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

Authors:
Open Access
Publisher website
Google Scholar
Abstract
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.
Funding Information
  • National Science Foundation (CAREER award #1453078 and #1720215)
  • National Science Foundation (#1761839 Spokes: MEDIUM: SOUTH: Collaborative: Integrating Biological Big Data Research into Student Training and Education)
  • University of Tennessee at Chattanooga (start up and internal research support)
  • National Institute of Health (#R01AG052507, Regulation of longevity through maintenance of transcription fidelity)
  • National Institute of Health (#R42AG058368, Developing an automated yeast dissection system for aging research)

This publication has 23 references indexed in Scilit: