Abstract
Recent advances in deep learning have given rise to a new paradigm of holographic image reconstruction and phase recovery techniques with real-time performance. Through data-driven approaches, these emerging techniques have overcome some of the challenges associated with existing holographic image reconstruction methods while also minimizing the hardware requirements of holography. These recent advances open up a myriad of new opportunities for the use of coherent imaging systems in biomedical and engineering research and related applications.
Highlights
Exponential advancements in computational resources and algorithms have given rise to new paradigms in microscopic imaging modalities that rely on computation to digitally reconstruct and enhance images, surpassing the capabilities of conventional microscopes
Recent developments in the field of deep learning have opened up exciting avenues for significantly advancing holography and coherent imaging systems by circumventing some of these challenges of coherent imaging systems while taking full advantage of their inherent benefits. We believe that this emerging body of exciting work on deep learning in holography will be the key to the wider-scale dissemination and adoption of holographic imaging and sensing systems in the life sciences, biomedicine and engineering fields at large, and it has already been applied to various important tasks in coherent imaging, such as phase recovery[3,4,5,6], super-resolution[7], phase unwrapping[8,9] and label-free sensing[10,11,12]
These methods are generally enabled by the supervised optimization of deep convolutional neural networks (CNNs) using accurately registered image data (Fig. 1a)
Summary
Exponential advancements in computational resources and algorithms have given rise to new paradigms in microscopic imaging modalities that rely on computation to digitally reconstruct and enhance images, surpassing the capabilities of conventional microscopes. Recent developments in the field of deep learning have opened up exciting avenues for significantly advancing holography and coherent imaging systems by circumventing some of these challenges of coherent imaging systems while taking full advantage of their inherent benefits We believe that this emerging body of exciting work on deep learning in holography will be the key to the wider-scale dissemination and adoption of holographic imaging and sensing systems in the life sciences, biomedicine and engineering fields at large, and it has already been applied to various important tasks in coherent imaging, such as phase recovery[3,4,5,6], super-resolution[7], phase unwrapping[8,9] and label-free sensing[10,11,12]. CNNs typically contain tens to hundreds of layers of convolution kernels (filters), bias terms, and nonlinear activation
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
