TY - JOUR
T1 - Differentiation of primary CNS lymphoma and glioblastoma using Raman spectroscopy and machine learning algorithms
AU - Klamminger, Gilbert Georg
AU - Klein, Karoline
AU - Mombaerts, Laurent
AU - Jelke, Finn
AU - Mirizzi, Giulia
AU - Slimani, Rédouane
AU - Husch, Andreas
AU - Mittelbronn, Michel
AU - Hertel, Frank
AU - Borgmann, Felix B.Kleine
N1 - Funding Information:
We thank the Fondation Cancer Luxemburg (grant to Frank Hertel, Michel Mittelbronn, Andreas Husch and Felix Kleine Borgmann) for the generous support.
Funding Information:
Michel Mittelbronn would like to thank the Luxembourg National Research Fund (FNR) for the generous support (PEARL P16/BM/11192868 grant).
Publisher Copyright:
© 2021 The author(s).
PY - 2021/10/4
Y1 - 2021/10/4
N2 - Objective and Methods: Timely discrimination between primary CNS lymphoma (PCNSL) and glioblastoma is crucial for diagnosis and therapy, but also determines the intraoperative surgical course. Advanced radiological methods allow for their distinction to a certain extent but ultimately, biopsies are still necessary for final diagnosis. As an upcoming method that enables tissue analysis by tracking changes in the vibrational state of molecules via inelastic scattered photons, we used Raman Spectroscopy (RS) as a label free method to examine specimens of both tumor entities intraoperatively, as well as postoperatively in formalin fixed paraffin embedded (FFPE) samples. Results: We applied and compared statistical performance of linear and nonlinear machine learning algorithms (Logistic Regression, Random Forest and XGBoost), and found that Random Forest classification distinguished the two tumor entities with a balanced accuracy of 82.4% in intraoperative tissue condition and with 94% using measurements of distinct tumor areas on FFPE tissue. Taking a deeper insight into the spectral properties of the tumor entities, we describe different tumor-specific Raman shifts of interest for classification. Conclusions: Due to our findings, we propose RS as an additional tool for fast and non-destructive tumor tissue discrimination, which may help to choose the proper treatment option. RS may further serve as a useful additional tool for neuropathological diagnostics with little requirements for tissue integrity.
AB - Objective and Methods: Timely discrimination between primary CNS lymphoma (PCNSL) and glioblastoma is crucial for diagnosis and therapy, but also determines the intraoperative surgical course. Advanced radiological methods allow for their distinction to a certain extent but ultimately, biopsies are still necessary for final diagnosis. As an upcoming method that enables tissue analysis by tracking changes in the vibrational state of molecules via inelastic scattered photons, we used Raman Spectroscopy (RS) as a label free method to examine specimens of both tumor entities intraoperatively, as well as postoperatively in formalin fixed paraffin embedded (FFPE) samples. Results: We applied and compared statistical performance of linear and nonlinear machine learning algorithms (Logistic Regression, Random Forest and XGBoost), and found that Random Forest classification distinguished the two tumor entities with a balanced accuracy of 82.4% in intraoperative tissue condition and with 94% using measurements of distinct tumor areas on FFPE tissue. Taking a deeper insight into the spectral properties of the tumor entities, we describe different tumor-specific Raman shifts of interest for classification. Conclusions: Due to our findings, we propose RS as an additional tool for fast and non-destructive tumor tissue discrimination, which may help to choose the proper treatment option. RS may further serve as a useful additional tool for neuropathological diagnostics with little requirements for tissue integrity.
KW - Glioblastoma
KW - Machine learning
KW - PCNSL
KW - Raman spectroscopy
UR - http://www.scopus.com/inward/record.url?scp=85129415822&partnerID=8YFLogxK
U2 - 10.17879/freeneuropathology-2021-3458
DO - 10.17879/freeneuropathology-2021-3458
M3 - Article
SN - 2699-4445
VL - 2
JO - Free Neuropathology
JF - Free Neuropathology
M1 - 26
ER -