||This talk focuses on the automatic quantitative performance analysis of bioprosthetic heart valves from video footage acquired during in vitro testing. Bioprosthetic heart valves, mimicking the shape and functionality of a human heart valve, are routinely used in valve replacement procedures to substitute defective native valves. Their reliability in both functionality and durability is crucial to the patients' well-being; as such, valve designs must be rigorously tested before deployment. A key quality metric of a heart valve design is the cyclical temporal evolution of the valve's area. This metric is typically computed manually from input video data, a time-consuming and error-prone task. We propose two novel, cost-effective approaches for the automatic tracking and segmentation of valve orifices. Experiments including comparisons with state-of-the-art methods demonstrate the value of the proposed approaches.
Dr. Alexandra Branzan Albu is an associate professor with the Department of Electrical and Computer Engineering at the University of Victoria (BC), Canada. She holds a PhD in Electrical Engineering from Politehnica University of Bucharest. Alexandra’s research focus is on computer vision. From a practical standpoint, her contributions to this field involve raising and solving research questions that are closely linked to societal needs such as medical imaging, environmental monitoring, and Big (Visual) Data. Due to the interdisciplinary and applied nature of the research problems under investigation, Alexandra has developed a number of industrial collaborations with local and international companies such as Vivitro Labs, Intel, SAP, Kongsberg-Mesotech, who have all provided funding for her research. Her research is also funded by the Natural Science and Engineering Research Council of Canada (NSERC). She serves on the executive committee of the International Association of Pattern Recognition (IAPR), and she is the Chair of the IEEE Victoria Section.