Submitted to: Food and Bioprocess Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/22/2015
Publication Date: 7/10/2015
Citation: Yoon, S.C., Lawrence, K.C., Park, B. 2015. Automatic counting and classification of bacterial colonies using hyperspectral imaging. Food and Bioprocess Technology. 8:2047-2065.
Interpretive Summary: Counting of bacterial colonies on agar plates is essential to estimate the density of microorganisms within a culture. Screening of agar plates is also essential to find presumptive positive pathogens in the culture. Manual counting and screening of pathogenic colonies is labor-intensive and often prone to human errors due to phenotypic difference in genetically similar microorganisms and presence of background microflora. This paper reports the development of a technique for detecting and counting pathogenic bacterial colonies on an agar plate using hyperspectral imaging. Visible and near-infrared hyperspectral imaging was used to detect bacterial colonies and to classify the types of non-O157 E. coli bacteria on agar plates. The automated colony segmentation algorithm with hyperspectral imaging was effective to detect colonies and to separate touching objects. The study also demonstrated the potential of a hyperspectral imaging system that provides a rapid and accurate tool to enumerate and identify pathogens on agar plates.
Technical Abstract: Detection and counting of bacterial colonies on agar plates is a routine microbiology practice to get a rough estimate of the number of viable cells in a sample. There have been a variety of different automatic colony counting systems and software algorithms mainly based on color or gray-scale pictures although manual counting is still common. In microbiology, identification of presumptive-positive colonies on agar plates is predominantly done manually, which is laborious and time-consuming. This paper addresses a problem related to automatic colony detection and classification that can count the number of colonies according to their type. Hyperspectral imaging was used to develop a colony segmentation algorithm for detecting non-O517 Shiga-toxin producing Escherichia coli (STEC) pathogens on Rainbow agar. Hyperspectral absorbance image analysis in the visible and near-infrared spectral range showed that colony morphology including size and texture was dependent on wavelength. The non-O157 STEC colonies showed dome-like absorbance distributions, which was used for finding local maxima. Touching colonies, causing problems for accurate counting and identification, were separated into multiple entities by optimally tessellating the mesh structure of local maximal points. The accuracy of the colony counting algorithm was up to 98.9%. The average of the colony classification algorithm using automated colony segments was 92.5%.