Deep learning-based virtual refocusing of images using an engineered point-spread function
This method offers a significant improvement in the depth of field for fluorescence microscopy, which is beneficial for researchers needing to image thicker biological samples without physical refocusing.
This paper tackles the problem of extending the depth of field (DOF) in fluorescence microscopy. By combining cascaded neural networks (W-Net) with a double-helix point-spread function (DH-PSF), the authors achieved a ~20-fold extension of the DOF.
We present a virtual image refocusing method over an extended depth of field (DOF) enabled by cascaded neural networks and a double-helix point-spread function (DH-PSF). This network model, referred to as W-Net, is composed of two cascaded generator and discriminator network pairs. The first generator network learns to virtually refocus an input image onto a user-defined plane, while the second generator learns to perform a cross-modality image transformation, improving the lateral resolution of the output image. Using this W-Net model with DH-PSF engineering, we extend the DOF of a fluorescence microscope by ~20-fold. This approach can be applied to develop deep learning-enabled image reconstruction methods for localization microscopy techniques that utilize engineered PSFs to improve their imaging performance, including spatial resolution and volumetric imaging throughput.