A preview of this full-text is provided by Wiley.
Content available from Expert Systems
This content is subject to copyright. Terms and conditions apply.
ORIGINAL ARTICLE
A swarm-optimized microbial colony counter
Sannidhan M S
1
| Jason Elroy Martis
2
| Senka Krivic
3
| Sudeepa K B
1
|
Pradeep Nazareth
4
1
Department of Computer Science and
Engineering, NMAM Institute of Technology
(Nitte Deemed to be University), Nitte,
Mangalore, India
2
Department of Information Science and
Engineering, NMAM Institute of Technology
(Nitte Deemed to be University), Nitte,
Mangalore, India
3
Faculty of Electrical Engineering, University
of Sarajevo, Sarajevo, Bosnia and Herzegovina
4
Department of Artificial Intelligence and
Machine Learning, Alva's Institute of
Engineering and Technology, Moodabidre,
India
Correspondence
Jason Elroy Martis, Department of Information
Science and Engineering, NMAM Institute of
Technology (Nitte Deemed to be University),
Nitte, Mangalore, India
Email: jason1987martis@nitte.edu.in
Abstract
The identification of bacterial colonies is deemed to be crucial in microbiology as it
helps in identifying specific categories of bacteria. The careful examination of colony
morphology plays a crucial role in microbiology laboratories for the identification of
microorganisms. Quantifying bacterial colonies on culture plates is a necessary task
in Clinical Microbiology Laboratories, but it can be time-consuming and susceptible
to inaccuracies. Therefore, there is a need to develop an automated system that is
both dependable and cost-effective. Advancements in Deep Learning have played a
crucial role in improving processes by providing maximum accuracy with a negligible
amount of error. This research proposes an automated technique to extract the bac-
terial colonies using SegNet, a semantic segmentation network. The segmented colo-
nies are then counted with the assistance of blob counter to accomplish the activity
of colony counting. Furthermore, to ameliorate the proficiency of the segmentation
network, the network weights are optimized using a swarm optimizer. The proposed
methodology is both cost-effective and time-efficient, while also providing better
accuracy and precise colony counts, ensuring the elimination of human errors
involved in traditional colony counting techniques. The investigative assessments
were carried out on three distinct sets of data: Microorganism, DIBaS, and tailored
datasets. The results obtained from these assessments revealed that the suggested
framework attained an accuracy rate of 88.32%, surpassing other conventional meth-
odologies with the utilization of an optimizer.
KEYWORDS
bacterial colonies, colony morphology, deep learning, microbiology, SegNet, swarm optimizer
1|INTRODUCTION
Identifying bacterial colonies is a crucial application in microbiology that helps to identify specific categories of bacteria. A bacterial conglomerate
refers to a cluster of microorganisms that originates from a solitary microbial entity. Discovering the colonies has many uses, such as in micro-
biome research and biofuel studies. Therefore, identifying colonies is an essential process in bacterial colony identification, which begins by
observing colony morphology (Badieyan et al., 2018). Colony features reveal the identity of a particular species of bacteria as they differ in struc-
ture between colonies. Analysing the physical characteristics of microbial colonies is an imperative proficiency employed in microbiological facili-
ties to discern and classify microorganisms. To examine the specific characteristics of microorganism colonies, it is crucial to isolate them from
neighbouring colonies. This allows for detailed observation of their distinct shapes, sizes, colours, surface appearances, and textures. Counting
bacterial colonies on microbiological culture plates is an essential quantitative task in medical microbiology facilities, despite being time-
consuming and prone to errors. Segmentation of bacterial colonies in live-cell microscopic image sequences is a challenging task that provides
Received: 30 April 2023 Revised: 21 July 2023 Accepted: 25 August 2023
DOI: 10.1111/exsy.13510
Expert Systems. 2024;41:e13510. wileyonlinelibrary.com/journal/exsy © 2023 John Wiley & Sons Ltd. 1of21
https://doi.org/10.1111/exsy.13510