Generative Augmentation of Raman Spectra for Glioma Classification

2026-07-11

AI Summary

This study addresses the limitations in Raman spectroscopy–based glioma classification caused by small sample sizes, high heterogeneity, and class imbalance. To overcome these challenges, the authors propose a deep generative data augmentation approach based on β-conditional variational autoencoders (β-CVAE) to synthesize class-conditional spectral data, which is then combined with real samples for classifier training. Under rigorous patient-wise cross-validation, this strategy significantly improves classification performance for both IDH mutation status and methylation subtypes, demonstrating the efficacy of generative augmentation. Furthermore, the work explores a classification-by-reconstruction (CbR) mechanism leveraging reconstruction errors, which enhances model robustness in extremely data-scarce scenarios.

Abstract

Access to sufficiently large biomedical datasets remains a major obstacle for machine learning in Raman spectroscopy-based diagnostics. In particular, for glioma analysis, datasets are typically small and heterogeneous, affected by acquisition-specific variability. This work investigates the utility of deep generative augmentation in such a small-cohort setting. We analyze glioma biopsy spectra acquired from 58 tumor samples and consider both binary IDH-status classification and 6-class methylation subtype classification problems. To address the limited size and imbalance of the dataset, we develop a conditional variational autoencoder ($β$-CVAE) capable of generating class-conditioned synthetic Raman spectra. The generated data are evaluated in Train-on-Synthetic, Test-on-Real (TS/TR) and Train-on-Synthetic+Real, Test-on-Real (TSR/TR) settings under a strict patient-isolated cross-validation protocol. Models trained exclusively on synthetic data underperform models trained on real spectra, indicating a substantial domain gap between synthetic and real distributions. However, augmenting the real training data with synthetic spectra consistently improves classification performance across multiple models. These findings indicate that, even with a limited number of independent patient samples, generative models can capture sufficient structure to provide useful regularization for downstream classifiers. We also investigate a reconstruction-based inference strategy, termed Classification by Reconstruction (CbR), in which class prediction is based on reconstruction error under different class conditions. Overall, the results support the use of deep generative augmentation as a practical strategy for improving machine learning robustness in Raman spectroscopy applications characterized by limited biomedical datasets.

Problem

• Raman spectroscopy
• glioma classification
• small dataset
• data heterogeneity
• class imbalance

Innovation

• generative augmentation
• conditional variational autoencoder
• Raman spectroscopy
• glioma classification
• classification by reconstruction