Abstract 2599: Does tumor volume effect the spectroscopic classification of brain cancer patients

Abstract

Abstract This study focuses on investigating the link between brain tumor volume and the spectroscopic classification between patients with known gliomas and healthy controls. Discrimination of brain cancer vs. non-cancer patients using serum-based ATR-FTIR diagnostics was first developed by Hands et al. achieving sensitivity and specificity values of 92.8% and 91.5% respectively. Cameron et al. then went on to stratifying between specific brain tumor types and was successful in providing a sensitivity of 90.1% and a specificity of 86.3%. Expanding on these studies, it is vital to determine if the size of a tumor has a direct effect on the sensitivity and specificity and whether or not it was only the larger tumors that were being identified as cancerous. A cohort of 90 patients whose tumor volumes were calculated using their MRI images (either T1-weighted contrast enhanced, T2-weighted or FLAIR images), including patients with high-grade glioblastoma multiforme (GBM), and low-grade gliomas such as anaplastic astrocytoma, astrocytoma, oligoastrocytoma and oligodendroglioma, were used for investigation. Utilizing ATR-FTIR spectroscopy coupled with machine learning algorithms these tumor patients were stratified against 87 healthy controls and were classified as either cancer or non-cancer. From these initial findings' sensitivities, specificities and balanced accuracies were greater than 88% and cancer patients with tumor volumes as small as 0.2 cubic cm were correctly identified, demonstrating that classifications are not affected by tumor volume. Both small and low-grade gliomas were identified which shows great promise for this technique to be used as a screening tool or in diagnostics for early detection of brain tumors. Citation Format: Ashton G. Theakstone, Paul M. Brennan, Matthew J. Baker. Does tumor volume effect the spectroscopic classification of brain cancer patients [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2599.