Prof. Milan Sonka, Iowa Institute for Biomedical Imaging, The University of Iowa, USA
Image segmentation is one of the most important steps leading to the analysis of image data - its main goal being division of an image into parts that have a strong correlation with objects or areas of the real world contained in the image. In biomedical image analysis, image segmentation is frequently a pre-requisite to morphologic and/or functional quantitative analyses. After introducing basic image segmentation concepts in 2-D image data, the tutorial will focus on inherently 3-D and 4-D approaches to segmenting volumetric image data routinely produced by CT, MR, OCT, SPECT, PET, and other medical imaging modalities. In addition to image segmentation methods and approaches, the tutorial will briefly discuss the need for and approaches to quantitative validation of image segmentation results.
Part 1: Image Segmentation Basics
Part 2: Advanced Image Segmentation Methods
The research interests of Milan Sonka (Ph.D. 1983, Professor of Electrical & Computer Engineering, Ophthalmology & Visual Sciences, and Radiation Oncology at the University of Iowa, co-director of Iowa Institute for Biomedical Imaging, IEEE Fellow, AIMBE Fellow) include medical imaging and knowledge-based image analysis. He is first author of a book Image Processing, Analysis and Machine Vision published in 1993, 2nd edition 1998 by PWS, 3rd edition Thomson Engineering in 2007. He has co-authored or co-edited 10 other books and over 250 other publications. He is Associate Editor of IEEE Transactions on Medical Imaging, member of the Editorial Board of the International Journal of Cardiovascular Imaging, and Medical Image Analysis.