Publikationstyp: Konferenz: Poster
Art der Begutachtung: Peer review (Abstract)
Titel: On the utility of 3D Zernike Moment Invariants to assess aneurysm disease status
Autor/-in: Juchler, Norman
Ebnöther, Ueli
Schilling, Sabine
Hirsch, Sven
Kurtcuoglu, Vartan
Angaben zur Konferenz: All Day, Bern, 15 September 2015
Erscheinungsdatum: 15-Sep-2015
Sprache: Englisch
Schlagwörter: Shape-based risk assessment; Zernike Moment Invariants; Intracranial aneurysms
Fachgebiet (DDC): 616: Innere Medizin und Krankheiten
Zusammenfassung: Intracranial aneurysms are pathological deformations of brain arteries. Although remaining asymptomatic most of the time, aneurysms expose the patient to an increased risk of subarachnoid hemorrhage, which can cause severe brain damage and death. To this date, it is difficult for clinicians to judge the aneurysm risk status reliably, even though availability and quality of imaging modalities have much improved recently. The goal of this project is to investigate whether a quantitative description of 3D-shape can be used to judge the disease status of intracranial aneurysms, and, ultimately, to equip clinicians with a tool to assess the risks of treatment. In recent scientific literature, various candidates of 3D-shape descriptors are discussed, out of which Zernike Moment Invariants (ZMIs) belong to the most popular ones. In an attempt to understand their mode of operation, we applied them to classify the rupture-risk status of intracranial aneurysms. Based on the analysis of synthetic and real data we accumulated evidence and are presenting first results on the utility of ZMI and alternative representations.
Volltext Version: Entwurf
Lizenz (gemäss Verlagsvertrag): Keine Angabe
Departement: Life Sciences und Facility Management
Organisationseinheit: Institut für Computational Life Sciences (ICLS)
Publiziert im Rahmen des ZHAW-Projekts: AneuX
Enthalten in den Sammlungen:Publikationen Life Sciences und Facility Management

Dateien zu dieser Ressource:
Es gibt keine Dateien zu dieser Ressource.
Zur Langanzeige

Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.