No abstract

Manual neuron tracing is a very labor-intensive task. In the drug screening context, the sheer number of images to process means that this approach is unrealistic. Moreover, the lack of reproducibility, objectivity, and auditing capability of manual tracing is limiting even in the context of smaller studies. We have developed fast, sensitive, and reliable algorithms for the purpose of detecting and analyzing neurites in cell cultures, and we have integrated them in software called HCA-Vision, suitable for the research environment. We validate the software on images of cortical neurons by comparing results obtained using HCA-Vision with those obtained using an established semi-automated tracing solution (NeuronJ). The effect of the Sez-6 deletion was characterized in detail. Sez-6 null neurons exhibited a significant increase in neurite branching, although the neurite field area was unchanged due to a reduction in mean branch length. HCAVision delivered considerable speed benefits and reliable traces. ' International Society for Analytical CytologyKey terms neurite tracing; neurite branching; neurite analysis; neurites; neurite outgrowth; neuron tracing; neuron analysis; cell morphology; neuron image analysis NEURITE tracing capabilities are invaluable in the drug development arena to identify compounds that display neuroprotective or neuroregenerative effects (1,2). Detailed morphological analyses of neurons are also vital for studying the normal development of dendritic and axonal arbors and for documenting neuropathological changes. Neurite arborization patterns established during development are characteristic for particular neuronal subtypes and relate to function. Neurite arbor size and shape influence the integration of synaptic inputs (3) and these, in turn, are regulated by both intrinsic developmental programs and external signals (4,5). Alterations in neurite arbors have been observed in a number of neuropathological conditions including mental retardation syndromes such as Down, Rett's and Fragile X syndromes (6), schizophrenia (7,8), and Alzheimer's disease (9).The simplest method for quantifying neurite arbors from digital micrographs involves intensity thresholding. Under controlled imaging conditions, good results can be obtained (10). However, most neurite images display noisy, low contrast areas that affect the ability to detect neurites. A recent implementation of neurite tracing by Xiong et al. used a multi-scale approach, with a Hessian matrix guiding the tracing (11). These authors report measurements of the total length of neurites and of the number of extremities. A system to study neurite dynamics has also been described (12). One of its most interesting features is the ability to correct for relatively frequent tracing mistakes by the use of a probabilistic model, making use of a mask associated with areas where pixel intensities change significantly from image to image.Here, we present a fully automated image analysis solution for generating neurite traces, for segmenting the ...

Recent advances in image classification methods, along with the availability of associated tools, have seen their use become widespread in many domains. This paper presents a novel application of current image classification approaches in the area of Emergency Situation Awareness. We discuss image classification based on low-level features as well as methods built on top of pretrained classifiers. The performance of the classifiers is assessed in terms of accuracy along with consideration to computational aspects given the size of the image database. Specifically, we investigate image classification in the context of a bush fire emergency in the Australian state of NSW, where images associated with Tweets during the emergency were used to train and test classification approaches. Emergency service operators are interested in having images relevant to such fires reported as extra information to help manage evolving emergencies. We show that these methodologies can classify images into fire and not fire-related classes with an accuracy of 86%.Keywords: classification, image processing, emergency response, machine learning, situation awareness InTRoDUcTIonIn times of crisis, it is increasingly common for the public to use social media to broadcast their needs, propagate news, and stay abreast of evolving situations (Landwehr and Carley, 2014). Situation awareness during disaster management and emergency response is an evolving area for research. In this context, situation awareness relates to picking up sensory cues from the environment, interpreting said cues, and forecasting what may occur (Endsley, 1995). The ubiquity of social media platforms presents an opportunity to harness developing information to improve situation awareness for management and response teams.With advances in natural language processing (NLP) technologies, attention has been given to research and development for extracting relevant information from streaming data such as Twitter. For example, Sen (2015) investigates finding tweets that do not reflect user sentiment using NLP. Varga et al. (2013) propose methods for matching problem reports to aid messages while Tweet4Act (Chowdhury et al., 2013) filters for irrelevant tweets. Power et al. (2014) have developed a system for processing large volumes of Twitter data using language models to identify Tweets of interest to emergency managers. An aspect of social media in relation to disaster management, which has so far received little attention, is images. Images have the potential to provide new insights on top of the text-derived intelligence in tweets, giving a rich and contextual information stream in crisis situations. For example, images of fires provide an immediate cue to crisis coordinators about an event allowing them to react appropriately. Images provide a less ambiguous insight into a situation compared to subjective textual descriptions. An image can show the size of the fire and also provide clues to environmental conditions such as weather conditions and the potential fuel load ...

Automating the analysis of neurons in culture represents a key aspect of the search for neuroactive compounds. A number of commercial neurite analysis software packages tend to measure some basic features such as total neurite length and number of branching points. However, with only these measurements, some differences between neurite morphologies that are clear to a human observer cannot be identified. The authors have developed a suite of image analysis tools that will allow researchers to produce quality analyses at primary screening rates. The suite provides sensitive and information-rich measurements of neurons and neurites. It can discriminate subtle changes in complex neurite arborization even when neurons and neurites are dense. This allows users to selectively screen for compounds triggering different types of neurite outgrowth behavior. In mixed cell populations, neurons can be filtered and separated from other brain cell types so that neurite analysis can be performed only on neurons. It supports batch processing with a built-in database to store the batch-processing results, a batch result viewer, and an ad hoc query builder for users to retrieve features of interest. The suite of tools has been deployed into a software package called HCA-Vision. The free version of the software package is available at http://www.hca-vision.com .