Raman Spectroscopy and Machine Learning for IDH Genotyping of Unprocessed Glioma Biopsies

Abstract

Isocitrate dehydrogenase (IDH) mutational status is pivotal in the management of gliomas. Patients with IDH-mutated (IDH-MUT) tumors have a better prognosis and benefit more from extended surgical resection than IDH wild-type (IDH-WT). Raman spectroscopy (RS) is a minimally invasive optical technique with great potential for intraoperative diagnosis. We evaluated the RS’s ability to characterize the IDH mutational status onto unprocessed glioma biopsies. We extracted 2073 Raman spectra from thirty-eight unprocessed samples. The classification performance was assessed using the eXtreme Gradient Boosted trees (XGB) and Support Vector Machine with Radial Basis Function kernel (RBF-SVM). Measured Raman spectra displayed differences between IDH-MUT and IDH-WT tumor tissue. From the 103 Raman shifts screened as input features, the cross-validation loop identified 52 shifts with the highest performance in the distinction of the two groups. Raman analysis showed differences in spectral features of lipids, collagen, DNA and cholesterol/phospholipids. We were able to distinguish between IDH-MUT and IDH-WT tumors with an accuracy and precision of 87%. RS is a valuable and accurate tool for characterizing the mutational status of IDH mutation in unprocessed glioma samples. This study improves RS knowledge for future personalized surgical strategy or in situ target therapies for glioma tumors.

Machine Learning of Raman Spectroscopy Data for Classifying Cancers: A Review of the Recent Literature

“…The latter model performed best because its feature selection allowed the detection of novel Raman peaks to be implicated in gliomas. In the team’s second study, Sciotino et al explored the potential to discriminate between the mutational status of gliomas, essentially attempting to genotype using RS [ 32 ]. They used GB and SVM (RBF) to successfully classify between the two disease genotypes.…”

“…Of those studies that split the data at the level of spectra, the best accuracies of 90%, 96.6%, 97.7%, 93.8% and 94.8% were achieved [ 19 , 25 , 26 , 29 , 35 ]. Of those studies splitting data at the level of subject or sample, the accuracies were: 84.4%, 99%, 81.8%, 98.3%, 83%, 87%, 92.9%, 81.3% and 62.5% [ 20 , 22 , 24 , 30 , 31 , 32 , 34 , 35 , 40 ]. Of those studies in which the level of split was not explicitly stated, the accuracies were: 86.0%, 96.7%, 80.2%, 99.0%, 92.0%, 90.5%, 99.5%, 98.8%, 96.9% and 99.0% [ 16 , 17 , 18 , 21 , 27 , 33 , 36 , 37 , 38 , 39 ].…”

“…Many studies took healthy and diseased samples from the same patient [ 24 , 25 , 27 , 30 , 32 , 36 , 37 , 38 ]. This is completely understandable given the ethical constraints upon taking healthy tissue, particularly with neurological tissues, but the consequences this has upon generalising to unseen patients needs exploring.…”

Method for the Intraoperative Detection of IDH Mutation in Gliomas with Differential Mobility Spectrometry

“…Recently, Raman spectroscopy has also been used for genotyping unprocessed glioma samples [20]. Raman spectroscopy is a modality that gives spectral tissue characteristics based on molecular signatures resulting from the inelastic scattering of incident light.…”

Application of Raman spectroscopy technology based on deep learning algorithm in the rapid diagnosis of glioma

“…[8] Raman spectroscopy not only has the advantages of being fast, accurate, and noninvasive, but it also has the potential to be easily implemented in a clinical environment. Therefore, in the past few decades, Raman spectroscopy technology has been widely used in cancer screening and diagnosis, such as brain cancer, [9][10][11][12][13] rectal cancer, [14] breast cancer, [15] and diabetes. [16] In addition, there are also applications of this technology in the classification of glioma patients.…”