| Online-Ressource |
Verfasst von: | Liao, Wei [VerfasserIn]  |
| Rohr, Karl [VerfasserIn]  |
| Kang, Chang-Ki [VerfasserIn]  |
| Cho, Zang-Hee [VerfasserIn]  |
| Wörz, Stefan [VerfasserIn]  |
Titel: | Automatic 3D segmentation and quantification of lenticulostriate arteries from high-resolution 7 Tesla MRA images |
Verf.angabe: | Wei Liao, Karl Rohr, Chang-Ki Kang, Zang-Hee Cho, and Stefan Wörz |
E-Jahr: | 2016 |
Jahr: | February 2016 |
Umfang: | 14 S. |
Fussnoten: | Gesehen am 04.06.2020 |
Titel Quelle: | Enthalten in: Institute of Electrical and Electronics EngineersIEEE transactions on image processing |
Ort Quelle: | New York, NY : IEEE, 1992 |
Jahr Quelle: | 2016 |
Band/Heft Quelle: | 25(2016), 1, Seite 400-413 |
ISSN Quelle: | 1941-0042 |
Abstract: | We propose a novel hybrid approach for automatic 3D segmentation and quantification of high-resolution 7 Tesla magnetic resonance angiography (MRA) images of the human cerebral vasculature. Our approach consists of two main steps. First, a 3D model-based approach is used to segment and quantify thick vessels and most parts of thin vessels. Second, remaining vessel gaps of the first step in low-contrast and noisy regions are completed using a 3D minimal path approach, which exploits directional information. We present two novel minimal path approaches. The first is an explicit approach based on energy minimization using probabilistic sampling, and the second is an implicit approach based on fast marching with anisotropic directional prior. We conducted an extensive evaluation with over 2300 3D synthetic images and 40 real 3D 7 Tesla MRA images. Quantitative and qualitative evaluation shows that our approach achieves superior results compared with a previous minimal path approach. Furthermore, our approach was successfully used in two clinical studies on stroke and vascular dementia. |
DOI: | doi:10.1109/TIP.2015.2499085 |
URL: | Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.
Volltext: https://doi.org/10.1109/TIP.2015.2499085 |
| DOI: https://doi.org/10.1109/TIP.2015.2499085 |
Datenträger: | Online-Ressource |
Sprache: | eng |
Sach-SW: | 3D minimal path approach |
| 3D model-based approach |
| 3D synthetic imaging |
| 3D vessel segmentation |
| 7T MRA data |
| automatic 3D segmentation |
| biomedical MRI |
| blood vessels |
| Cerebral Cortex |
| cerebral vasculature |
| Data models |
| Dementia, Vascular |
| directional speed function |
| energy minimization |
| fast marching |
| high-resolution 7 tesla magnetic resonance angiography imaging |
| high-resolution 7 tesla MRA imaging |
| human cerebral vasculature |
| Humans |
| image denoising |
| image resolution |
| image segmentation |
| Image segmentation |
| Imaging, Three-Dimensional |
| lenticulostriate arteries |
| low-contrast noisy regions |
| magnetic flux density 7 tesla |
| Magnetic Resonance Angiography |
| medical disorders |
| medical image processing |
| Middle Cerebral Artery |
| minimal path |
| minimal path approach |
| minimal path approaches |
| Noise measurement |
| parametric intensity model |
| Probabilistic logic |
| probabilistic sampling |
| probability |
| Shape |
| Solid modeling |
| Stroke |
| stroke dementia |
| thin vessels |
| Three-dimensional displays |
| vascular dementia |
| vessel gaps |
K10plus-PPN: | 1699780617 |
Verknüpfungen: | → Zeitschrift |
Automatic 3D segmentation and quantification of lenticulostriate arteries from high-resolution 7 Tesla MRA images / Liao, Wei [VerfasserIn]; February 2016 (Online-Ressource)