Deep Learning Microscopy

TL;DR

This paper presents a deep learning method that enhances optical microscopy images, significantly improving resolution over large areas and depths without changing the microscope hardware.

Contribution

The authors introduce a neural network that boosts microscopy resolution from low-quality images, matching high-end systems without hardware modifications.

Findings

Deep learning improves microscopy resolution and field-of-view.

The method works across various tissue samples and imaging conditions.

It surpasses traditional optical limits without hardware changes.

Abstract

We demonstrate that a deep neural network can significantly improve optical microscopy, enhancing its spatial resolution over a large field-of-view and depth-of-field. After its training, the only input to this network is an image acquired using a regular optical microscope, without any changes to its design. We blindly tested this deep learning approach using various tissue samples that are imaged with low-resolution and wide-field systems, where the network rapidly outputs an image with remarkably better resolution, matching the performance of higher numerical aperture lenses, also significantly surpassing their limited field-of-view and depth-of-field. These results are transformative for various fields that use microscopy tools, including e.g., life sciences, where optical microscopy is considered as one of the most widely used and deployed techniques. Beyond such applications, our presented approach is broadly applicable to other imaging modalities, also spanning different parts of the electromagnetic spectrum, and can be used to design computational imagers that get better and better as they continue to image specimen and establish new transformations among different modes of imaging.