Automated fluorescence microscopy image analysis of Pseudomonas aeruginosa bacteria in alive and dead stadium. (January 2018)

• Record Type: Journal Article
• Authors: Woźniak, Marcin; Połap, Dawid; Kośmider, Leon; Cłapa, Tomasz
• Is Part Of: Engineering applications of artificial intelligence. Volume 67(2018:Jan.)
• Page Start: 100
• Page End: 110
• Publication Date: 2018-01
• Subjects: 92C55 -- 68U10 -- 68T10 -- 68T45; Fluorescence microscopy -- Bacteria detection -- Automated image analysis; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2017.09.003
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Fluorescent microscopy techniques take advantage of observing even single cells in live and dead stadium, and make it possible to selectively recognize specific components of biomolecular structures. This methodology is based on Green Fluorescent Protein (GFP) recognition of biochemical activities of individual microbial cells visible in screening. Unfortunately, recognition perception of human professional for fluorescent signals can be affected by various environmental factors what can lead to false interpretation of the results. Therefore intelligent computer method for fluorescent signal counting can be a great assistance at work. In this article we present experimental research results on the development of new automated fluorescence microscopy image analysis, implemented for Pseudomonas aeruginosa bacteria. Proposed method is composed of two stages of image processing. In the first, we enhance the image and extract only important bacteria shapes into simplified image. In the second, this simplification is used for detection of rod shape and spherical shape bacteria. At the end of processing statistical analysis is performed to evaluate number of bacteria in dead and alive stadium. Highlights: Novel, efficient methodology for bacteria detection from fluorescent microscopy images. Automated approach to analysis and calculation of bacteria, both in dead and alive stadium. Experimental research results for Pseudomonas aeruginosa . Epifluorescence microscope, filter set for Green Fluorescence Protein plasmid and for Propidium Iodide.