Computer Vision Approach for the Determination of Microbial Concentration and Growth Kinetics Using a Low Cost Sensor System
"> Figure 1
<p>Picture of the proposed computer vision sensor system for microbial analysis (<b>a</b>) and designed mask to select the area of the inoculum (<b>b</b>).</p> "> Figure 2
<p>Pictures of the colonies grown on the Petri dish in the case of the microbial specie <span class="html-italic">Saccharomyces cerevisiae</span>. Picture taken by the camera (<b>a</b>), after the binarization process (<b>b</b>) and after the application of the blob detection algorithm (<b>c</b>).</p> "> Figure 3
<p>Number of detected colonies as a function of time in the case of <span class="html-italic">Escherichia coli</span> plated on BHI medium (microbial concentration 2500 CFU/mL). The algorithm has been implemented with a binarization threshold parameter of 0.07 for different values of the blur parameter (0.5–5).</p> "> Figure 4
<p>Number of detected colonies (<b>a</b>) and percent of covered area (<b>b</b>) as a function of time in the case of <span class="html-italic">Escherichia coli</span> plated on BHI medium (microbial concentration 2500 CFU/mL). The algorithm has been implemented with blur parameter of 0.5 for different values of the binarization threshold parameter (0.03–0.17).</p> "> Figure 5
<p>Number of detected colonies (<b>a</b>), percent of covered area (<b>b</b>) and percent of covered area for a single colony (<b>c</b>) as a function of time in the case of <span class="html-italic">Escherichia coli</span> plated on BHI medium for different microbial concentrations of the inoculum.</p> "> Figure 6
<p>Percent of covered area for a single colony plotted vs. time in the case of the different microbial species and growth media investigated in this work.</p> "> Figure 7
<p>Scatter plot representing the number of detected colonies (<b>a</b>) and the error of the number of detected colonies (<b>b</b>) vs. the microbial concentration measured by the reference PCT assay in the case of the full set of investigated samples and the number of detected colonies vs. the microbial concentration for a subset of samples featuring a microbial concentration lower than 1200 CFU/mL (<b>c</b>).</p> "> Figure 8
<p>Schematic of a possible implementation of the computer vision sensor system proposed in this work in the form of an embedded electronic instrument for microbial analysis outside a laboratory environment.</p> ">
Abstract
:1. Introduction
2. Materials and Methods
2.1. The Computer Vision Sensor System
- −
- the image is blurred using a blur parameter of 5,
- −
- the image is converted from RGB to grayscale,
- −
- an image is generated as the difference of the current image and the image acquired at time 0,
- −
- the new generated image is binarized using a threshold of 0.07,
- −
- the number of colonies and the total colonies area for the binarized image are determined.
2.2. Microbiological Analysis
3. Results and Discussion
3.1. Determination of the Algorithm Parameters
3.2. Evaluation of the Algorithm Accuracy
3.3. Towards an Embedded Electronic System
4. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Justino, C.I.; Duarte, A.C.; Rocha-Santos, T.A. Recent progress in biosensors for environmental monitoring: A review. Sensors 2017, 17, 2918. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Partyka, M.L.; Bond, R.F.; Chase, J.A.; Atwill, E.R. Monitoring bacterial indicators of water quality in a tidally influenced delta: A Sisyphean pursuit. Sci. Total Environ. 2017, 578, 346–356. [Google Scholar] [CrossRef] [PubMed]
- Välimaa, A.L.; Tilsala-Timisjärvi, A.; Virtanen, E. Rapid detection and identification methods for Listeria monocytogenes in the food chain—A review. Food Control 2015, 55, 103–114. [Google Scholar] [CrossRef]
- Mizan, M.F.R.; Jahid, I.K.; Ha, S.D. Microbial biofilms in seafood: A food-hygiene challenge. Food Microbiol. 2015, 49, 41–55. [Google Scholar] [CrossRef] [PubMed]
- Bertelli, C.; Greub, G. Rapid bacterial genome sequencing: Methods and applications in clinical microbiology. Clin. Microbiol. Infect. 2013, 19, 803–813. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Fournier, P.E.; Drancourt, M.; Colson, P.; Rolain, J.M.; La Scola, B.; Raoult, D. Modern clinical microbiology: New challenges and solutions. Nat. Rev. Microbiol. 2013, 11, 574–585. [Google Scholar] [CrossRef]
- Scallan, E.; Hoekstra, R.M.; Angulo, F.J.; Tauxe, R.V.; Widdowson, M.A.; Roy, S.L.; Jones, J.L.; Griffin, P.M. Foodborne illness acquired in the United States—Major pathogens. Emerg. Infect. Dis. 2011, 17, 7. [Google Scholar] [CrossRef]
- Reasoner, D.J. Heterotrophic plate count methodology in the United States. Int. J. Food Microbiol. 2004, 92, 307–315. [Google Scholar] [CrossRef]
- Ladero, V.; Martínez, N.; Martín, M.C.; Fernández, M.; Alvarez, M.A. qPCR for quantitative detection of tyramine-producing bacteria in dairy products. Food Res. Int. 2010, 43, 289–295. [Google Scholar] [CrossRef]
- Sedgley, C.; Nagel, A.; Dahlén, G.; Reit, C.; Molander, A. Real-time quantitative polymerase chain reaction and culture analyses of Enterococcus faecalis in root canals. J. Endod. 2006, 32, 173–177. [Google Scholar] [CrossRef]
- Carbonnelle, E.; Mesquita, C.; Bille, E.; Day, N.; Dauphin, B.; Beretti, J.L.; Ferrini, A.; Gutmann, L.; Nassif, X. MALDI-TOF mass spectrometry tools for bacterial identification in clinical microbiology laboratory. Clin. Biochem. 2011, 44, 104–109. [Google Scholar] [CrossRef] [PubMed]
- Clark, A.E.; Kaleta, E.J.; Arora, A.; Wolk, D.M. Matrix-assisted laser desorption ionization–time of flight mass spectrometry: A fundamental shift in the routine practice of clinical microbiology. Clin. Microbiol. Rev. 2013, 26, 547–603. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Boehm, D.A.; Gottlieb, P.A.; Hua, S.Z. On-chip microfluidic biosensor for bacterial detection and identification. Sens. Actuators B Chem. 2007, 126, 508–514. [Google Scholar] [CrossRef]
- Singh, A.; Poshtiban, S.; Evoy, S. Recent advances in bacteriophage based biosensors for food-borne pathogen detection. Sensors 2013, 13, 1763–1786. [Google Scholar] [CrossRef] [Green Version]
- Wang, Y.; Ye, Z.; Ying, Y. New trends in impedimetric biosensors for the detection of foodborne pathogenic bacteria. Sensors 2012, 12, 3449–3471. [Google Scholar] [CrossRef] [Green Version]
- Ercole, C.; Del Gallo, M.; Mosiello, L.; Baccella, S.; Lepidi, A. Escherichia coli detection in vegetable food by a potentiometric biosensor. Sens. Actuators B Chem. 2003, 91, 163–168. [Google Scholar] [CrossRef]
- Nik Mansor, N.; Leong, T.; Safitri, E.; Futra, D.; Ahmad, N.; Nasuruddin, D.; Itnin, A.; Zaini, I.; Arifin, K.T.; Heng, L.Y.; et al. An amperometric biosensor for the determination of bacterial sepsis biomarker, secretory phospholipase group 2-IIA using a tri-enzyme system. Sensors 2018, 18, 686. [Google Scholar] [CrossRef] [Green Version]
- Grossi, M.; Riccò, B. Electrical impedance spectroscopy (EIS) for biological analysis and food characterization: A review. J. Sens. Sens. Syst. 2017, 6, 303–325. [Google Scholar] [CrossRef] [Green Version]
- Kleiss, T.; Albrecht, J.; Putallaz, T.; Cordier, J.L. Impedance measurement of the microbial flora in dairy-based desserts. J. Microbiol. Methods 1995, 22, 131–137. [Google Scholar] [CrossRef]
- Grossi, M.; Lanzoni, M.; Pompei, A.; Lazzarini, R.; Matteuzzi, D.; Ricco, B. A portable biosensor system for bacterial concentration measurements in cow’s raw milk. In Proceedings of the 4th IEEE International Workshop on Advances in Sensors and Interfaces (IWASI), Savelletri di Fasano, Italy, 28–29 June 2011; pp. 132–137. [Google Scholar]
- Hardy, D.; Kraeger, S.J.; Dufour, S.W.; Cady, P. Rapid detection of microbial contamination in frozen vegetables by automated impedance measurements. Appl. Environ. Microbiol. 1977, 34, 14–17. [Google Scholar]
- Bülte, M.; Reuter, G. Impedance measurement as a rapid method for the determination of the microbial contamination of meat surfaces, testing two different instruments. Int. J. Food Microbiol. 1984, 1, 113–125. [Google Scholar] [CrossRef]
- Grossi, M.; Lazzarini, R.; Lanzoni, M.; Pompei, A.; Matteuzzi, D.; Riccò, B. A portable sensor with disposable electrodes for water bacterial quality assessment. IEEE Sens. J. 2013, 13, 1775–1782. [Google Scholar] [CrossRef]
- Grossi, M.; Parolin, C.; Vitali, B.; Riccò, B. A portable sensor system for bacterial concentration monitoring in metalworking fluids. J. Sens. Sens. Syst. 2018, 7, 349–357. [Google Scholar] [CrossRef] [Green Version]
- Zhou, X.; King, V.M. An impedimetric method for rapid screening of cosmetic preservatives. J. Ind. Microbiol. 1995, 15, 103–107. [Google Scholar] [CrossRef]
- Gomez-Sjoberg, R.; Morisette, D.T.; Bashir, R. Impedance microbiology-on-a-chip: Microfluidic bioprocessor for rapid detection of bacterial metabolism. J. Microelectromech. Syst. 2005, 14, 829–838. [Google Scholar] [CrossRef] [Green Version]
- Grossi, M.; Parolin, C.; Vitali, B.; Riccò, B. Measurement of bacterial concentration using a portable sensor system with a combined electrical-optical approach. IEEE Sens. J. 2019, 19, 10693–10700. [Google Scholar] [CrossRef]
- Ates, H.; Gerek, O.N. An image-processing based automated bacteria colony counter. In Proceedings of the 24th International Symposium on Computer and Information Sciences, Guzelyurt, Cyprus, 14–16 September 2009; pp. 18–23. [Google Scholar]
- Brugger, S.D.; Baumberger, C.; Jost, M.; Jenni, W.; Brugger, U.; Mühlemann, K. Automated counting of bacterial colony forming units on agar plates. PLoS ONE 2012, 7, e33695. [Google Scholar] [CrossRef] [Green Version]
- Commercial Colony Counter. Available online: http://iul-instruments.com/product/sphereflash-automatic-colony-counter/ (accessed on 25 November 2019).
- Griffith, R.V.; McMahon, T.A.; Espinosa, G. A commercial bacterial colony counter for semiautomatic track counting. Nucl. Tracks Radiat. Meas. 1984, 8, 215–218. [Google Scholar] [CrossRef] [Green Version]
- Grossi, M. A sensor-centric survey on the development of smartphone measurement and sensing systems. Measurement 2019, 135, 572–592. [Google Scholar] [CrossRef]
- Minoi, J.L.; Chiang, T.T.; Lim, T.; Yusoff, Z.; Karim, A.H.A.; Zulharnain, A. Mobile vision-based automatic counting of bacteria colonies. In Proceedings of the International Conference on Information and Communication Technology (ICICTM), Kuala Lumpur, Malaysia, 16–17 May 2016; pp. 41–46. [Google Scholar]
- Poladia, M.; Fakatkar, P.; Hatture, S.; Rathod, S.S.; Kuruwa, S. Detection and analysis of waterborne bacterial colonies using image processing and smartphones. In Proceedings of the International Conference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials (ICSTM), Chennai, India, 6–8 May 2015; pp. 159–164. [Google Scholar]
- Blob Detection Algorithm, Principle of Work and Code in JAVA. Available online: http://www.labbookpages.co.uk/software/imgProc/blobDetection.html (accessed on 25 November 2019).
- Yuen, H.K.; Princen, J.; Illingworth, J.; Kittler, J. Comparative study of Hough transform methods for circle finding. Image Vis. Comput. 1990, 8, 71–77. [Google Scholar] [CrossRef] [Green Version]
Kinetics Parameter | E. coli (NA) | E. coli (BHI) | S. aureus (NA) | S. aureus (BHI) | P. aeruginosa (NA) | S. cerevisiae (SDA) |
---|---|---|---|---|---|---|
b | 572.65 ± 1.63 | 473.77 ± 7.64 | 1025.1 ± 153.2 | 1045.1 ± 69.93 | 727.9 ± 13.71 | 1502.9 ± 110.1 |
c | (6.91 ± 1.21)∙10−4 | (1.11 ± 0.1)∙10−3 | (2.13 ± 0.04)∙10−4 | (4.85 ± 1.15)∙10−4 | (9.01 ± 0.56)∙10−4 | (2.86 ± 0.44)∙10−4 |
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Grossi, M.; Parolin, C.; Vitali, B.; Riccò, B. Computer Vision Approach for the Determination of Microbial Concentration and Growth Kinetics Using a Low Cost Sensor System. Sensors 2019, 19, 5367. https://doi.org/10.3390/s19245367
Grossi M, Parolin C, Vitali B, Riccò B. Computer Vision Approach for the Determination of Microbial Concentration and Growth Kinetics Using a Low Cost Sensor System. Sensors. 2019; 19(24):5367. https://doi.org/10.3390/s19245367
Chicago/Turabian StyleGrossi, Marco, Carola Parolin, Beatrice Vitali, and Bruno Riccò. 2019. "Computer Vision Approach for the Determination of Microbial Concentration and Growth Kinetics Using a Low Cost Sensor System" Sensors 19, no. 24: 5367. https://doi.org/10.3390/s19245367