Computational Assessment of Spectral Heterogeneity within Fresh Glioblastoma Tissue Using Raman Spectroscopy and Machine Learning Algorithms
Understanding and classifying inherent tumor heterogeneity is a multimodal approach, which can be undertaken at the genetic, biochemical, or morphological level, among others. Optical spectral methods such as Raman spectroscopy aim at rapid and non-destructive tissue analysis, where each spectrum ge...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1420-3049/29/5/979 |
| _version_ | 1797264191255478272 |
|---|---|
| author | Karoline Klein Gilbert Georg Klamminger Laurent Mombaerts Finn Jelke Isabel Fernandes Arroteia Rédouane Slimani Giulia Mirizzi Andreas Husch Katrin B. M. Frauenknecht Michel Mittelbronn Frank Hertel Felix B. Kleine Borgmann |
| author_facet | Karoline Klein Gilbert Georg Klamminger Laurent Mombaerts Finn Jelke Isabel Fernandes Arroteia Rédouane Slimani Giulia Mirizzi Andreas Husch Katrin B. M. Frauenknecht Michel Mittelbronn Frank Hertel Felix B. Kleine Borgmann |
| author_sort | Karoline Klein |
| collection | DOAJ |
| description | Understanding and classifying inherent tumor heterogeneity is a multimodal approach, which can be undertaken at the genetic, biochemical, or morphological level, among others. Optical spectral methods such as Raman spectroscopy aim at rapid and non-destructive tissue analysis, where each spectrum generated reflects the individual molecular composition of an examined spot within a (heterogenous) tissue sample. Using a combination of supervised and unsupervised machine learning methods as well as a solid database of Raman spectra of native glioblastoma samples, we succeed not only in distinguishing explicit tumor areas—vital tumor tissue and necrotic tumor tissue can correctly be predicted with an accuracy of 76%—but also in determining and classifying different spectral entities within the histomorphologically distinct class of vital tumor tissue. Measurements of non-pathological, autoptic brain tissue hereby serve as a healthy control since their respective spectroscopic properties form an individual and reproducible cluster within the spectral heterogeneity of a vital tumor sample. The demonstrated decipherment of a spectral glioblastoma heterogeneity will be valuable, especially in the field of spectroscopically guided surgery to delineate tumor margins and to assist resection control. |
| first_indexed | 2024-04-25T00:24:58Z |
| format | Article |
| id | doaj.art-f15a9d3c5f564a2a942e2fdef5709b92 |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-04-25T00:24:58Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-f15a9d3c5f564a2a942e2fdef5709b922024-03-12T16:50:38ZengMDPI AGMolecules1420-30492024-02-0129597910.3390/molecules29050979Computational Assessment of Spectral Heterogeneity within Fresh Glioblastoma Tissue Using Raman Spectroscopy and Machine Learning AlgorithmsKaroline Klein0Gilbert Georg Klamminger1Laurent Mombaerts2Finn Jelke3Isabel Fernandes Arroteia4Rédouane Slimani5Giulia Mirizzi6Andreas Husch7Katrin B. M. Frauenknecht8Michel Mittelbronn9Frank Hertel10Felix B. Kleine Borgmann11Faculty of Medicine, Saarland University (USAAR), 66424 Homburg, GermanyDepartment of General and Special Pathology, Saarland University (USAAR), 66424 Homburg, GermanyLuxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg (UL), 4362 Esch-sur-Alzette, LuxembourgNational Center of Neurosurgery, Centre Hospitalier de Luxembourg (CHL), 1210 Luxembourg, LuxembourgNational Center of Neurosurgery, Centre Hospitalier de Luxembourg (CHL), 1210 Luxembourg, LuxembourgDoctoral School in Science and Engineering (DSSE), University of Luxembourg (UL), 4362 Esch-sur-Alzette, LuxembourgFaculty of Medicine, Saarland University (USAAR), 66424 Homburg, GermanyNational Center of Neurosurgery, Centre Hospitalier de Luxembourg (CHL), 1210 Luxembourg, LuxembourgNational Center of Pathology (NCP), Laboratoire National de Santé (LNS), 3555 Dudelange, LuxembourgNational Center of Pathology (NCP), Laboratoire National de Santé (LNS), 3555 Dudelange, LuxembourgFaculty of Medicine, Saarland University (USAAR), 66424 Homburg, GermanyFaculty of Medicine, Saarland University (USAAR), 66424 Homburg, GermanyUnderstanding and classifying inherent tumor heterogeneity is a multimodal approach, which can be undertaken at the genetic, biochemical, or morphological level, among others. Optical spectral methods such as Raman spectroscopy aim at rapid and non-destructive tissue analysis, where each spectrum generated reflects the individual molecular composition of an examined spot within a (heterogenous) tissue sample. Using a combination of supervised and unsupervised machine learning methods as well as a solid database of Raman spectra of native glioblastoma samples, we succeed not only in distinguishing explicit tumor areas—vital tumor tissue and necrotic tumor tissue can correctly be predicted with an accuracy of 76%—but also in determining and classifying different spectral entities within the histomorphologically distinct class of vital tumor tissue. Measurements of non-pathological, autoptic brain tissue hereby serve as a healthy control since their respective spectroscopic properties form an individual and reproducible cluster within the spectral heterogeneity of a vital tumor sample. The demonstrated decipherment of a spectral glioblastoma heterogeneity will be valuable, especially in the field of spectroscopically guided surgery to delineate tumor margins and to assist resection control.https://www.mdpi.com/1420-3049/29/5/979Raman spectroscopyvibrational spectroscopyglioblastomabrain tumorheterogeneitymachine learning |
| spellingShingle | Karoline Klein Gilbert Georg Klamminger Laurent Mombaerts Finn Jelke Isabel Fernandes Arroteia Rédouane Slimani Giulia Mirizzi Andreas Husch Katrin B. M. Frauenknecht Michel Mittelbronn Frank Hertel Felix B. Kleine Borgmann Computational Assessment of Spectral Heterogeneity within Fresh Glioblastoma Tissue Using Raman Spectroscopy and Machine Learning Algorithms Molecules Raman spectroscopy vibrational spectroscopy glioblastoma brain tumor heterogeneity machine learning |
| title | Computational Assessment of Spectral Heterogeneity within Fresh Glioblastoma Tissue Using Raman Spectroscopy and Machine Learning Algorithms |
| title_full | Computational Assessment of Spectral Heterogeneity within Fresh Glioblastoma Tissue Using Raman Spectroscopy and Machine Learning Algorithms |
| title_fullStr | Computational Assessment of Spectral Heterogeneity within Fresh Glioblastoma Tissue Using Raman Spectroscopy and Machine Learning Algorithms |
| title_full_unstemmed | Computational Assessment of Spectral Heterogeneity within Fresh Glioblastoma Tissue Using Raman Spectroscopy and Machine Learning Algorithms |
| title_short | Computational Assessment of Spectral Heterogeneity within Fresh Glioblastoma Tissue Using Raman Spectroscopy and Machine Learning Algorithms |
| title_sort | computational assessment of spectral heterogeneity within fresh glioblastoma tissue using raman spectroscopy and machine learning algorithms |
| topic | Raman spectroscopy vibrational spectroscopy glioblastoma brain tumor heterogeneity machine learning |
| url | https://www.mdpi.com/1420-3049/29/5/979 |
| work_keys_str_mv | AT karolineklein computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT gilbertgeorgklamminger computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT laurentmombaerts computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT finnjelke computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT isabelfernandesarroteia computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT redouaneslimani computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT giuliamirizzi computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT andreashusch computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT katrinbmfrauenknecht computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT michelmittelbronn computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT frankhertel computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms AT felixbkleineborgmann computationalassessmentofspectralheterogeneitywithinfreshglioblastomatissueusingramanspectroscopyandmachinelearningalgorithms |