Deep learning for single-shot autofocus microscopy

Maintaining an in-focus image over long time scales is an essential and nontrivial task for a variety of microscopy applications. Here, we describe a fast, robust autofocusing method compatible with a wide range of existing microscopes. It requires only the addition of one or a few off-axis illumination sources (e.g., LEDs), and can predict the focus correction from a single image with this illumination. We designed a neural network architecture, the fully connected Fourier neural network (FCFNN), that exploits an understanding of the physics of the illumination to make accurate predictions with 2-3 orders of magnitude fewer learned parameters and less memory usage than existing state-of-the-art architectures, allowing it to be trained without any specialized hardware. We provide an open-source implementation of our method, to enable fast, inexpensive autofocus compatible with a variety of microscopes. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement