Raman Spectroscopy and Machine Learning for IDH Genotyping of Unprocessed Glioma Biopsies
Isocitrate dehydrogenase (IDH) mutational status is pivotal in the management of gliomas. Patients with IDH-mutated (IDH-MUT) tumors have a better prognosis and benefit more from extended surgical resection than IDH wild-type (IDH-WT). Raman spectroscopy (RS) is a minimally invasive optical techniqu...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/13/16/4196 |
id |
doaj-e934d7714af24cf28a6ccb08e77e93ad |
---|---|
record_format |
Article |
spelling |
doaj-e934d7714af24cf28a6ccb08e77e93ad2021-08-26T13:36:10ZengMDPI AGCancers2072-66942021-08-01134196419610.3390/cancers13164196Raman Spectroscopy and Machine Learning for IDH Genotyping of Unprocessed Glioma BiopsiesTommaso Sciortino0Riccardo Secoli1Ester d’Amico2Sara Moccia3Marco Conti Nibali4Lorenzo Gay5Marco Rossi6Nicolò Pecco7Antonella Castellano8Elena De Momi9Bethania Fernandes10Marco Riva11Lorenzo Bello12Unit of Oncological Neurosurgery, Humanitas Clinical and Research Center—IRCCS, 20089 Rozzano, ItalyThe Hamlyn Centre for Robotic Surgery, Institute of Global Health Innovation, Imperial College London, Exhibition Road, London SW7 2AZ, UKDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133 Milano, ItalyThe BioRobotics Institute and Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, 56127 Pisa, ItalyUnit of Oncological Neurosurgery, Humanitas Clinical and Research Center—IRCCS, 20089 Rozzano, ItalyUnit of Oncological Neurosurgery, Humanitas Clinical and Research Center—IRCCS, 20089 Rozzano, ItalyUnit of Oncological Neurosurgery, Humanitas Clinical and Research Center—IRCCS, 20089 Rozzano, ItalyDepartment of Neuroradiology, IRCCS Ospedale San Raffaele, 20132 Milan, ItalyNeuroradiology Unit, IRCCS San Raffaele and Vita-Salute San Raffaele University, 20132 Milan, ItalyDepartment of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133 Milano, ItalyUnit of Pathology, Humanitas Clinical and Research Center—IRCCS, Via Manzoni 56, 20089 Rozzano, ItalyDepartment of Medical Biotechnology and Translational Medicine, Università degli Studi di Milano, 20122 Milan, ItalyUnit of Oncological Neurosurgery, Humanitas Clinical and Research Center—IRCCS, 20089 Rozzano, ItalyIsocitrate dehydrogenase (IDH) mutational status is pivotal in the management of gliomas. Patients with IDH-mutated (IDH-MUT) tumors have a better prognosis and benefit more from extended surgical resection than IDH wild-type (IDH-WT). Raman spectroscopy (RS) is a minimally invasive optical technique with great potential for intraoperative diagnosis. We evaluated the RS’s ability to characterize the IDH mutational status onto unprocessed glioma biopsies. We extracted 2073 Raman spectra from thirty-eight unprocessed samples. The classification performance was assessed using the eXtreme Gradient Boosted trees (XGB) and Support Vector Machine with Radial Basis Function kernel (RBF-SVM). Measured Raman spectra displayed differences between IDH-MUT and IDH-WT tumor tissue. From the 103 Raman shifts screened as input features, the cross-validation loop identified 52 shifts with the highest performance in the distinction of the two groups. Raman analysis showed differences in spectral features of lipids, collagen, DNA and cholesterol/phospholipids. We were able to distinguish between IDH-MUT and IDH-WT tumors with an accuracy and precision of 87%. RS is a valuable and accurate tool for characterizing the mutational status of IDH mutation in unprocessed glioma samples. This study improves RS knowledge for future personalized surgical strategy or in situ target therapies for glioma tumors.https://www.mdpi.com/2072-6694/13/16/4196raman spectroscopyneuro-oncologyclassificationgliomamachine learningisocitrate dehydrogenase (IDH) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tommaso Sciortino Riccardo Secoli Ester d’Amico Sara Moccia Marco Conti Nibali Lorenzo Gay Marco Rossi Nicolò Pecco Antonella Castellano Elena De Momi Bethania Fernandes Marco Riva Lorenzo Bello |
spellingShingle |
Tommaso Sciortino Riccardo Secoli Ester d’Amico Sara Moccia Marco Conti Nibali Lorenzo Gay Marco Rossi Nicolò Pecco Antonella Castellano Elena De Momi Bethania Fernandes Marco Riva Lorenzo Bello Raman Spectroscopy and Machine Learning for IDH Genotyping of Unprocessed Glioma Biopsies Cancers raman spectroscopy neuro-oncology classification glioma machine learning isocitrate dehydrogenase (IDH) |
author_facet |
Tommaso Sciortino Riccardo Secoli Ester d’Amico Sara Moccia Marco Conti Nibali Lorenzo Gay Marco Rossi Nicolò Pecco Antonella Castellano Elena De Momi Bethania Fernandes Marco Riva Lorenzo Bello |
author_sort |
Tommaso Sciortino |
title |
Raman Spectroscopy and Machine Learning for IDH Genotyping of Unprocessed Glioma Biopsies |
title_short |
Raman Spectroscopy and Machine Learning for IDH Genotyping of Unprocessed Glioma Biopsies |
title_full |
Raman Spectroscopy and Machine Learning for IDH Genotyping of Unprocessed Glioma Biopsies |
title_fullStr |
Raman Spectroscopy and Machine Learning for IDH Genotyping of Unprocessed Glioma Biopsies |
title_full_unstemmed |
Raman Spectroscopy and Machine Learning for IDH Genotyping of Unprocessed Glioma Biopsies |
title_sort |
raman spectroscopy and machine learning for idh genotyping of unprocessed glioma biopsies |
publisher |
MDPI AG |
series |
Cancers |
issn |
2072-6694 |
publishDate |
2021-08-01 |
description |
Isocitrate dehydrogenase (IDH) mutational status is pivotal in the management of gliomas. Patients with IDH-mutated (IDH-MUT) tumors have a better prognosis and benefit more from extended surgical resection than IDH wild-type (IDH-WT). Raman spectroscopy (RS) is a minimally invasive optical technique with great potential for intraoperative diagnosis. We evaluated the RS’s ability to characterize the IDH mutational status onto unprocessed glioma biopsies. We extracted 2073 Raman spectra from thirty-eight unprocessed samples. The classification performance was assessed using the eXtreme Gradient Boosted trees (XGB) and Support Vector Machine with Radial Basis Function kernel (RBF-SVM). Measured Raman spectra displayed differences between IDH-MUT and IDH-WT tumor tissue. From the 103 Raman shifts screened as input features, the cross-validation loop identified 52 shifts with the highest performance in the distinction of the two groups. Raman analysis showed differences in spectral features of lipids, collagen, DNA and cholesterol/phospholipids. We were able to distinguish between IDH-MUT and IDH-WT tumors with an accuracy and precision of 87%. RS is a valuable and accurate tool for characterizing the mutational status of IDH mutation in unprocessed glioma samples. This study improves RS knowledge for future personalized surgical strategy or in situ target therapies for glioma tumors. |
topic |
raman spectroscopy neuro-oncology classification glioma machine learning isocitrate dehydrogenase (IDH) |
url |
https://www.mdpi.com/2072-6694/13/16/4196 |
work_keys_str_mv |
AT tommasosciortino ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT riccardosecoli ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT esterdamico ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT saramoccia ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT marcocontinibali ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT lorenzogay ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT marcorossi ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT nicolopecco ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT antonellacastellano ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT elenademomi ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT bethaniafernandes ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT marcoriva ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies AT lorenzobello ramanspectroscopyandmachinelearningforidhgenotypingofunprocessedgliomabiopsies |
_version_ |
1721194537822453760 |