More about HKUST
Graph Algorithmic Techniques for Biomedical Image Segmentation: LOGISMOS
Speaker: Prof. Milan Sonka The Iowa Institute for Biomedical Imaging The University of Iowa Title: "Graph Algorithmic Techniques for Biomedical Image Segmentation: LOGISMOS" Date: Tuesday, 3 November 2015 Time: 4:30pm to 5:30pm Venue: Lecture Theater E, Chia-Wei Woo Academic Concourse, HKUST Abstract: Accurate and reliable image segmentation is of paramount importance in medical image analysis. With a widespread use of 3D/4D imaging modalities like MR, MDCT, ultrasound, or OCT in routine clinical practice, physicians are faced with ever-increasing amounts of image data to analyze and quantitative outcomes of such analyses are increasingly important. Yet, daily interpretation of clinical images is still typically performed visually and qualitatively, with quantitative analysis being an exception rather than the norm. Since performing organ/object segmentations in 3D or 4D is infeasible for a human observer in clinical setting due to the time constraints, quantitative and highly automated analysis methods must be developed. Situation is similar when analyzing research animal images or biological images of living cells from microscopic images. Utilizing contextual information of mutually related surfaces and objects is hypothesized to increase segmentation robustness. Our method for simultaneous segmentation of multiple interacting surfaces belonging to multiple interacting objects will be presented. The reported method is part of the family of graph-based image segmentation methods dubbed LOGISMOS for Layered Optimal Graph Image Segmentation of multiple Objects and Surfaces. This family of methods guarantees solution optimality with directly applicability to n-D problems. LOGISMOS is generally applicable to a multitude of image segmentation problems and its utility and performance will be demonstrated on cardiovascular MR, pulmonary CT, orthopaedic MR, and ophthalmic OCT images showing the broad applicability of the developed algorithmic concepts. ******************** Biography: Professor Milan Sonka is Lowell C. Battershell Chair in Biomedical Engineering, The University of Iowa, USA. He is currently the Associate Dean for Graduate Programs and Research, College of Engineering, The University of Iowa. He is the Professor of Electrical and Computer Engineering, Applied Mathematical and Computational Sciences, Ophthalmology and Visual Sciences, and Radiation Oncology. His research areas are Image Processing and Analysis, and Medical Image Analysis. http://www.engineering.uiowa.edu/ece/faculty-staff/milan-sonka [www.engineering.uiowa.edu]