Deep learning in computational microscopy

Thanh C. Nguyen, George Nehmetallah, Lei Tian, Lei Tian, Abhijit Mahalanobis, Jonathan C. Petruccelli
2019 Computational Imaging IV  
We propose to use deep convolutional neural networks (DCNNs) to perform 2D and 3D computational imaging. Specifically, we investigate three different applications. We first try to solve the 3D inverse scattering problem based on learning a huge number of training target and speckle pairs. We also demonstrate a new DCNN architecture to perform Fourier ptychographic Microscopy (FPM) reconstruction, which achieves high-resolution phase recovery with considerably less data than standard FPM.
more » ... tandard FPM. Finally, we employ DCNN models that can predict focused 2D fluorescent microscopic images from blurred images captured at overfocused or underfocused planes.
doi:10.1117/12.2520089 fatcat:s5xl4swxqvg2rpx6yfrhsja6su