Spectroscopic stimulated Raman scattering imaging of highly dynamic specimens through matrix completion

Spectroscopic stimulated Raman scattering (SRS) imaging generates chemical maps of intrinsic molecules, with no need for prior knowledge. Despite great advances in instrumentation, the acquisition speed for a spectroscopic SRS image stack is fundamentally bounded by the pixel integration time. In this work, we report three-dimensional sparsely sampled spectroscopic SRS imaging that measures similar to 20% of pixels throughout the stack. In conjunction with related work in low-rank matrix completion (e.g., the Netflix Prize), we develop a regularized non-negative matrix factorization algorithm to decompose the sub-sampled image stack into spectral signatures and concentration maps. This design enables an acquisition speed of 0.8 s per image stack, with 50 frames in the spectral domain and 40,000 pixels in the spatial domain, which is faster than the conventional raster laser-scanning scheme by one order of magnitude. Such speed allows real-time metabolic imaging of living fungi suspended in a growth medium while effectively maintaining the spatial and spectral resolutions. This work is expected to promote broad application of matrix completion in spectroscopic laser-scanning imaging.