Automated Counting of Bacterial Colony Forming Units on Agar Plates

Abstract

Manual counting of bacterial colony forming units (CFUs) on agar plates is laborious and error-prone. We therefore implemented a colony counting system with a novel segmentation algorithm to discriminate bacterial colonies from blood and other agar plates. A colony counter hardware was designed and a novel segmentation algorithm was written in MATLAB. In brief, pre-processing with Top-Hat-filtering to obtain a uniform background was followed by the segmentation step, during which the colony images were extracted from the blood agar and individual colonies were separated. A Bayes classifier was then applied to count the final number of bacterial colonies as some of the colonies could still be concatenated to form larger groups. To assess accuracy and performance of the colony counter, we tested automated colony counting of different agar plates with known CFU numbers of S. pneumoniae , P. aeruginosa and M. catarrhalis and showed excellent performance.

Automated counting of bacterial colonies by image analysis

“…Using the fact that three points can define a circle, they then semiautomatically identified the rims of Petri dishes and used the compactness ratio to determine the existence of clustered colonies that require dividing. Brugger et al (2012) used one CCD to capture images of colonies. The boundary of the dish was viewed as a perfect circle.…”

Multistage classification for bacterial colonies recognition on solid agar images

“…Up to now, the majority of HW/SW imaging solutions related to bacteria colony growth have been focused on providing automated colony counting features, especially for application fields relying on exact (quantitative) and fast bacterial load estimation, such as food and beverage safety [2], [3], [4] or various environmental control and specific clinical usages [5], [6], [7]. Clinical bacteriology usually requires qualitative bacterial load estimation even in cases where massively confluent colonies growth occurs and traditional bacterial enumeration systems would fail.…”

“…Similarly to what proposed in [6] we adopted the adaptive thresholding foreground detection technique described in [16] where, for each pixel I(x, y), a different threshold is selected according to the intensity values in its local neighborhood. A binary segmentation result is obtained according to the following steps (also depicted in Fig.3): • 1) compute A(x, y) = h σ (x, y) I(x, y) with h σ (x, y) the averaging kernel of radius σ.…”

Colonizer: Anandroid OS based automated microbial colony counter

“…Zhang et al, 2009 [4] designed an automatic bacterial colony counting system using a Nikon D50 DSLR for image acquisition and an Intel Core 2 Duo PC for running the watershed algorithm for segmenting colonies. Recently, Brugger et al, 2012 [5] came up with a hardware setup for automatic counting of bacterial CFUs on agar plates. They used a circular darkfield illuminator with an uEye UI1640C Camera for imaging and a PCfor adaptive thresholding and segmenting colonies.…”