Deep learning in computational microscopy

Thanh Nguyen; George Nehmetallah; Lei Tian

doi:10.1117/12.2520089

Translator Disclaimer

13 May 2019 Deep learning in computational microscopy

Thanh Nguyen, George Nehmetallah, Lei Tian

Author Affiliations +

Proceedings Volume 10990, Computational Imaging IV; 1099007 (2019) https://doi.org/10.1117/12.2520089
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, Maryland, United States

Abstract

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. Finally, we employ DCNN models that can predict focused 2D fluorescent microscopic images from blurred images captured at overfocused or underfocused planes.

Conference Presentation

Citation Download Citation

Thanh Nguyen, George Nehmetallah, and Lei Tian "Deep learning in computational microscopy", Proc. SPIE 10990, Computational Imaging IV, 1099007 (13 May 2019); https://doi.org/10.1117/12.2520089

ACCESS THE FULL ARTICLE