×

Recognition of species and genera of bacteria by means of the product of weights of the classifiers. (English) Zbl 1466.92114

Summary: In microbiology, computer methods are applied in the analysis and recognition of laboratory-acquired microscopic images concerning, for example, bacterial cells or other microorganisms. Proper recognition of the species and genera of bacteria is a key stage in the microbiological diagnostics process, because it allows a quick start of the appropriate therapy. The original method proposed in the paper concerns the automatic recognition of selected species and genera of bacteria presented in digital images. The classification was made on the basis of the analysis of the physical characteristics of bacterial cells using the product of classifier confidence weights. The end result of the classification process is the classification list, sorted in descending order according to the weights of the classifiers. In addition to the correct classification, a list of other possible results of the analysis is obtained. The method thus allows not only the classification, but also an analysis of the confidence level of the selection made. The proposed method can be used to recognize not only bacterial cells, but also other microorganisms, for example, fungi that exhibit similar morphological characteristics. In addition, the use of the method does not require the application of specialized computer equipment, which widens the scope of applications regardless of the laboratory IT infrastructure, not only in microbiological diagnostics, but also in other diagnostic laboratories.

MSC:

92C70 Microbiology
62P10 Applications of statistics to biology and medical sciences; meta analysis
62H30 Classification and discrimination; cluster analysis (statistical aspects)

Software:

AlexNet; ImageNet
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Abdullah, A., Jing, T., Sie, C., Yusuf, N., Zakaria, A., Omar, M., Shakaff, A.M., Adom, A.H., Kamarudin, L., Juan, Y. and et al. (2014). Rapid identification method of aerobic bacteria in diabetic foot ulcers using electronic nose, Advanced Science Letters20(1): 37-41.
[2] Alvarez-Ordonez, A., Mouwen, D., Lopez, M. and Prieto, M. (2011). Fourier transform infrared spectroscopy as a tool to characterize molecular composition and stress response in foodborne pathogenic bacteria, Journal of Microbiological Methods84(3): 369-378.
[3] Arabestani, M.R., Fazzeli, H. and Esfahani, B.N. (2014). Identification of the most common pathogenic bacteria in patients with suspected sepsis by multiplex PCR, Journal of Infection in Developing Countries8(4): 461-468.
[4] Ates, H. and Gerek, O.N. (2009). An image-processing based automated bacteria colony counter, Proceedings: International Symposium on Computer and Information Sciences ISCIS, Guzelyurt, Cyprus, pp. 18-23.
[5] Blackburn, N., Hagström, Å., Wikner, J., Cuadros-Hansson, R. and Bjórnsen, P.K. (1998). Rapid determination of bacterial abundance, biovolume, morphology, and growth by neural network-based image analysis, Applied and Environmental Microbiology64: 3246-3255.
[6] Bruyne, D.K., Slabbinck, B., Waegeman, W., Vauterin, P., De Baets, B. and Vandamme, P. (2011). Bacterial species identification from MALDI-TOF mass spectra through data analysis and machine learning, Systematic and Applied Microbiology34(1): 20-29.
[7] Bulanda, M. and Brzychczy-Włoch, M. (Eds) (2015). Microbiology and Parasitology: Lecture Notes for 2nd Year Students of the Faculty of Medicine of Jagiellonian University Collegium Medicum, Cracow Scientific Publishers Tekst, (in Polish).
[8] Cimpoi, M., Maji, S., Kokkinos, I. and Vedaldi, A. (2016). Deep filter banks for texture recognition, description, and segmentation, International Journal of Computer Vision118: 65-94.
[9] Cortes, C. and Vapnik, V. (1995). Support-vector networks, Machine Learning20: 273-297. · Zbl 0831.68098
[10] Green, G., Chan, A. and Lin, M. (2014). Robust identification of bacteria based on repeated odor measurements from individual bacteria colonies, Sensors and Actuators B: Chemical190: 16-24.
[11] Hasman, H., Saputra, D., Sicheritz-Ponten, T., Lund, O., Svendsen, C., Frimodt-Móller, N. and Aarestrup, F. (2013). Rapid whole genome sequencing for the detection and characterization of microorganisms directly from clinical samples, Journal of Clinical Microbiology52(1): 139-146.
[12] Hiremath, P. and Bannigidad, P. (2009). Automated gram-staining characterization of digital bacterial cell images, Procceedings: International Conference on Signal and Image Processing ICSIP, Amsterdam, The Netherlands, pp. 209-211.
[13] Holmberg, M., Gustafsson, F., Hörnsten, G.E., Winquist, F., Nilsson, L.E., Ljung, L. and Lundström, I. (1998). Bacteria classification based on feature extraction from sensor data, Biotechnology Techniques12(4): 319-324.
[14] Kim, H., Doh, I.-J., Bhunia, A., King, G. and Bae, E. (2015). Scalar diffraction modeling of multispectral forward scatter patterns from bacterial colonies, Optics Express23(7): 8545-8554.
[15] Krizhevsky, A., Sutskever, I. and Hinton, G. (2012). Imagenet classification with deep convolutional neural networks, in P. Bartlett (Ed.), Advances in Neural Information Processing Systems, NIPS, San Diego, CA, pp. 1097-1105.
[16] Kusic, D., Kampe, B., Rösch, P. and Popp, J. (2014). Identification of water pathogens by Raman microspectroscopy, Water Research48: 179-189.
[17] Liu, J., Dazzo, F., Glagoleva, O., Yu, B. and Jain, A. (2001). CMEIAS: A computer-aided system for the image analysis of bacterial morphotypes in microbial communities, Microbial Ecology41: 173-194.
[18] Murray, P., Rosenthal, K. and Pfaller, M. (2015). Medical Microbiology, Elsevier, Amsterdam.
[19] Perner, P. (2001). Classification of hep-2 cells using fluorescent image analysis and data mining, International Symposium on Medical Data Analysis: Medical Data Analysis, Madrid, Spain, pp. 219-224. · Zbl 1030.68813
[20] Plichta, A. (2019). Methods of classification of the genera and species of bacteria using decision tree, Journal of Telecommunications & Information Technology4: 74-82.
[21] Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition, https://arxiv.org/abs/1409.1556.
[22] Sommer, C. and Gerlich, D. (2013). Machine learning in cell biology—Teaching computers to recognize phenotypes, Journal of Cell Science126: 18-23.
[23] Suchwałko, A., Buzalewicz, I. and Podbielska, H. (2014). Bacteria identification in an optical system with optimized diffraction pattern registration condition supported by enhanced statistical analysis, Optics Express22(21): 26312-26327.
[24] Suchwałko, A., Buzalewicz, I., Wieliczko, A. and Podbielska, H. (2013). Bacteria species identification by the statistical analysis of bacterial colonies fresnel patterns, Optics Express21(9): 11322-11337.
[25] Tadeusiewicz, R. and Wajs, W. (1999). Health Informatics, AGH University of Science and Technology Press, Cracow, (in Polish).
[26] Trattner, S., Greenspan, H., Tepper, G. and Abboud, S. (2004). Automatic identification of bacterial types using statistical imaging methods, IEEE Transactions on Medical Imaging23: 807-820.
[27] Zieliński, B., Plichta, A., Misztal, K., Spurek, P., Brzychczy-Włoch, M. and Ochońska, D. (2017). Deep learning approach to bacterial colony classification, PloS One12(9): e0184554.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.