Raman spectroscopy and artificial intelligence to predict the Bayesian probability of breast cancer

Abstract This study addresses the core issue facing a surgical team during breast cancer surgery: quantitative prediction of tumor likelihood including estimates of prediction error. We have previously reported that a molecular probe, Laser Raman spectroscopy (LRS), can distinguish healthy and tumor...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ragini Kothari, Veronica Jones, Dominique Mena, Viviana Bermúdez Reyes, Youkang Shon, Jennifer P. Smith, Daniel Schmolze, Philip D. Cha, Lily Lai, Yuman Fong, Michael C. Storrie-Lombardi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/74b8e0603ab6427490c20c75e6ad68da
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:74b8e0603ab6427490c20c75e6ad68da
record_format	dspace
spelling	oai:doaj.org-article:74b8e0603ab6427490c20c75e6ad68da2021-12-02T14:02:55ZRaman spectroscopy and artificial intelligence to predict the Bayesian probability of breast cancer10.1038/s41598-021-85758-62045-2322https://doaj.org/article/74b8e0603ab6427490c20c75e6ad68da2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85758-6https://doaj.org/toc/2045-2322Abstract This study addresses the core issue facing a surgical team during breast cancer surgery: quantitative prediction of tumor likelihood including estimates of prediction error. We have previously reported that a molecular probe, Laser Raman spectroscopy (LRS), can distinguish healthy and tumor tissue. We now report that combining LRS with two machine learning algorithms, unsupervised k-means and stochastic nonlinear neural networks (NN), provides rapid, quantitative, probabilistic tumor assessment with real-time error analysis. NNs were first trained on Raman spectra using human expert histopathology diagnostics as gold standard (74 spectra, 5 patients). K-means predictions using spectral data when compared to histopathology produced clustering models with 93.2–94.6% accuracy, 89.8–91.8% sensitivity, and 100% specificity. NNs trained on k-means predictions generated probabilities of correctness for the autonomous classification. Finally, the autonomous system characterized an extended dataset (203 spectra, 8 patients). Our results show that an increase in DNA\|RNA signal intensity in the fingerprint region (600–1800 cm−1) and global loss of high wavenumber signal (2800–3200 cm−1) are particularly sensitive LRS warning signs of tumor. The stochastic nature of NNs made it possible to rapidly generate multiple models of target tissue classification and calculate the inherent error in the probabilistic estimates for each target.Ragini KothariVeronica JonesDominique MenaViviana Bermúdez ReyesYoukang ShonJennifer P. SmithDaniel SchmolzePhilip D. ChaLily LaiYuman FongMichael C. Storrie-LombardiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-17 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ragini Kothari Veronica Jones Dominique Mena Viviana Bermúdez Reyes Youkang Shon Jennifer P. Smith Daniel Schmolze Philip D. Cha Lily Lai Yuman Fong Michael C. Storrie-Lombardi Raman spectroscopy and artificial intelligence to predict the Bayesian probability of breast cancer
description	Abstract This study addresses the core issue facing a surgical team during breast cancer surgery: quantitative prediction of tumor likelihood including estimates of prediction error. We have previously reported that a molecular probe, Laser Raman spectroscopy (LRS), can distinguish healthy and tumor tissue. We now report that combining LRS with two machine learning algorithms, unsupervised k-means and stochastic nonlinear neural networks (NN), provides rapid, quantitative, probabilistic tumor assessment with real-time error analysis. NNs were first trained on Raman spectra using human expert histopathology diagnostics as gold standard (74 spectra, 5 patients). K-means predictions using spectral data when compared to histopathology produced clustering models with 93.2–94.6% accuracy, 89.8–91.8% sensitivity, and 100% specificity. NNs trained on k-means predictions generated probabilities of correctness for the autonomous classification. Finally, the autonomous system characterized an extended dataset (203 spectra, 8 patients). Our results show that an increase in DNA\|RNA signal intensity in the fingerprint region (600–1800 cm−1) and global loss of high wavenumber signal (2800–3200 cm−1) are particularly sensitive LRS warning signs of tumor. The stochastic nature of NNs made it possible to rapidly generate multiple models of target tissue classification and calculate the inherent error in the probabilistic estimates for each target.
format	article
author	Ragini Kothari Veronica Jones Dominique Mena Viviana Bermúdez Reyes Youkang Shon Jennifer P. Smith Daniel Schmolze Philip D. Cha Lily Lai Yuman Fong Michael C. Storrie-Lombardi
author_facet	Ragini Kothari Veronica Jones Dominique Mena Viviana Bermúdez Reyes Youkang Shon Jennifer P. Smith Daniel Schmolze Philip D. Cha Lily Lai Yuman Fong Michael C. Storrie-Lombardi
author_sort	Ragini Kothari
title	Raman spectroscopy and artificial intelligence to predict the Bayesian probability of breast cancer
title_short	Raman spectroscopy and artificial intelligence to predict the Bayesian probability of breast cancer
title_full	Raman spectroscopy and artificial intelligence to predict the Bayesian probability of breast cancer
title_fullStr	Raman spectroscopy and artificial intelligence to predict the Bayesian probability of breast cancer
title_full_unstemmed	Raman spectroscopy and artificial intelligence to predict the Bayesian probability of breast cancer
title_sort	raman spectroscopy and artificial intelligence to predict the bayesian probability of breast cancer
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/74b8e0603ab6427490c20c75e6ad68da
work_keys_str_mv	AT raginikothari ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT veronicajones ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT dominiquemena ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT vivianabermudezreyes ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT youkangshon ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT jenniferpsmith ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT danielschmolze ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT philipdcha ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT lilylai ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT yumanfong ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer AT michaelcstorrielombardi ramanspectroscopyandartificialintelligencetopredictthebayesianprobabilityofbreastcancer
_version_	1718392088573247488

Raman spectroscopy and artificial intelligence to predict the Bayesian probability of breast cancer

Ejemplares similares