Label2label : training a neural network to selectively restore cellular structures in fluorescence microscopy

Tools

Kölln, Lisa Sophie and Salem, Omar and Valli, Jessica and Hansen, Carsten Gram and McConnell, Gail (2022) Label2label : training a neural network to selectively restore cellular structures in fluorescence microscopy. Journal of Cell Science, 135 (3). jcs258994. ISSN 0021-9533 (https://doi.org/10.1242/jcs.258994)

[thumbnail of Kolln-etal-JCS-2022-training-a-neural-network-to-selectively-restore-cellular-structures]
Preview
 Text. Filename: Kolln_etal_JCS_2022_training_a_neural_network_to_selectively_restore_cellular_structures.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (4MB)| Preview

Abstract

Immunofluorescence microscopy is routinely used to visualise the spatial distribution of proteins that dictates their cellular function. However, unspecific antibody binding often results in high cytosolic background signals, decreasing the image contrast of a target structure. Recently, convolutional neural networks (CNNs) were successfully employed for image restoration in immunofluorescence microscopy, but current methods cannot correct for those background signals. We report a new method that trains a CNN to reduce unspecific signals in immunofluorescence images; we name this method label2label (L2L). In L2L, a CNN is trained with image pairs of two non-identical labels that target the same cellular structure. We show that after L2L training a network predicts images with significantly increased contrast of a target structure, which is further improved after implementing a multiscale structural similarity loss function. Here, our results suggest that sample differences in the training data decrease hallucination effects that are observed with other methods. We further assess the performance of a cycle generative adversarial network, and show that a CNN can be trained to separate structures in superposed immunofluorescence images of two targets.

ORCID iDs

Kölln, Lisa Sophie, Salem, Omar, Valli, Jessica, Hansen, Carsten Gram and McConnell, Gail ORCID logoORCID: https://orcid.org/0000-0002-7213-0686;
  • Item type:Article
    ID code:79271
    Dates:
    Date
    Event
    10 February 2022
    Published
    13 January 2022
    Published Online
    17 December 2021
    Accepted
    Subjects:Science > Physics
    Department:Faculty of Science > Physics
    Depositing user: Pure Administrator
    Date deposited:25 Jan 2022 13:13
    Last modified:11 Nov 2024 13:22
    URI:https://strathprints.strath.ac.uk/id/eprint/79271
CORE (COnnecting REpositories)