We will discuss recently emerging applications of the state-of-art deep learning methods on optical microscopy and microscopic image reconstruction, which enable new transformations among different modalities of microscopic imaging, driven entirely by image data.
We explore the advantages of an synthetic aperture microscopy for improvement to apply enlarged space bandwidth product to in dynamic imaging in phase imaging.
We demonstrate a method to reconstruct confocally gated reflection images acquired through a multimode fiber. It requires a series of distinct illumination patterns obtained by varying the proximal coupling of the illumination and enables fast volumetric imaging without physically focusing the light into the sample.
We propose a fast image recovery method through dynamic turbid media using properties of bispectrum.
We explore using full-wave forward and adjoint solvers to approach the inverse problem in Optical Coherence Tomography. We demonstrate that oscillatory artifacts in the electric susceptibility arise in the inversion process due to the intrinsic wave-nature of the models, yet, measured data id faithfully reproduced.