‍Objectives
‍In recent years there has been an increase in the application of image analysis technologies within the clinical laboratory, particularly within the cell-based fields of haematology, anatomical pathology and cytopathology. The agar plate remains an important diagnostic tool within the clinical laboratory and has not yet been replaced by alternate technologies. Agar plates continue to provide a reliable microbial detection system, even though they are associated with requirements for highly trained staff, laboratory space and minimal access to automated handling.

The Automated Plate Assessment System (APAS) is an image analysis system dedicated to screening agar plates following incubation. The system detects colony growth, enumerates the various colony types present and applies conventional microbiological logic to sort each plate into categories suitable for further processing.

The aim of this study was to evaluate the abilities of this imaging device to screen three routinely used agars following inoculation with clinical specimens.

‍Methods
‍One hundred and one stool samples were inoculated onto Xylose Lysine Desoxycholate agar and one hundred and seventy urines onto Horse Blood Agar and Brilliance UTI Clarity Agar bi-plates (Thermo Fisher Scientific, Thebarton, Australia). Following incubation, the plates were read by experienced microbiologists and then analysed by a prototype Automated Plate Assessment System, APAS (LBT Innovations Ltd, Adelaide, Australia). The results for colony detection, enumeration and preliminary colony identification were then compared. Results generated from the two-plate urine protocol by the APAS Decision Support System were also compared with those produced by the microbiologists.

‍Conclusions
‍The image analysis technology used by APAS demonstrated an ability to detect target colonies on XLD agar and differentiated them from colonies of non-pathogenic species. No potential pathogens were missed by APAS in this series of cases. As a device for screening a multi-agar protocol such as urine, APAS also was able to perform colony counts and provide a preliminary identification for the primary isolates. The incorporation of a Decision Support System with plate interpretation logic and standard reporting rules further enhanced the usefulness of the system.

Poster Presentation: LBT Innovations Ltd and Australian Centre for Visual Technologies, University of Adelaide

‍Conference: ECCMID 2014

‍Date: May 2014, Barcelona

‍Authors: Glasson, J.H., Hill, R. and Summerford, M.J.

‍Citation: Glasson, J.H., Hill, R. and Summerford, M.J. 2014. Initial Evaluation of an image analysis device for the screening of cultures from clinical specimens. ECCMID 2014. Barcelona.