Super-Resolution and Large Depth of Field Model for Optical Microscope Imaging

Ruo-Peng Zheng,Lei Li,Shu-Bin Liu,Paramasivam Senthilkumaran

doi:10.1155/2021/6493130

Ruo-Peng Zheng, Lei Li + Show 2 more

Open Access

https://doi.org/10.1155/2021/6493130

Copy DOI

Abstract

Due to the limitation of numerical aperture (NA) in a microscope, it is very difficult to obtain a clear image of the specimen with a large depth of field (DOF). We propose a deep learning network model to simultaneously improve the imaging resolution and DOF of optical microscopes. The proposed M-Deblurgan consists of three parts: (i) a deblurring module equipped with an encoder-decoder network for feature extraction, (ii) an optimal approximation module to reduce the error propagation between the two tasks, and (iii) an SR module to super-resolve the image from the output of the optimal approximation module. The experimental results show that the proposed network model reaches the optimal result. The peak signal-to-noise ratio (PSNR) of the method can reach 37.5326, and the structural similarity (SSIM) can reach 0.9551 in the experimental dataset. The method can also be used in other potential applications, such as microscopes, mobile cameras, and telescopes.

Highlights

In microscopy, it is very difficult to obtain a clear image of the specimen with a large depth of field (DOF), especially for large numerical aperture (NA)
It is very difficult to obtain a clear image of the specimen with a large depth of field (DOF), especially for large NA
The deep learning single-image super-resolution (SISR) model [10,11,12] and convolutional neural network (CNN) model [13] have been applied to improve the resolution and definition in microscope images, which indicates that they have great potential in microscopes

Summary

Introduction

It is very difficult to obtain a clear image of the specimen with a large depth of field (DOF), especially for large NA. We propose a generative adversarial neural network framework model (M-Deblurgan) based on the optimal approximation, which is to simultaneously solve the low-resolution and insufficient depth of field in an optical microscope. E PSNR of the method can reach 37.5326, and the SSIM can reach 0.9551 in the experimental dataset, which shows the deblurred results and resolution are improved compared to other models.

Results

Conclusion