Abstract

In modern digital microscopy, deconvolution methods are widely used to eliminate a number of image defects and increase resolution. In this review, we have divided these methods into classical, deep learning-based, and optimization-based methods. The review describes the major architectures of neural networks, such as convolutional and generative adversarial networks, autoencoders, various forms of recurrent networks, and the attention mechanism used for the deconvolution problem. Special attention is paid to deep learning as the most powerful and flexible modern approach. The review describes the major architectures of neural networks used for the deconvolution problem. We describe the difficulties in their application, such as the discrepancy between the standard loss functions and the visual content and the heterogeneity of the images. Next, we examine how to deal with this by introducing new loss functions, multiscale learning, and prior knowledge of visual content. In conclusion, a review of promising directions and further development of deconvolution methods in microscopy is given.

Highlights

  • Progress in modern imaging optics is still limited by the physical limitations of image resolution caused by the wave nature of light

  • Modern microscopy methods based on structured illumination work with complex-shaped light beams that can introduce serious geometric distortions [7], which affect the visible shape of cells and particles in the image

  • Neural networks have a huge reserve for “reduction”. This is confirmed by the recent emergence of a multitude of so-called “lightweight architectures”, which are not that inferior in accuracy compared to complex ones, but which are much simpler and require less computational resources [140–142]

Read more

Summary

Introduction

Progress in modern imaging optics is still limited by the physical limitations of image resolution caused by the wave nature of light. In addition to optical limitations, various distortions are encountered in microscopy These include scattering (random disturbance of light caused by differences in the sample’s refractive index and its environment), glare (random disturbances caused by the unexpected appearance of a beam of light with inappropriate polarization), and blur. Modern microscopy methods based on structured illumination (for example, light microscopy [6]) work with complex-shaped light beams that can introduce serious geometric distortions [7], which affect the visible shape of cells and particles in the image. They can serve as a good example of the distortion that is inevitable when using an optical system. The advantages of these methods (high acquisition speed with low photodamage, high resolution, and contrast) are enormous

Methods
Findings
Discussion
Conclusion

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 call

Disclaimer: 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.