Deep Learning Facilitates Alignment of Coordinate-Targeted Superresolution Microscopes

In STED microscopy, an additional laser is used to deplete fluorescence and limit emission to a tightly confined, subdiffraction-sized volume around an intensity minimum. In theory, achievable resolution is unlimited and scales with the intensity of the depletion laser. In practice, aberrations, misalignments and scattering deflect light into the intensity minima, deplete the signal and deteriorate signal to noise ratio [1]. STED microscopes are re-aligned regularly to maintain performance, which is a time-consuming task requiring an experienced expert. Recently, machine learning has been successfully combined with microscopy, e.g. for image processing or aberration correction [2].

Here, we demonstrate a neural net capable of recognizing and correcting common misalignments and aberrations. A training pair consists of (1) a weighted combination of Zernike polynomials and (2) images of the aberrated PSF. In contrast to [3], we create our training data in-silico using vector diffraction theory [4]. By using all three orthogonal crosssections of the PSF, we achieve better correction than study [3].

Our workflow can be adapted to other intensity distributions simply by replacing the vortex pattern used for training data generation.

Download paper here