Predicting meningioma recurrence using spectrochemical analysis of tissues and subsequent predictive computational algorithms. (12th October 2019)

• Record Type: Journal Article
• Authors: Lilo, Taha; Morais, Camilo; Ashton, Kate; Pardilho, Ana; Dawson, Timothy; Gurusinghe, Nihal; Davis, Charles; Martin, Frank
• Is Part Of: Neuro-oncology. Volume 21(2019)Supplement 4
• Page Start: iv5
• Page End: iv5
• Publication Date: 2019-10-12
• Subjects: Brain Neoplasms -- Periodicals; Brain -- Tumors -- Periodicals; Brain -- Cancer -- Periodicals; Nervous system -- Cancer -- Periodicals; 616.99481
• DOI: 10.1093/neuonc/noz167.020
• Languages: English
• ISSNs: 1522-8517

Abstract

Abstract: Introduction: Meningioma recurrence remains a clinical dilemma. This has a significant clinical and huge financial implication. Hence, the search for predictors for meningioma recurrence has become an increasingly urgent research topic in recent years. Objective: Using spectrochemical analytical methods such as attenuated total reflection Fourier-transform infrared (ATR-FTIR) and Raman spectroscopy, our primary objective is to compare the spectral fingerprint signature of WHO grade I meningioma vs. WHO grade I meningioma that recurred. Secondary objectives compare WHO grade I meningioma vs. WHO grade II meningioma and WHO grade II meningioma vs. WHO grade I meningioma recurrence. Materials and Methods: Our selection criteria included convexity meningioma only restricted to Simpson grade I & II only and WHO grade I & grade II only with a minimum 5 years follow up. We obtained tissue from tumour blocks retrieved from the tissue bank. These were sectioned onto slides and de-waxed prior to ATR-FTIR or Raman spectrochemical analysis. Derived spectral datasets were then explored for discriminating features using computational algorithms in the IRootLab toolbox within MATLAB; this allowed for classification and feature extraction. Results: After analysing the data using various classification algorithms with cross-validation to avoid over-fitting of the spectral data, we can readily and blindly segregate those meningioma samples that recurred from those that did not recur in the follow-up timeframe. The forward feature extraction classification algorithms generated results that exhibited excellent sensitivity and specificity, especially with spectra obtained following ATR-FTIR spectroscopy. Our secondary objectives remain to be fully developed.