Open AccessComplementary performances of convolutional and capsule neural networks on classifying microfluidic images of dividing yeast cells
Author(s) -
Mehran Ghafari,
Justin Clark,
HaoBo Guo,
Ruofan Yu,
Yu Sun,
Weiwei Dang,
Hong Qin
Publication year - 2021
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0246988
Subject(s) - convolutional neural network , deep learning , budding yeast , artificial intelligence , computer science , microfluidics , yeast , artificial neural network , pattern recognition (psychology) , process (computing) , precision and recall , machine learning , computational biology , saccharomyces cerevisiae , biology , nanotechnology , genetics , materials science , operating system
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.