Method and system for phase recovery and holographic image reconstruction using a neural network

A method of performing phase retrieval and holographic image reconstruction of an imaged sample comprising:

• obtaining a single hologram intensity image of the sample using an imaging device;
• back propagating the single hologram intensity image to generate a real input image and an imaginary input image of the sample with image processing software, wherein the real input image and the imaginary input image contain twin-image and/or interference-related artifacts;
• and
• providing a trained deep neural network that is executed by the image processing software using one or more processors and configured to receive the real input image and the imaginary input image of the sample and generate an output real image and an output imaginary image in which the twin-image and/or interference-related artifacts are substantially suppressed or eliminated.

A method of performing simultaneous phase-recovery and auto-focusing of a hologram intensity image of a sample volume and objects contained therein comprising:

• obtaining a single hologram intensity image of the sample volume using an image sensor;
• back propagating the single hologram intensity image with image processing software to generate a real input image and an imaginary input image of the sample, wherein the real input image and the imaginary input image contain twin-image and/or interference-related artifacts and out-of-focus objects within the sample;
• and
• providing a trained, convolutional neural network that is executed by the image processing software using one or more processors, the trained convolutional neural network trained with pairs of randomly back-propagated de-focused images and their corresponding in-focus phase-recovered images, wherein the trained, convolutional neural network is configured to receive the real input image and the imaginary input image of the sample and generate an output real image and an output imaginary image of one or more objects in the sample in which the twin-image and/or interference-related artifacts are substantially suppressed or eliminated and the output real and/or imaginary images have all of the objects in the sample volume brought into focus, all in parallel.