Deep-Learning-Based Virtual Refocusing of Images Using an Engineered Point-Spread Function

We present a virtual image refocusing method over an extended depth of field (DOF) enabled by cascaded neural networks and double-helix point-spread function (DH-PSF). This network model, referred to as W-Net, is composed two generator discriminator pairs. The first learns virtually refocus input onto user-defined plane, while the second perform cross-modality transformation, improving lateral resolution output image. Using this W-Net model with DH-PSF engineering, we extend DOF fluorescence microscope ~20-fold. approach can be applied develop deep learning-enabled reconstruction methods for localization microscopy techniques that utilize engineered PSFs improve their imaging performance, including spatial volumetric throughput.