We have developed a computer aided system for detection and quantification of intracranial aneurysms, which enables interactive visualization of three-dimensional (3D) images and 3D surfaces of anatomical structures, focusing mainly on vascular structures. The system enables interactive visualization of 3D raster images using an arbitrary ray-casting function and enables superposition of 3D raster images using arbitrary color coding. In this way, the visualized pre-operative 3D image can be visualized together with a backprojected information extracted from live 2D image. The visualization is designed to run on a local desktop machine or remotely in a web browser based on WebGL standard. The web-based design offers the advantage to test and validate the latest technologies for 3D and 2D image visualization and analysis on a remote basis. Currently, the system is being intensively tested with our clinical partners from Neurology department in Ljubljana and UCLA, USA.
F.21 Development of new health/diagnostic methods/procedures
Intracranial aneurysms are often asymptomatic and thus discovered incidentally. Due to high prevalence of intracranial aneurysms in general population (3-5%) the cost-benefit ratio of their surgical treatment is critical. Follow-up imaging is a new approach to stratify low- and high-rupture risk aneurysms and to determine the optimal treatment type and time. The aim of this thesis was to develop and validate computational methods and tools for two related clinical needs: (1) automated detection of intracranial aneurysms in angiographic images and (2) assessment of aneurysm morphology changes based on follow-up imaging with the goal to identify growing aneurysms. The candidate successfully defended his master thesis and employed at the UL FE, where he is a PhD student under the supervision of assoc. prof. dr. Žiga Špiclin.
F.03 Increased qualifications of the research and development staff
COBISS.SI-ID: 12591956Advanced guidance and verification in endovascular interventions and minimally invasive surgery are made possible with the use of spatial registration of 3D pre- and 2D intra-intervential images. In this chapter, we start with a mathematical definition and classification of 3D-2D registration methods and then review the state-of-the-art with respect to registrations basis and transformation estimation approach. We also review validation procedures, involving gold standard creation, registration error definition and standardized performance evaluation protocols, and showcase its use and elaborate on future challenges in the context of 3D-2D registration of cerebral angiograms.
F.02 Acquisition of new scientific knowledge
COBISS.SI-ID: 12739412This thesis concentrates on the development and validation of methods for computer-aided detection and quantification of intracranial saccular aneurysms in 3D angiographic images that are designed to assist a clinician towards a quicker and more reliable diagnosis and treatment of aneurysms. The main emphasis of the presented detection methods is the provision of high sensitivity and low specificity which is essential if to be used in clinical routine where an incorrect decision can adversely impact a patient’s life, whereas the design of the proposed quantification method aimed at producing accurate and robust morphologic measures that are unaffected by aneurysms’ size and shape variations, and thus, providing a reliable mean for monitoring the state of the aneurysms through time.
F.02 Acquisition of new scientific knowledge
COBISS.SI-ID: 11760468