Multivariate analysis of Brillouin imaging data by supervised and unsupervised learning

TL;DR

This paper introduces multivariate supervised and unsupervised learning methods for Brillouin imaging data analysis, enabling faster, more detailed spectral unmixing, classification, and segmentation compared to traditional spectral fitting.

Contribution

It presents novel multivariate algorithms for hyperspectral Brillouin data analysis, improving speed and robustness over conventional line fitting methods.

Findings

More contrast and detail in images

Analysis performed 100 times faster than fitting

Spectral parameters consistent with traditional methods

Abstract

Brillouin imaging relies on the reliable extraction of subtle spectral information from hyperspectral datasets. To date, the mainstream practice has been using line fitting of spectral features to retrieve the average peak shift and linewidth parameters. Good results, however, depend heavily on sufficient SNR and may not be applicable in complex samples that consist of spectral mixtures. In this work, we thus propose the use of various multivariate algorithms that can be used to perform supervised or unsupervised analysis of the hyperspectral data, with which we explore advanced image analysis applications, namely unmixing, classification and segmentation in a phantom and live cells. The resulting images are shown to provide more contrast and detail, and obtained on a timescale $10^2$ faster than fitting. The estimated spectral parameters are consistent with those calculated from pure fitting.