
Paulsen, Keith D.
López Higuera, José Miguel|||0000-0002-8615-8487
Pogue, Brian William
Conde Portilla, Olga María|||0000-0002-2471-3051
author Pardo Franco, Arturo|||0000-0003-3362-3485
author_facet Pardo Franco, Arturo|||0000-0003-3362-3485
Streeter, Samuel S.
Maloney, Benjamin W.
Gutiérrez Gutiérrez, José Alberto|||0000-0002-9822-9406
McClatchy, David M.
Wells, Wendy A.
Paulsen, Keith D.
López Higuera, José Miguel|||0000-0002-8615-8487
Pogue, Brian William
Conde Portilla, Olga María|||0000-0002-2471-3051
author_role author
author2 Streeter, Samuel S.
Maloney, Benjamin W.
Gutiérrez Gutiérrez, José Alberto|||0000-0002-9822-9406
McClatchy, David M.
Wells, Wendy A.
Paulsen, Keith D.
López Higuera, José Miguel|||0000-0002-8615-8487
Pogue, Brian William
Conde Portilla, Olga María|||0000-0002-2471-3051
author2_role author
author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Universidad de Cantabria
dc.subject.none.fl_str_mv Biomedical optical imaging
Breast cancer
Tissue optical properties
Modeling
Pathology
Deep learning
Dimensionality reduction
Variational autoencoder
Convolutional neural networks
topic Biomedical optical imaging
Breast cancer
Tissue optical properties
Modeling
Pathology
Deep learning
Dimensionality reduction
Variational autoencoder
Convolutional neural networks
description Is it possible to find deterministic relationships between optical measurements and pathophysiology in an unsupervised manner and based on data alone? Optical property quantification is a rapidly growing biomedical imaging technique for characterizing biological tissues that shows promise in a range of clinical applications, such as intraoperative breast-conserving surgery margin assessment. However, translating tissue optical properties to clinical pathology information is still a cumbersome problem due to, amongst other things, inter- and intrapatient variability, calibration, and ultimately the nonlinear behavior of light in turbid media. These challenges limit the ability of standard statistical methods to generate a simple model of pathology, requiring more advanced algorithms. We present a data-driven, nonlinear model of breast cancer pathology for real-time margin assessment of resected samples using optical properties derived from spatial frequency domain imaging data. A series of deep neural network models are employed to obtain sets of latent embeddings that relate optical data signatures to the underlying tissue pathology in a tractable manner. These self-explanatory models can translate absorption and scattering properties measured from pathology, while also being able to synthesize new data. The method was tested on a total of 70 resected breast tissue samples containing 137 regions of interest, achieving rapid optical property modeling with errors only limited by current semi-empirical models, allowing for mass sample synthesis and providing a systematic understanding of dataset properties, paving the way for deep automated margin assessment algorithms using structured light imaging or, in principle, any other optical imaging technique seeking modeling. Code is available.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-06-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10902/21833
url http://hdl.handle.net/10902/21833
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers Inc.
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers Inc.
dc.source.none.fl_str_mv IEEE Transactions on Medical Imaging, 2021, 40(6), 1687-1701
reponame:UCrea Repositorio Abierto de la Universidad de Cantabria
instname:Universidad de Cantabria (UC)
instname_str Universidad de Cantabria (UC)
reponame_str UCrea Repositorio Abierto de la Universidad de Cantabria
collection UCrea Repositorio Abierto de la Universidad de Cantabria
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869415088983638016
score 15,301603