Identification of Staphylococcus species with hyperspectral microscope imaging and classification algorithms

Abstract

Hyperspectral microscope imaging method was presented as a rapid and efficient tool to classify gram-positive bacteria species. The datacube (1024 × 1024 × 89) were obtained by hyperspectral microscope imaging system, which provided cell images between 450 and 800 nm wavelengths with 4-nm resolution, resulting in 89 contiguous spectral images that were acquired with an acousto-optic tunable filters (AOTF) hyperspectral imaging platform. Spectral information of bacteria were extracted from region-of-interest (ROI) in the cell, which were approximately between 140 and 380 pixels depending on the size of the cells. Using a Mahalanobis distance algorithm, the outliers beyond 99 % confidence of data were eliminated and classified five species with classification methods including partial least square discriminant analysis (PLS-DA) and support vector machine (SVM) for linear and non-linear classification algorithms to differentiate Staphylococcus species. PLS-DA classified five species with 89.8 % accuracy and 0.87 kappa coefficient; whereas, SVM had much higher classification accuracy of 97.8 % with 0.97 kappa coefficient. To reduce the number of wavelengths for fast data processing, thirty-one spectral bands out of 89 contiguous bands were selected using the correlation of each band. When SVM classification method with selected bands were used, the classification accuracy and kappa coefficient were 93.9 % and 0.92, respectively.