På svenska

Presentation Information     2010-09-13 (15:15)   •  The seminar room at Vi2

Speaker Jimmy Azar
Title Automated Tracking of the Carotid Artery in Ultrasound Image Sequences Using an Incremental Self-Organizing Neural Network
Abstract This thesis proposes an automated method for the segmentation and tracking of moving vessel walls in 2D ultrasound image sequences. Tracking was achieved via a self-organizing incremental neural network. The topology-preserving algorithm assigns a net of nodes connected by edges that distributes itself within the vessel walls and adapts to changes in topology with time. Thereafter the movement of any set of nodes may be analyzed to uncover the dynamics of the vessel wall. By this way, radial and longitudinal strain and strain rates have been estimated. Wave intensity signals were also computed from these measurements, and another approach for visualizing the progression of the wave temporally and spatially along the vessel wall is presented. The method proposed in this thesis improves upon wave intensity wall analysis and opens up a possibility for easy and efficient diagnosis of vascular disease through noninvasive ultrasound examination.