Publication detail

Machine-learning Approach to Microbial Colony Localisation

ČIČATKA, M. BURGET, R. KARÁSEK, J.

Original Title

Machine-learning Approach to Microbial Colony Localisation

Type

conference paper

Language

English

Original Abstract

Due to the massive expansion of the mass spectrometry, increased demands for precision and constant price growth of the human labour the optimisation of the microbial samples preparation comes into question. This paper deals with designing and implementing an image processing pipeline that takes an input in the form of a Petri dish image with cultivated colonies and outputs the position of possible sampling points. In total 547 samples were collected. The first block of the pipeline consists of a trained customised ENet model which predicts a binary mask. Architectures U-Net, UNet++ and ENet were examined, where ENet was found to perform with the highest Dice coefficient (0.979).

Keywords

ENet; mass spectrometry; microbial colonies; U-Net; UNet++

Authors

ČIČATKA, M.; BURGET, R.; KARÁSEK, J.

Released

15. 7. 2022

Publisher

IEEE

ISBN

978-1-6654-2933-7

Book

45th International Conference on Telecommunications and Signal Processing (TSP 2022). IEEE, 2022

Pages from

206

Pages to

211

Pages count

6

URL

https://ieeexplore.ieee.org/document/9851236

BibTex

@inproceedings{BUT178628,
  author="Michal {Čičatka} and Radim {Burget} and Jan {Karásek}",
  title="Machine-learning Approach to Microbial Colony Localisation",
  booktitle="45th International Conference on Telecommunications and Signal Processing (TSP 2022). IEEE, 2022",
  year="2022",
  pages="206--211",
  publisher="IEEE",
  doi="10.1109/TSP55681.2022",
  isbn="978-1-6654-2933-7",
  url="https://ieeexplore.ieee.org/document/9851236"
}