Accurate Tumor Subtype Detection with Raman Spectroscopy via Variational Autoencoder and Machine Learning

Accurate diagnosis of cancer subtypes is a great guide for the development of surgical plans and prognosis in the clinic. Raman spectroscopy, combined with the machine learning algorithm, has been demonstrated to be a powerful tool for tumor identification. However, the analysis and classification of Raman spectra for biological samples with complex compositions are still challenges. In addition, the signal-to-noise ratio of the spectra also influences the accuracy of the classification. Herein, we applied the variational autoencoder (VAE) to Raman spectra for downscaling and noise reduction simultaneously. We validated the performance of the VAE algorithm at the cellular and tissue levels. VAE successfully downscaled high-dimensional Raman spectral data to two-dimensional (2D) data for three subtypes of non-small cell lung cancer cells and two subtypes of kidney cancer tissues. Gaussian naive bayes was applied to subtype discrimination with the 2D data after VAE encoding at both the cellular and tissue levels, significantly outperforming the discrimination results using original spectra. Therefore, the analysis of Raman spectroscopy based on VAE and machine learning has great potential for rapid diagnosis of tumor subtypes.

Automated summary

In this study, Raman spectroscopy combined with the variational autoencoder (VAE) was used to analyze and classify tumor subtypes. The VAE successfully downscaled and reduced noise in the Raman spectra, leading to improved discrimination results compared to the original spectra.