College - Author 1

College of Science and Mathematics

Department - Author 1

Biological Sciences Department

College - Author 2

College of Science and Mathematics

Department - Author 2

Computer Science Department

College - Author 4

College of Engineering

Department - Author 4

Computer Science Department

Advisor

Jonathan Ventura, College of Engineering, Computer Science & Software Engineering

Funding Source

National Institutes of Health (NIH)

Date

10-2024

Abstract/Summary

In order to avoid damaging live cells, optical microscope imaging must be conducted under low-excitation light intensity and/or short exposure times, resulting in low signal-to-noise ratios (SNR). Deep learning methods offer an effective solution for removing microscope noise, utilizing algorithms that are able to reconstruct finer features in low SNR images. This research explores the denoising capability of several deep learning methods based on PSNR and SSIM. Tested methods include traditional approaches (BMED), supervised learning (CARE and Restormer), and unsupervised methods (Noise2Fast, N2V, SSD-Unsupervised, and SASSID). The Restormer model, which employs an encoder-decoder transformer architecture and progressive learning, stood out from other methods, demonstrating strong PSNR and SSIM performance.

Share

COinS
 

URL: https://digitalcommons.calpoly.edu/ceng_surp/83

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.