Tools for classification of growing/non-growing bacterial colonies using laser speckle imaging

Ilya Balmages; Janis Liepins; Stivens Zolins; Dmitrijs Bliznuks; Renars Broks; Ilze Lihacova; Alexey Lihachev

doi:10.3389/fmicb.2023.1279667

Tools for classification of growing/non-growing bacterial colonies using laser speckle imaging

Front Microbiol. 2023 Oct 20:14:1279667. doi: 10.3389/fmicb.2023.1279667. eCollection 2023.

Authors

Ilya Balmages^{1

2}, Janis Liepins³, Stivens Zolins⁴, Dmitrijs Bliznuks¹, Renars Broks^{1

5}, Ilze Lihacova², Alexey Lihachev²

Affiliations

¹ Faculty of Computer Science and Information Technology, Riga Technical University, Riga, Latvia.
² Institute of Atomic Physics and Spectroscopy, University of Latvia, Riga, Latvia.
³ Institute of Microbiology and Biotechnology, University of Latvia, Riga, Latvia.
⁴ Laboratorija Auctoritas Ltd., Riga, Latvia.
⁵ Department of Biology and Microbiology, Riga Stradins University, Riga, Latvia.

Abstract

Prior research has indicated the feasibility of assessing growth-associated activity in bacterial colonies through the application of laser speckle imaging techniques. A subpixel correlation method was employed to identify variations in sequential laser speckle images, thereby facilitating the visualization of specific zones indicative of microbial growth within the colony. Such differentiation between active (growing) and inactive (non-growing) bacterial colonies holds considerable implications for medical applications, like bacterial response to certain drugs or antibiotics. The present study substantiates the capability of laser speckle imaging to categorize bacterial colonies as growing or non-growing, a parameter which nonvisible in colonies when observed under white light illumination.

Keywords: artificial neural network; image processing; laser speckle imaging; microorganism activity estimation; sensitive subpixel correlation method.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This work has been supported by the European Regional Development Fund projects “Fast and cost-effective machine learning based system for microorganism growth analysis” (agreement No. 1.1.1.1/19/A/147), “Rapid assessment system of antibacterial resistance for patients with secondary bacterial infections” (No. 1.1.1.1/21/A/034), and by the Latvian Council of Science funded project “Dynamic laser speckle imaging for evaluation of fungal growth activity” (agreement No. lzp-2022/1-0247).