In our previous study we have shown that identification of bacteria species with the use of Fresnel diffraction patterns is possible with high accuracy and at low cost. Fresnel diffraction patterns were recorded with the optical system with converging spherical wave illumination. Obtained experimental results have shown that colonies of specific bacteria species generate unique diffraction signatures. Features used for building classification models and thus for identification were simply mean value and standard deviation calculated of pixel intensities within regions of interest called rings. This work presents new, interpretable features denoting morphological and textural properties of the Fresnel diffraction patterns and their verification with the use of the statistical analysis workflow specially developed for bacteria species identification. As data set of bacteria species diffraction patterns it is very important to find features that differentiate species in the best manner. This task includes two steps. The first is finding and extracting new, interpretable features that can potentially be better for bacteria species differentiation than the ones used before. While the second one is deciding which of them are the best for identification purposes. The new features are calculated basing on normalized diffraction patterns and central statistical moments. For the verification the analysis workflow based on ANOVA for feature selection, LDA, QDA and SVM models for classification and identification and CV, sensitivity and specificity for performance assessment of the identification process, are applied. Additionally, the Fisher divergence method also known as signal to noise ratio (SNR) for feature selection was exploited.
In the presented paper the optical system with converging spherical wave illumination for classification of bacteria
species, is proposed. It allows for compression of the observation space, observation of Fresnel patterns, diffraction
pattern scaling and low level of optical aberrations, which are not possessed by other optical configurations.
Obtained experimental results have shown that colonies of specific bacteria species generate unique diffraction
signatures. Analysis of Fresnel diffraction patterns of bacteria colonies can be fast and reliable method for
classification and recognition of bacteria species. To determine the unique features of bacteria colonies diffraction
patterns the image processing analysis was proposed. Classification can be performed by analyzing the spatial
structure of diffraction patterns, which can be characterized by set of concentric rings. The characteristics of such
rings depends on the bacteria species. In the paper, the influence of basic features and ring partitioning number
on the bacteria classification, is analyzed. It is demonstrated that Fresnel patterns can be used for classification
of following species: Salmonella enteritidis, Staplyococcus aureus, Proteus mirabilis and Citrobacter freundii.
Image processing is performed by free ImageJ software, for which a special macro with human interaction, was
written. LDA classification, CV method, ANOVA and PCA visualizations preceded by image data extraction
were conducted using the free software R.
A novel method for evaluation of bacteria colonies concentration based on optical spectra examination, is proposed. The
influence of bacteria colonies number on Fourier spectrum properties is considered in term of scalar diffraction theory
and corresponding theoretical model is presented. Computational simulations are performed to confirm the theoretical
predictions. Additionally, optical Mellin transform is used to omit the dependence of Fourier spectrum pattern on
bacteria colonies size fluctuations and to provide a scale-invariant analysis. Presented results have shown high potential
of the proposed approach for comparative study of bacteria colonies grown on solid medium in vitro.