loading page

Machine learning-based automated yeast cell counting under a complicated background with ilastik and ImageJ
  • +5
  • Chenxi Li,
  • Xiaoyu Ma,
  • Jing Deng,
  • Jiajia Li,
  • Yanjie Liu,
  • Xudong Zhu,
  • Ping Zhang,
  • Jin Liu
Chenxi Li
Beijing Normal University College of Life Sciences
Author Profile
Xiaoyu Ma
Beijing Normal University College of Life Sciences
Author Profile
Jing Deng
Beijing Normal University College of Life Sciences
Author Profile
Jiajia Li
Beijing Normal University College of Life Sciences
Author Profile
Yanjie Liu
Author Profile
Xudong Zhu
Beijing Normal University College of Life Sciences
Author Profile
Ping Zhang
Beijing Normal University College of Life Sciences
Author Profile
Jin Liu
Beijing Normal University College of Life Sciences
Author Profile

Abstract

Measuring the concentration and viability of yeast cells is an important and fundamental procedure in scientific research and industrial fermentation. In consideration of the drawbacks of manual cell counting, large quantities of yeast cells require methods that provide easy, objective, and reproducible high-throughput calculations, especially for samples in complicated backgrounds. To answer this challenge, we explored and developed an easy-to-use yeast cell counting pipeline that combined the machine learning-based ilastik tool with the freeware ImageJ, as well as a conventional photomicroscope. Briefly, learning from labels provided by the user, ilastik performs segmentation and classification automatically in batch processing mode for large numbers of images and thus discriminates yeast cells from complex backgrounds. The files processed through ilastik can be recognized by ImageJ, which can set up customizable parameters based on cell size, perimeter, roundness and so on. In this work, we programmed an ImageJ macro, “Yeast Counter”, to compute the numeric results of yeast cells for automatic batch processing. Taking the yeast Cryptococccus deneoformans as an example, we observed that the customizable software algorithm for yeast counting with ilastik and ImageJ reduced inter-operator errors significantly and achieved accurate and objective results in the spotting test, while manual counting with a haemocytometer exhibited some errors between repeats and required more time. In summary, a convenient, rapid, reproducible and extremely low-cost method to count yeast cells is described here that can be applied to multiple kinds of yeasts in genetics, cell biology and industrial fermentation.