TY - JOUR
T1 - Computational Assessment of Spectral Heterogeneity within Fresh Glioblastoma Tissue Using Raman Spectroscopy and Machine Learning Algorithms
AU - Klein, Karoline
AU - Klamminger, Gilbert Georg
AU - Mombaerts, Laurent
AU - Jelke, Finn
AU - Arroteia, Isabel Fernandes
AU - Slimani, Rédouane
AU - Mirizzi, Giulia
AU - Husch, Andreas
AU - Frauenknecht, Katrin B.M.
AU - Mittelbronn, Michel
AU - Hertel, Frank
AU - Kleine Borgmann, Felix B.
N1 - Funding: This research was funded by Foundation Cancer Luxembourg supporting F.B.K.B., A.H.
and F.H. In addition, M.M. received funding from the Luxembourg National Research Fund (FNR
PEARL P16/BM/11192868).
Publisher Copyright:
© 2024 by the authors.
PY - 2024/2/23
Y1 - 2024/2/23
N2 - 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.
AB - 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.
KW - brain tumor
KW - glioblastoma
KW - heterogeneity
KW - machine learning
KW - Raman spectroscopy
KW - unsupervised learning
KW - vibrational spectroscopy
UR - http://www.scopus.com/inward/record.url?scp=85187798897&partnerID=8YFLogxK
UR - https://pubmed.ncbi.nlm.nih.gov/38474491
U2 - 10.3390/molecules29050979
DO - 10.3390/molecules29050979
M3 - Article
C2 - 38474491
AN - SCOPUS:85187798897
SN - 1420-3049
VL - 29
JO - Molecules
JF - Molecules
IS - 5
M1 - 979
ER -