Phase recovery and holographic image reconstruction using deep learning in neural networks

TLDR

Phase recovery from intensity‑only measurements is central to coherent imaging and holography. The study demonstrates that a neural network can learn to perform phase recovery and holographic image reconstruction after appropriate training. The neural network was trained to recover phase and reconstruct holographic images, and its performance was validated by reconstructing phase and amplitude images of samples such as blood, Pap smears, and tissue sections. The deep learning approach rapidly eliminates twin‑image and self‑interference artifacts, reconstructs phase and amplitude images from a single hologram, and shows that machine learning can overcome challenging imaging problems, opening new avenues for computational imaging systems.

Abstract

Phase recovery from intensity-only measurements forms the heart of coherent imaging techniques and holography. In this study, we demonstrate that a neural network can learn to perform phase recovery and holographic image reconstruction after appropriate training. This deep learning-based approach provides an entirely new framework to conduct holographic imaging by rapidly eliminating twin-image and self-interference-related spatial artifacts. This neural network-based method is fast to compute and reconstructs phase and amplitude images of the objects using only one hologram, requiring fewer measurements in addition to being computationally faster. We validated this method by reconstructing the phase and amplitude images of various samples, including blood and Pap smears and tissue sections. These results highlight that challenging problems in imaging science can be overcome through machine learning, providing new avenues to design powerful computational imaging systems.