Enhancing Mechanical Stimulated Brillouin Scattering Imaging with Physics-Driven Model Selection

Brillouin microscopy (BM) is an emerging technique for all-optical mechanical imaging without the need for physical contact with the sample or for an external mechanical stimulus. However, BM often retrieves a single Brillouin frequency shift for multiple mechanically different materials of structures and/or in regions-sufficiently larger than the phonon wavelength-inside the volume and its surroundings, resulting in significantly limited mechanical specificity in the Brillouin shift images produced. Here, a new physics-driven model selection framework is developed based on information theory and a physical-statistical overfit Brillouin water peak threshold that enables the robust identification of single- and multi-peak Brillouin signatures in the sample pixels. The model selection framework is applied to Brillouin data of material interfaces and living NIH/3T3 cells measured by stimulated Brillouin scattering (SBS) microscopy, facilitating the quantification of the Brillouin frequency shift of materials in different regions of the sample and significantly improving mechanical specificity compared with the standard single peak fitting analysis. A physics-driven model selection scheme for improving the analysis of Brillouin microscopy images is proposed. The scheme is based on information theory and a physical-statistical overfit Brillouin water peak threshold. The new analysis strategy together with the multi-parameter contrast of stimulated Brillouin microscopy open new possibilities for an improved, more quantitative, mechanically-specific analysis of Brillouin imaging data of materials and biological systems. image