Share Email Print
cover

Proceedings Paper

3D fluorescence deconvolution with deep priors (Conference Presentation)

Paper 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.

Paper Details

Date Published: 9 March 2020
PDF
Proc. SPIE 11245, Three-Dimensional and Multidimensional Microscopy: Image Acquisition and Processing XXVII, 112450N (9 March 2020); doi: 10.1117/12.2545041
Show Author Affiliations
Kevin Zhang, Univ. of California, Berkeley (United States)
Michael R. Kellman, Univ. of California, Berkeley (United States)
Emrah Bostan, Univ. of California, Berkeley (United States)
Laura Waller, Univ. of California, Berkeley (United States)


Published in SPIE Proceedings Vol. 11245:
Three-Dimensional and Multidimensional Microscopy: Image Acquisition and Processing XXVII
Thomas G. Brown; Tony Wilson; Laura Waller, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray