Learning flat optics for extended depth of field microscopy imaging

Conventional microscopy systems have limited depth of field, which often necessitates depth scanning techniques hindered by light scattering. Various techniques have been developed to address this challenge, but they have limited extended depth of field (EDOF) capabilities. To overcome this challenge, this study proposes an end-to-end optimization framework for building a computational EDOF microscope that combines a 4f microscopy optical setup incorporating learned optics at the Fourier plane and a post-processing deblurring neural network. Utilizing the end-to-end differentiable model, we present a systematic design methodology for computational EDOF microscopy based on the specific visualization requirements of the sample under examination. In particular, we demonstrate that the metasurface optics provides key advantages for extreme EDOF imaging conditions, where the extended DOF range is well beyond what is demonstrated in state of the art, achieving superior EDOF performance.

Automated summary

Conventional microscopy systems have limited depth of field. To address this challenge, a computational extended depth of field (EDOF) microscope combining learned optics and a deblurring neural network is proposed. A systematic design methodology based on the specific sample visualization requirements is presented, showing that metasurface optics provides superior EDOF performance.