Search

Background The application of image analysis technologies for the interpretation of microbiological cultures is evolving rapidly. The primary aim of this study was to establish whether the image analysis system named Automated Plate Assessment System (APAS; LBT Innovations Ltd., Australia) could be applied to screen urine cultures. A secondary aim was to evaluate differences between traditional plate reading (TPR) and the reading of cultures from images, or digital plate reading (DPR). Methods A total of 9,224 urine samples submitted for culture to three clinical laboratories, two in Australia and one in the USA, were included in the study. Cultures were prepared on sheep blood and MacConkey agar plates and read by panels of three microbiologists. The plates were then presented to APAS for image capture and analysis, and the images and results were stored for later review. Results Image analysis of cultures using APAS produced a diagnostic sensitivity and specificity of 99.0% and 84.5%, respectively. Colonies were detected by APAS on 99.0% of blood agar plates with growth and on 99.5% of MacConkey agar plates. DPR agreed with TPR for colony enumeration on 92.1% of the plates, with a sensitivity of 90.8% and specificity of 92.8% for case designation. However, several differences in the classification of colony morphologies using DPR were identified. Conclusions APAS was shown to be a reliable screening system for urine cultures. The study also showed acceptable concordance between DPR and TPR for colony detection, enumeration, and case designation.

Letting go of traditional 'one-sided' teaching practices and moving towards power sharing and learning with students can be a daunting and challenging process. This article describes one teacher's journey towards a sociocultural approach and what supported him.

The subject of laboratory error was examined during a symposium at the ASM Microbe 2016 conference in Boston, MA. During the session, it became clear that discussion on this subject has not flourished within our field, possibly due to a lack of published experiences. We therefore submit our

A key enabler for the construction of large-scale intelligent surveillance systems is the accurate estimation of activity topology graphs. An activity topology graph describes the relationships between the fields of view of the cameras in a surveillance network. An accurate activity topology estimate allows higher-level processing such as network-wide tracking to be localised within neighbourhoods defined by the topology, and thus to scale. The camera overlap graph is an important special case of the general activity topology, in which edges represent overlap between cameras’ fields of view. We describe a family of pairwise occupancy overlap estimators, which are the only approaches proven to scale to networks with thousands of cameras. A distributed implementation is described, which enables the estimator to scale beyond the limits achievable by centralised implementations, and supports growth of the network whilst it remains online. Formulae are derived to describe the memory and network bandwidth requirements of the distributed implementation, which are verified by empirical results. Finally, the efficacy of the overlap estimators is demonstrated using results from their application in higher-level processing, specifically to network-wide tracking, which becomes feasible within the topology oriented architecture.

The development of assignments for undergraduate teaching typically requires a compromise between what is achievable by an average student and what engages the interest of a more advanced member of the class. Selecting a suitable compromise is particularly problematic for undergraduate artificial intelligence (AI) courses which typically attempt to cover a very broad range of topics, without delving too deeply into the details. Ideally, a single problem would be selected whose solution could be approached with more than one technique covered in the course, enabling students to carry out a comparative analysis of performance. Robot soccer simulation has provided an interesting platform for artificial intelligence research and is increasingly being used as a teaching apparatus. There are a number of limitations with existing simulation methodologies for this purpose. Current robot soccer simulators are aimed at research groups where accuracy is paramount and all facets of the real system must be emulated. However, many of the intricacies of a real robot soccer player are inappropriate for a teaching environment, as they detract from desired learning outcomes. Consequently, there is a need for a simulation that employs a simplified set of game rules and dynamics. This paper describes the design and implementation of such a framework and presents experiences gained from its use as a third year practical.