Abstract
Early diagnosis of Parkinson's disease (PD) is of immense importance, since clinical symptoms do not occur until substantial parts of the brain stem have been irreparably damaged. Recent work suggests that by means of transcranial sonography (TCS) it is possible to determine the formation of monogenic forms of parkinsonism at a very early state. In TCS images, the mesencephalon shows a distinct hyperechogenic pattern in about 90% of patients with PD, despite its normal appearance on CT and MRI scans. At present, this pattern is manually segmented and the region size is used as an early PD indicator. In order to remove investigator dependence inherent to manual segmentation, we develop and validate semi-automatic features to serve as risk factors for PD manifestation. We show in a clinical study that some of the features correlate significantly with the presence of specific genetic mutations causing PD.
Originalsprache | Englisch |
---|---|
Titel | 4th European Conference of the International Federation for Medical and Biological Engineering |
Redakteure/-innen | Jos Vander Sloten, Pascal Verdonck, Marc Nyssen, Jens Haueisen |
Seitenumfang | 4 |
Band | 22 |
Erscheinungsort | Berlin, Heidelberg |
Herausgeber (Verlag) | Springer Berlin Heidelberg |
Erscheinungsdatum | 01.11.2009 |
Seiten | 456-459 |
ISBN (Print) | 978-3-540-89207-6 |
ISBN (elektronisch) | 978-3-540-89208-3 |
DOIs | |
Publikationsstatus | Veröffentlicht - 01.11.2009 |
Veranstaltung | 4th European Conference of the International Federation for Medical and Biological Engineering - Antwerp, Belgien Dauer: 23.11.2008 → 27.11.2008 Konferenznummer: 81647 |