Systems and methods for two-dimensional fluorescence wave propagation onto surfaces using deep learning

Abstract

A fluorescence microscopy method includes a trained deep neural network. At least one 2D fluorescence microscopy image of a sample is input to the trained deep neural network, wherein the input image(s) is appended with a digital propagation matrix (DPM) that represents, pixel-by-pixel, an axial distance of a user-defined or automatically generated surface within the sample from a plane of the input image. The trained deep neural network outputs fluorescence output image(s) of the sample that is digitally propagated or refocused to the user-defined surface or automatically generated. The method and system cross-connects different imaging modalities, permitting 3D propagation of wide-field fluorescence image(s) to match confocal microscopy images at different sample planes. The method may be used to output a time sequence of images (e.g., time-lapse video) of a 2D or 3D surface within a sample.

Description

[0001] Related applications [0002] This application claims priority to US Provisional Patent Application Serial Nos. 62 / 912,537, filed on October 8, 2019, and 62 / 785,012, filed on December 26, 2018, the entire contents of which are incorporated herein by reference . Claims priority under 35 U.S.C. § 119 and any other applicable regulations. technical field [0003] The technical field generally relates to systems and methods for obtaining fluorescence images of a sample or object. More specifically, the technical field relates to fluorescence microscopy using a digital image propagation framework by training deep neural networks that inherently learn physical laws governing fluorescence wave propagation and time reversal using microscopic image data to convert The 2D fluorescence image is virtually refocused onto a user-defined 3D surface within the sample, enabling three-dimensional (3D) imaging of the fluorescent sample using a single two-dimensional (2D) image without a...

AI Technical Summary

Problems solved by technology

Very importantly, all of these methods outlined above, as well as many others, require the addition of custom optics and hardware to a standard fluorescence microscope, potentially requiring extensive alignment and calibration procedures, which not only increase the cost of the optical setup and complexity, but also leads to potential aberrations and reduced photon efficiency of the fluorescence signal

Images