Search

Much recent research attention has focused on providing some form of visually meaningful information to blind people through electrical stimulation of a component of the visual system. Current technology limits the number of perceived points of light (phosphenes) that can be provided to a user and methods are required to optimize the amount of presented information. This paper describes a PDA based artificial human vision simulator, and proposes a method for alerting a user of possible looming obstacles. Experimental results indicate that obstacle alerts can be successfully provided, however with the current simulator components, high-quality lighting and accurate image segmentation is critical for reducing the number of false alerts.

This paper examines intelligent image processing constraints which may need to be considered for visual prosthesis development and proposes a display framework which incorporates context, task and alerts related to a scene. A simulation device to investigate this framework is also described. Mobility requirements, assessment, and devices are discussed to identify the functions required by a prosthesis, and an overview of state of the art visual prostheses is provided. Two main computer vision approaches are discussed with application to a visual prosthesis: information reduction and scene understanding.

Multi-slice spiral computed tomography angiography (MS-CTA) is emerging as a clinically robust modality for diagnosis and surgical planning for coronary heart disease. To enable these tasks the coronary arteries must be segmented and visualised. This paper proposes the use of an improved tracking-based algorithm for segmenting the coronary artery network. The segmentation results are coupled with direct volume rendering allowing for the 3-D visualisation of the degree of stenosis. We represent vessels using a generalised-cylinder model, which facilitates fast segmentation and the visualisation of vessel cross-sectional area. A number of synthetic and in vivo datasets are used to validate and demonstrate the approach.

We present a novel system for 3-D visualisation of the heart and coronary arteries. Binary tags (generated offline) are combined with value-gradient transfer functions (specified online) allowing for interactive visualisation, while relaxing the offline segmentation criteria. The arteries are roughly segmented using a Hessian-based line filter and the pericardial cavity using a Fast Marching active contour. A comparison of different contour initialisations reveals that simple geometric shapes (such as spheres or extruded polygons) produce suitable results.

Image fusion provides a mechanism to combine multiple images into a single representation to aid human visual perception and image processing tasks. Such algorithms endeavour to create a fused image containing the salient information from each source image, without introducing artefacts or inconsistencies. Image fusion is applicable for numerous fields including: defence systems, remote sensing and geoscience, robotics and industrial engineering, and medical imaging. In the medical imaging domain, image fusion may aid diagnosis and surgical planning tasks requiring the segmentation, feature extraction, and/or visualisation of multi-modal datasets. This paper discusses the implementation of an image fusion toolkit built upon the Insight Toolkit (ITK). Based on an existing architecture, the proposed framework (GIFT) offers a 'plug-and-play' environment for the construction of n-D multi-scale image fusion methods. We give a brief overview of the toolkit design and demonstrate how to construct image fusion algorithms from low-level components (such as multi-scale methods and feature generators). A number of worked examples for medical applications are presented in Appendix A, including quadrature mirror filter discrete wavelet transform (QMF DWT) image fusion.

Introduction. Coronary heart disease is the primary cause of sudden death in Australia, and is predicted to become the single leading health problem for the world by 2020 [1]. This disease results from an accumulation of plaque (consisting of cholesterol, calcium, and other substances) on the interior surface of arteries supplying the heart. Multi-slice spiral computed tomography angiography (MS-CTA) is emerging as a non-invasive alternative to the current "gold-standard" -- catheter-based coronary angiography (CCA) [2]. To effectively employ MS-CTA as a diagnostic tool, cardiologists use a variety of post-processing software algorithms to measure the degree of artery blockage (known as stenosis). Currently a number of algorithms exist including: oblique sectioning, curved sectioning, thin-slab maximum intensity projection (MIP), and surface rendering [3]. Methods. Unfortunately the current algorithms are inherently limited for providing insight into the complex three dimensional nature of diseased coronary arteries. These limitations stem from the two dimensional nature of these methods and/or their inability to clearly distinguish the vessel lumen from calcification artefacts. This work proposes the combined use of vessel segmentation and direct volume rendering (DVR) as a post-processing technique for more easily assessing stenosis within MS-CTA datasets. We present an initial investigation into a tracking-based vessel segmentation algorithm, coupled with direct volume rendering for visualisation. Results. A number of synthetic datasets were generated for the purpose of developing and verifying the tracking-based segmentation algorithm. Visual inspection of initial results from these synthetic datasets demonstrates the usefulness and potential of the proposed method. Further, we discuss a number of issues and present preliminary results for applying the segmentation method to real MS-CTA datasets. Conclusions. An initial investigation was undertaken into the usefulness of assessing coronary heart disease by applying vessel segmentation and direct volume rendering. Preliminary results using both synthetic and real datasets were presented and discussed. This method shows potential for allowing cardiologists to more easily visualise the complex three dimensional nature of diseased arteries, as well as providing a means to assess the true vessel lumen in the presence of calcification artefacts.

Direct volume rendering (DVR) provides medical users with insight into datasets by creating a 3-D representation from a set of 2-D image slices (such as CT or MRI). This visualisation technique has been used to aid various medi-cal diagnostic and therapy planning tasks. Volume render-ing has recently become faster and more affordable with the advent of 3-D texture-mapping on commodity graphics hardware. Current implementations of the DVR algorithm on such hardware allow users to classify sample points (known as "voxels") using 2-D transfer functions (func-tions based on sample intensity and sample intensity gradi-ent magnitude). However, such 2-D transfer functions in-herently ignore spatial information. We present a novel modification to 3-D texture-based volume rendering allow-ing users to classify fuzzy-segmented, overlapping regions with independent 2-D transfer functions. This modification improves direct volume rendering by allowing for more sophisticated classification using spatial information.

Background Parents juggling caregiving and paid employment encounter a range of barriers in providing healthy food to their families. Mobile apps have the potential to help parents in planning, purchasing, and preparing healthy family food. The utility and acceptability of apps for supporting parents are unknown. User perspectives of existing technology, such as commercially available apps, can guide the development of evidence-based apps in the future. Objective This study aims to determine the feasibility of existing commercially available apps for supporting the healthy food provision practices of working parents. Methods Working parents (N=133) were recruited via the web and completed a 10-item Capability, Opportunity, Motivation, and Behavior (COM-B) self-evaluation survey assessing their needs in relation to the provision of healthy family meals. A total of 5 apps were selected for testing, including a meal planning app, recipe app, recipe manager app, family organizer app, and barcode scanning app. Survey items were mapped to app features, with a subsample of parents (67/133, 50.4%) allocated 2 apps each to trial simultaneously over 4 weeks. A semistructured interview exploring app utility and acceptability and a web-based survey, including the System Usability Scale and the user version of the Mobile App Rating Scale, followed app testing. The interview data were analyzed using a theoretical thematic approach. Results Survey participants (N=133; mean age 34 years, SD 4 years) were mainly mothers (130/133, 97.7%) and partnered (122/133, 91.7%). Participants identified a need for healthy recipes (109/133, 82% agreed or strongly agreed) and time for food provision processes (107/133, 80.5%). Engagement quality was the lowest rated domain of the user version of the Mobile App Rating Scale across all 5 apps (mean score per app ranging from 3.0 to 3.7 out of a maximum of 5). The family organizer, requiring a high level of user input, was rated the lowest for usability (median 48, IQR 34-73). In the interviews, participants weighed the benefits of the apps (ie, time saving) against the effort involved in using them in determining their acceptability. Organization was a subtheme emerging from interviews, associated with the use of meal planners and shopping lists. Meal planners and shopping lists were used in time, while behavior was occurring. Conclusions Meal planning apps and features promoting organization present feasible, time-saving solutions to support healthy food provision practices. Attention must be paid to enhancing app automation and integration, as well as recipe and nutrition content, to ensure that apps do not add to the time burden of food provision and are supportive of healthy food provision behavior in time.