PATH-45. APOLLO: RAMAN-BASED PATHOLOGY OF MALIGNANT GLIOMA

Adrian Lita, Joel Sjöberg, Stefan Filipescu, Orieta Celiku, Luigia Petre, Mark Gilbert, Houtan Noushmehr, Ion Petre, Mioara Larion

Research output: Contribution to journalArticlepeer-review

Abstract

BACKGROUND: DNA methylation is an essential component for integrative diagnosis of gliomas. Methylation subtype prediction of gliomas is currently done via sample extraction of high-quality DNA (~1ug), methylome profiling, followed by probe identification, curation and subsequent analysis via different random forest classifiers. However, the DNA methylation classification is not always available for all the samples. Examples include when the existing material is not suitable for methylation profiling or the sample is very limiting. Therefore, we hypothesized that Raman spectroscopy might be suitable to predict the glioma methylome, based upon its ability to create a molecular fingerprint of the tumor and would provide biological insights unknown before.
METHODS: Coherent Raman Spectroscopy was used for molecular fingerprinting of the regions of interest
using 1mm2 FFPE tissue spots from 39 patient samples with LGm1 to LGm6 methylation subtypes. Spectral information was then used to train a convolutional neural network (CNN) and develop a prediction algorithm, capable of detecting the glioma methylation subtypes. 70 % of the dataset was used for model training while the remaining 30% for validation. Oversampling was used to obtain a subtype-balanced data distribution. In addition, supervised wrapper methods and random forests were used to identify the top 50 most discriminatory Raman frequencies out of 1738.
RESULTS: We demonstrate that Raman spectroscopy can accurately and rapidly classify gliomas according to their methylation subtype from achieved FFPE samples, which are routinely present in pathological laboratories as a complementary mean to obtain this important classification when other analyses are not available. The most discriminatory frequencies show differential spectral intensities depending upon the glioma subtypes across the larger areas of the tissue.
CONCLUSIONS: The non-destructive nature of this method and the ability to be applied on FFPE samples directly, allows the histopathologist to reuse of the same slide for subsequent staining and downstream analyses.
Original languageEnglish
Pages (from-to)vi125-vi125
Number of pages1
JournalNeuro-Oncology
Volume23
Issue numberSupplement_6
DOIs
Publication statusPublished - 12 Nov 2021
MoE publication typeA1 Journal article-refereed

Keywords

  • dna
  • dna methylation
  • glioma
  • methylation
  • patients' rooms
  • mental recall
  • spectrum analysis
  • raman
  • diagnosis
  • neoplasms
  • pathology
  • malignant
  • precision
  • formalin-fixed paraffin-embedded tissue specimen
  • forests
  • datasets
  • epigenome
  • convolutional neural networks

Fingerprint

Dive into the research topics of 'PATH-45. APOLLO: RAMAN-BASED PATHOLOGY OF MALIGNANT GLIOMA'. Together they form a unique fingerprint.

Cite this