Cargando…

Rotation equivariant and invariant neural networks for microscopy image analysis

MOTIVATION: Neural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image...

Descripción completa

Detalles Bibliográficos
Autores principales: Chidester, Benjamin, Zhou, Tianming, Do, Minh N, Ma, Jian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6612823/
https://www.ncbi.nlm.nih.gov/pubmed/31510662
http://dx.doi.org/10.1093/bioinformatics/btz353
_version_ 1783432944943104000
author Chidester, Benjamin
Zhou, Tianming
Do, Minh N
Ma, Jian
author_facet Chidester, Benjamin
Zhou, Tianming
Do, Minh N
Ma, Jian
author_sort Chidester, Benjamin
collection PubMed
description MOTIVATION: Neural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet). RESULTS: We evaluated the efficacy of CFNet and G-CNN as compared to a standard CNN for several different image classification tasks, including simulated and real microscopy images of subcellular protein localization, and demonstrated improved performance. We believe CFNet has the potential to improve many high-throughput microscopy image analysis applications. AVAILABILITY AND IMPLEMENTATION: Source code of CFNet is available at: https://github.com/bchidest/CFNet. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
format Online
Article
Text
id pubmed-6612823
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-66128232019-07-12 Rotation equivariant and invariant neural networks for microscopy image analysis Chidester, Benjamin Zhou, Tianming Do, Minh N Ma, Jian Bioinformatics Ismb/Eccb 2019 Conference Proceedings MOTIVATION: Neural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet). RESULTS: We evaluated the efficacy of CFNet and G-CNN as compared to a standard CNN for several different image classification tasks, including simulated and real microscopy images of subcellular protein localization, and demonstrated improved performance. We believe CFNet has the potential to improve many high-throughput microscopy image analysis applications. AVAILABILITY AND IMPLEMENTATION: Source code of CFNet is available at: https://github.com/bchidest/CFNet. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. Oxford University Press 2019-07 2019-07-05 /pmc/articles/PMC6612823/ /pubmed/31510662 http://dx.doi.org/10.1093/bioinformatics/btz353 Text en © The Author(s) 2019. Published by Oxford University Press. http://creativecommons.org/licenses/by-nc/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.com
spellingShingle Ismb/Eccb 2019 Conference Proceedings
Chidester, Benjamin
Zhou, Tianming
Do, Minh N
Ma, Jian
Rotation equivariant and invariant neural networks for microscopy image analysis
title Rotation equivariant and invariant neural networks for microscopy image analysis
title_full Rotation equivariant and invariant neural networks for microscopy image analysis
title_fullStr Rotation equivariant and invariant neural networks for microscopy image analysis
title_full_unstemmed Rotation equivariant and invariant neural networks for microscopy image analysis
title_short Rotation equivariant and invariant neural networks for microscopy image analysis
title_sort rotation equivariant and invariant neural networks for microscopy image analysis
topic Ismb/Eccb 2019 Conference Proceedings
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6612823/
https://www.ncbi.nlm.nih.gov/pubmed/31510662
http://dx.doi.org/10.1093/bioinformatics/btz353
work_keys_str_mv AT chidesterbenjamin rotationequivariantandinvariantneuralnetworksformicroscopyimageanalysis
AT zhoutianming rotationequivariantandinvariantneuralnetworksformicroscopyimageanalysis
AT dominhn rotationequivariantandinvariantneuralnetworksformicroscopyimageanalysis
AT majian rotationequivariantandinvariantneuralnetworksformicroscopyimageanalysis