Deep learning in computational microscopyMS65

Using deep learning, we demonstrate significant advances in different modes of microscopic imaging, including bright-field, holographic and mobile-phone based microscopy tools, increasing their imaging throughput, resolution and depth-of-field, while also eliminating or correcting for undesired spatial and/or spectral artifacts. This deep learning based framework can be broadly applied for solving inverse problems in computational microscopic imaging, and especially benefit imaging modalities where an accurate modeling of the image formation process is challenging.

This presentation is part of Minisymposium “MS65 - Machine learning techniques for image reconstruction (2 parts)
organized by: Markus Haltmeier (University Innsbruck) , Linh Nguyen (University of Idaho) .

Yair Rivenson (University of California Los Angeles)
deep learning, image deblurring, image enhancement, image reconstruction