3D fluorescence deconvolution with deep priors (Conference Presentation)

Kevin Zhang; Michael R. Kellman; Emrah Bostan; Laura Waller

doi:10.1117/12.2545041

9 March 2020 3D fluorescence deconvolution with deep priors (Conference Presentation)

Kevin Zhang, Michael R. Kellman, Emrah Bostan, Laura Waller

Proceedings Volume 11245, Three-Dimensional and Multidimensional Microscopy: Image Acquisition and Processing XXVII; 112450N (2020) https://doi.org/10.1117/12.2545041
Event: SPIE BiOS, 2020, San Francisco, California, United States

Abstract

The goal of this work is to incorporate Convolutional Neural Networks (CNNs) into the 3D deconvolution process without training. CNNs are well suited to the problem of 2D deconvolution, however training a CNN on 3D volumes requires excessive time and impractical amounts of training data. To circumvent these problems, we use a CNN architecture as if it were a handcrafted prior, similar to the work deep image prior. Using this method, we achieve high SSIM and PSNR metrics relative to other modern techniques for deconvolving through-focus fluorescence measurements to recover a 3D volume with no training data and minimal hyperparameter tuning.

Conference Presentation

Citation Download Citation

Kevin Zhang, Michael R. Kellman, Emrah Bostan, and Laura Waller "3D fluorescence deconvolution with deep priors (Conference Presentation)", Proc. SPIE 11245, Three-Dimensional and Multidimensional Microscopy: Image Acquisition and Processing XXVII, 112450N (9 March 2020); https://doi.org/10.1117/12.2545041

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available