This study was designed to evaluate hyperspectral microscope images for early and rapid detection of Salmonella serotypes Enteritidis, Heidelberg, Infantis, Kentucky, and Typhimurium at incubation times of 6, 8, 10, 12, and 24 h. Images were collected by an acousto-optical tunable filter hyperspectral microscope imaging system with a metal halide light source measuring 89 contiguous wavelengths every 4 nm between 450 and 800 nm. Pearson correlation values were calculated for incubation times of 8, 10, and 12 h and compared with data for 24 h to evaluate the change in spectral signatures from bacterial cells over time. Regions of interest were analyzed at 30% of the pixels in an average cell size. Spectral data were preprocessed by applying a global data transformation algorithm and then subjected to principal component analysis (PCA). The Mahalanobis distance was calculated from PCA score plots for analyzing serotype cluster separation. Partial least-squares regression was applied for calibration and validation of the model, and soft independent modeling of class analogy was utilized to classify serotype clusters in the training set. Pearson correlation values indicate very similar spectral patterns for reduced incubation times ranging from 0.9869 to 0.9990. PCA score plots indicated cluster separation at all incubation times, with incubation time Mahalanobis distances of 2.146 to 27.071. Partial least-squares regression had a maximum root mean squared error of calibration of 0.0025 and a root mean squared error of validation of 0.0030. Soft independent modeling of class analogy correctly classified values at 8 h (98.32%), 10 h (96.67%), 12 h (88.33%), and 24 h (98.67%) with the optimal number of principal components (four or five). The results of this study suggest that Salmonella serotypes can be classified by applying a PCA to hyperspectral microscope imaging data from samples after only 8 h of incubation.
: Hyperspectral microscope images (HMIs) have previously shown promise as a means for rapid and early detection of foodborne bacteria at the cellular level. System calibration and data normalization are critical for comparing information obtained from HMIs collected with multiple instruments and system parameters. Here, we implement a wavelength and radiometric calibration for spectral data obtained from a hyperspectral microscope, assess the spatial uniformity of HMIs, and show the need to normalize data from single-cell regions of interest (ROIs). A hyperspectral microscope with a tungsten halogen light source, acousto-optical tunable filter, and electron multiplying camera with variable gain and exposure time settings were used. HMIs were collected at additional gain settings of 0%, 1.6%, 3.5%, and 5.1% along with ten exposure time settings between 100 and 1000 ms with both calibration lamps. Wavelength peak shift started to occur at an exposure time of 600 ms for 1.6% gain, at 400 ms for 3.5% gain, and at 200 ms for 5.1% gain. HMIs of , Typhimurium, and cells were collected to assess spectral data normalcy and the need for preprocessing spectra from single bacteria cells. Spatial characteristics of cells were assessed by HMIs of a glass slide with a micrometer for determining pixel size from the field of view. HMIs were preprocessed by normalizing cell spectra to the light source and applying multiplicative scatter correction. Data normalcy was assessed on both the raw and preprocessed data sets. Preprocessing the data was found to reduce the cell-to-cell variation associated with a single-cell ROI method, while outliers were detected and verified through HMIs as physically different from other cells. Keywords: Bacteria, Calibration, Food safety, Hyperspectral microscope, Pathogen.