Processing, visualization, and repurposing Space

It is a track on graphics models, performance processing, real time and interactive visualization on the medical related data. One special subject is the development of teaching materials and learning objects by repurposing graphical and visual information.

Saturday, 7 April, 2012 - 08:00 to 09:30
Conference room: 
Track Organiser/Chair: 

Creating Medical eLearning Resources through Repurposing Procedures, Social and Semantic Web Functionalities

Abstract: 
Abstract: The creation of new, high quality eLearning resources is most of the time a very complex process that requires elaborate planning, long implementation time and the involvement of both medical and IT specialists. Addressing these issues, research and educational communities in medicine have studied different approaches for maximizing the quality of the resources while maintaining the costs at a low level. Most promising solutions used at present involve materials sharing between different content providers (either automatically or based on human content editors) and the creation of new resources based on already existing ones, in an approach named repurposing. One of the key steps in this approach is the identification of relevant and high quality resources. As this is not a trivial task, we present a method of describing, evaluating and recommending the best materials through social interactions and Semantic Web functionalities. In our solution each resource is described through a social profile encoded in RDF format that is later enriched with semantic connections based on different medical ontologies (Mesh, Snomed, etc.). For describing the resources, both on social and semantic level, we are using mEducator 3.0 which uses the mEducator schema for data modelling and repurposing history description. Another major issue in developing medical eLearning resources is generated by the fact that most of the medical specialists that are creating teaching materials do not have a thorough technical background, so they require the assistance of an IT specialist. As an alternative, we are presenting MEDIS, a meta-design oriented application that provides specialized tools for data retrieval, visual presentation management, user interaction settings and resources repurposing. Through simple, dedicated interfaces, medical specialists can integrate in the same resource images, videos, texts or 3D resources, from remote locations over the Internet, without having specialized technical knowledge.
Share/Save

Graphical Simulation and Visualization of Human Organs

Abstract: 
A physically based modeling of deformable objects is used in various applications (from games to medical simulations) to increase the realism and to allow relevant interactions. The medical training education could benefit from this approach to model human organs as deformable objects that could be used in a computer based surgical simulation. These simulations must include interactions of different surgical tools with multiple deformable objects, allowing the surgeons to learn and practice in a realistic environment. To achieve a certain degree of realism, the simulation environment need to support complex 3D models of human organs, complex geometry and material properties of objects, real time interactions, etc. In this paper, we discuss and analyze different approaches to simulate and interact with complex 3D models of human organs, modeled as deformable objects in an efficient and realistic manner and using NVIDIA PhysX technology for real time simulations. An important component is the collision detection, not only for realism but also because the simulation involves different medical instruments, modeled in this case as rigid objects. We also present two case studies for modeling and interacting with two human organs, stomach and lungs.
Share/Save

Distributed processing and analysis of medical images based on Grid infrastructure

Abstract: 
The need of requiring and analyzing large volume of medical data is one of the main issues concerning the modern society. The information of these medical images is available in different formats and stored in multiple remote locations. The Computer Aided Detection (CADe) algorithms, based on features extraction and pattern classification, could be used in order to improve the diagnosis of the most frequently known diseases. In order to achieve this purpose, the algorithms should rapidly analyze all the input dataset and generate the correct output in a reasonable amount of time. The Grid infrastructure is the most suitable solution for these kinds of problems, by offering large data repositories, high power computation mechanisms and the possibility to perform parallel and distributed data processing at the same time. In order to simplify the user actions, the paper proposes a new Web application that encapsulates all these features: algorithms parallelization, storage and computing support, data management, online results visualization and analysis, etc. The solution is based on representing all these algorithms as acyclic graphs, called PDG (Process Description Graph) and iPDG (instantiated PDG), used in the Grid execution processes. The gProcess platform is the middleware that assures the communication between the Web application and the Grid infrastructure.
Share/Save

Distributed Computer Aided Detection Algorithms

Abstract: 
Today medical computing requirements are growing due to the need to make Computer Aided Detection (CADe) available for all patients. Development of CADe software is an ongoing issue, mostly due to the high computational and storage costs of detection algorithms. The objective of this paper is to identify, study, and test the feasibility of distributed algorithms for computer aided detection, which are able to scale to increasingly larger inputs and larger datasets corresponding to more intense processing. There are two parallel approaches to the problem, the first one tries to respond to the need for greater access to this type of software and diagnostic methods, by creating the premise for massive parallel execution of these algorithms. The second method hinges on the idea of parallelizing the algorithms for detection, making them execute faster and do more intensive processing thus raising the quality of the response. The solution of the proposed subject is based on gProcess, an interactive toolset supporting the flexible description, instantiation, scheduling and execution by Grid processing. Within the framework description of a processing, the workflow is done via Process Description Graphs, which are directed graph of processing nodes.
Share/Save

Exploring a graphic cluster based solution for real-time virtual surgery

Abstract: 
Surgical simulators have been continuously gaining popularity in the medical world. As simulated morphologies become increasingly complex, there is a growing demand for simulators to do fast and precise calculations in order to allow the user to interact with the system in real-time. Due to performance reasons, many existent surgical simulators are based on simple, fast mass-spring deformable models. However, even physically based models such as these, display slow convergence behavior as model resolution and size increases. Parallelization can be used in order to improve the performance of surgical simulators and to allow improved realism of tissue deformation. This paper explores a graphic cluster based solution to accelerate calculations for mass-spring models. Acceleration is obtained by harnessing the parallel processing power of the GPU and by dividing computational effort among more computers, organized in cluster architecture. The solution uses the new OpenCL standard for General Purpose GPU programming, OpenMPI for distributed computing and VirtualGL for remote visualization and interaction.
Share/Save

Facilitating Healthcare Reform through Evidence-Based Research: The Role of Technology Acceptance among Healthcare Professionals and End-Users

Abstract: 
Background: Health informatics aim to facilitate and reform existing healthcare services, with multiple benefits for both healthcare professionals and patients or end-users. Nevertheless, not all professionals or patients are keen on new technology usage, and this may considerably limit the applicability and impact of contemporary health IT applications on the healthcare system. Tailor-made theoretical models derived from social psychological research can help researchers and policy-makers in healthcare to better understand and validly predict health professionals and end-users’ acceptance of health informatics applications. Objective: The present paper aims to provide a detailed account of state-of-the-art approaches in technology acceptance in healthcare settings, and present specific recommendations for interventions to increase technology acceptance and utilization. Method: A systematic literature review was conducted retrieving published studies on technology acceptance models in healthcare settings. Results/Conclusions: Acceptance and utilization of health informatics applications is determined by a range of psychosocial factors well described in studies of technology acceptance. Such empirical findings should be incorporated in interventions aiming to promote health informatics utilization in both health professionals and other potential end-users.
Share/Save
Parallel
Share/Save