Technical Abstract: A new non-destructive imaging method was investigated as an automated presumptive colony screening technique to rapidly detect and accurately identify pathogenic non-O157 Shiga-toxin producing Escherichia coli (STEC) serotypes on agar plates. Although traditional culture methods are still the “gold standard” for presumptive-positive detection of pathogens, they are time-consuming and not effective in testing large amount of food samples. Another challenge is unwanted background microflora grow together with target microorganisms on agar media and often look similar. Hyperspectral imaging is an optical imaging technique that combines aspects of conventional imaging and vibrational spectroscopy so that data can provide two-dimensional spatial information on colony shapes and one-dimensional spectral information at every pixel in each colony under test. In this study, the spectral “fingerprints” of bacteria provided by the hyperspectral imaging were used for detection and identification of pathogens. A hyperspectral imaging method was tested to discriminate each of big 6 non-O157 STEC serotypes (O26, O111, O45, O121, O103, and O145) on agar plates. Spectral libraries of pure pathogen cultures were built and classification models were developed. Tests with Rainbow agar plates showed the potential of the hyperspectral imaging technique for rapid screening of food samples contaminated by STEC pathogens.