Machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures

Abstract We implemented machine learning in the radiation biodosimetry field to quantitatively reconstruct neutron doses in mixed neutron + photon exposures, which are expected in improvised nuclear device detonations. Such individualized reconstructions are crucial for triage and treatment because...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Igor Shuryak, Helen C. Turner, Monica Pujol-Canadell, Jay R. Perrier, Guy Garty, David J. Brenner
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/35230253caf340c5a876ae1e78980dac
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:35230253caf340c5a876ae1e78980dac
record_format	dspace
spelling	oai:doaj.org-article:35230253caf340c5a876ae1e78980dac2021-12-02T14:21:42ZMachine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures10.1038/s41598-021-83575-52045-2322https://doaj.org/article/35230253caf340c5a876ae1e78980dac2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83575-5https://doaj.org/toc/2045-2322Abstract We implemented machine learning in the radiation biodosimetry field to quantitatively reconstruct neutron doses in mixed neutron + photon exposures, which are expected in improvised nuclear device detonations. Such individualized reconstructions are crucial for triage and treatment because neutrons are more biologically damaging than photons. We used a high-throughput micronucleus assay with automated scanning/imaging on lymphocytes from human blood ex-vivo irradiated with 44 different combinations of 0–4 Gy neutrons and 0–15 Gy photons (542 blood samples), which include reanalysis of past experiments. We developed several metrics that describe micronuclei/cell probability distributions in binucleated cells, and used them as predictors in random forest (RF) and XGboost machine learning analyses to reconstruct the neutron dose in each sample. The probability of “overfitting” was minimized by training both algorithms with repeated cross-validation on a randomly-selected subset of the data, and measuring performance on the rest. RF achieved the best performance. Mean R2 for actual vs. reconstructed neutron doses over 300 random training/testing splits was 0.869 (range 0.761 to 0.919) and root mean squared error was 0.239 (0.195 to 0.351) Gy. These results demonstrate the promising potential of machine learning to reconstruct the neutron dose component in clinically-relevant complex radiation exposure scenarios.Igor ShuryakHelen C. TurnerMonica Pujol-CanadellJay R. PerrierGuy GartyDavid J. BrennerNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Igor Shuryak Helen C. Turner Monica Pujol-Canadell Jay R. Perrier Guy Garty David J. Brenner Machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures
description	Abstract We implemented machine learning in the radiation biodosimetry field to quantitatively reconstruct neutron doses in mixed neutron + photon exposures, which are expected in improvised nuclear device detonations. Such individualized reconstructions are crucial for triage and treatment because neutrons are more biologically damaging than photons. We used a high-throughput micronucleus assay with automated scanning/imaging on lymphocytes from human blood ex-vivo irradiated with 44 different combinations of 0–4 Gy neutrons and 0–15 Gy photons (542 blood samples), which include reanalysis of past experiments. We developed several metrics that describe micronuclei/cell probability distributions in binucleated cells, and used them as predictors in random forest (RF) and XGboost machine learning analyses to reconstruct the neutron dose in each sample. The probability of “overfitting” was minimized by training both algorithms with repeated cross-validation on a randomly-selected subset of the data, and measuring performance on the rest. RF achieved the best performance. Mean R2 for actual vs. reconstructed neutron doses over 300 random training/testing splits was 0.869 (range 0.761 to 0.919) and root mean squared error was 0.239 (0.195 to 0.351) Gy. These results demonstrate the promising potential of machine learning to reconstruct the neutron dose component in clinically-relevant complex radiation exposure scenarios.
format	article
author	Igor Shuryak Helen C. Turner Monica Pujol-Canadell Jay R. Perrier Guy Garty David J. Brenner
author_facet	Igor Shuryak Helen C. Turner Monica Pujol-Canadell Jay R. Perrier Guy Garty David J. Brenner
author_sort	Igor Shuryak
title	Machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures
title_short	Machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures
title_full	Machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures
title_fullStr	Machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures
title_full_unstemmed	Machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures
title_sort	machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/35230253caf340c5a876ae1e78980dac
work_keys_str_mv	AT igorshuryak machinelearningmethodologyforhighthroughputpersonalizedneutrondosereconstructioninmixedneutronphotonexposures AT helencturner machinelearningmethodologyforhighthroughputpersonalizedneutrondosereconstructioninmixedneutronphotonexposures AT monicapujolcanadell machinelearningmethodologyforhighthroughputpersonalizedneutrondosereconstructioninmixedneutronphotonexposures AT jayrperrier machinelearningmethodologyforhighthroughputpersonalizedneutrondosereconstructioninmixedneutronphotonexposures AT guygarty machinelearningmethodologyforhighthroughputpersonalizedneutrondosereconstructioninmixedneutronphotonexposures AT davidjbrenner machinelearningmethodologyforhighthroughputpersonalizedneutrondosereconstructioninmixedneutronphotonexposures
_version_	1718391477466300416

Machine learning methodology for high throughput personalized neutron dose reconstruction in mixed neutron + photon exposures

Ejemplares similares