Cargando…

Complementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells

Microfluidic-based assays have become effective high-throughput approaches to examining replicative aging of budding yeast cells. Deep learning may offer an efficient way to analyze a large number of images collected from microfluidic experiments. Here, we compare three deep learning architectures t...

Descripción completa

Detalles Bibliográficos
Autores principales: Ghafari, Mehran, Clark, Justin, Guo, Hao-Bo, Yu, Ruofan, Sun, Yu, Dang, Weiwei, Qin, Hong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7968698/
https://www.ncbi.nlm.nih.gov/pubmed/33730031
http://dx.doi.org/10.1371/journal.pone.0246988
_version_ 1783666116105601024
author Ghafari, Mehran
Clark, Justin
Guo, Hao-Bo
Yu, Ruofan
Sun, Yu
Dang, Weiwei
Qin, Hong
author_facet Ghafari, Mehran
Clark, Justin
Guo, Hao-Bo
Yu, Ruofan
Sun, Yu
Dang, Weiwei
Qin, Hong
author_sort Ghafari, Mehran
collection PubMed
description Microfluidic-based assays have become effective high-throughput approaches to examining replicative aging of budding yeast cells. Deep learning may offer an efficient way to analyze a large number of images collected from microfluidic experiments. Here, we compare three deep learning architectures to classify microfluidic time-lapse images of dividing yeast cells into categories that represent different stages in the yeast replicative aging process. We found that convolutional neural networks outperformed capsule networks in terms of accuracy, precision, and recall. The capsule networks had the most robust performance in detecting one specific category of cell images. An ensemble of three best-fitted single-architecture models achieves the highest overall accuracy, precision, and recall due to complementary performances. In addition, extending classification classes and data augmentation of the training dataset can improve the predictions of the biological categories in our study. This work lays a useful framework for sophisticated deep-learning processing of microfluidic-based assays of yeast replicative aging.
format Online
Article
Text
id pubmed-7968698
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-79686982021-03-31 Complementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells Ghafari, Mehran Clark, Justin Guo, Hao-Bo Yu, Ruofan Sun, Yu Dang, Weiwei Qin, Hong PLoS One Research Article Microfluidic-based assays have become effective high-throughput approaches to examining replicative aging of budding yeast cells. Deep learning may offer an efficient way to analyze a large number of images collected from microfluidic experiments. Here, we compare three deep learning architectures to classify microfluidic time-lapse images of dividing yeast cells into categories that represent different stages in the yeast replicative aging process. We found that convolutional neural networks outperformed capsule networks in terms of accuracy, precision, and recall. The capsule networks had the most robust performance in detecting one specific category of cell images. An ensemble of three best-fitted single-architecture models achieves the highest overall accuracy, precision, and recall due to complementary performances. In addition, extending classification classes and data augmentation of the training dataset can improve the predictions of the biological categories in our study. This work lays a useful framework for sophisticated deep-learning processing of microfluidic-based assays of yeast replicative aging. Public Library of Science 2021-03-17 /pmc/articles/PMC7968698/ /pubmed/33730031 http://dx.doi.org/10.1371/journal.pone.0246988 Text en © 2021 Ghafari et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Ghafari, Mehran
Clark, Justin
Guo, Hao-Bo
Yu, Ruofan
Sun, Yu
Dang, Weiwei
Qin, Hong
Complementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells
title Complementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells
title_full Complementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells
title_fullStr Complementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells
title_full_unstemmed Complementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells
title_short Complementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells
title_sort complementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7968698/
https://www.ncbi.nlm.nih.gov/pubmed/33730031
http://dx.doi.org/10.1371/journal.pone.0246988
work_keys_str_mv AT ghafarimehran complementaryperformancesofconvolutionalandcapsuleneuralnetworksonclassifyingmicrofluidicimagesofdividingyeastcells
AT clarkjustin complementaryperformancesofconvolutionalandcapsuleneuralnetworksonclassifyingmicrofluidicimagesofdividingyeastcells
AT guohaobo complementaryperformancesofconvolutionalandcapsuleneuralnetworksonclassifyingmicrofluidicimagesofdividingyeastcells
AT yuruofan complementaryperformancesofconvolutionalandcapsuleneuralnetworksonclassifyingmicrofluidicimagesofdividingyeastcells
AT sunyu complementaryperformancesofconvolutionalandcapsuleneuralnetworksonclassifyingmicrofluidicimagesofdividingyeastcells
AT dangweiwei complementaryperformancesofconvolutionalandcapsuleneuralnetworksonclassifyingmicrofluidicimagesofdividingyeastcells
AT qinhong complementaryperformancesofconvolutionalandcapsuleneuralnetworksonclassifyingmicrofluidicimagesofdividingyeastcells