Ghassan Hamarneh
Professor
Computer Science
Dr. Hamarneh is a tenured Professor of Computing Science at Simon Fraser University (SFU). He has over 15 years of experience in developing computer vision, machine learning, and image processing methods for biomedical imaging applications. Dr. Hamarneh has been a Senior Member of IEEE and a Senior member of ACM since 2010. He is a Founding Member of the IEEE Engineering in Medicine and Biology Chapter in Vancouver. He is also a Medical Image Computing and Computer Assisted Interventions (MICCAI) society member and a member of the Djavad Mowafaghian Centre for Brain Health (formerly: Brain Research Centre), Kids Brain Health Network (formerly: NeuroDevNet), SFU/UBC Graduate Program in Bioinformatics, BCNI Behavioral & Cognitive Neuroscience Institute, SFU Neuroscience, SFU Centre for Disability Independence Research and Education, and others. Throughout his career and education, Dr. Hamarneh was affiliated with the University of Toronto and the Hospital for Sick Children, Chalmers University of Technology, University of Jordan, Rostock University, INRIA and École Central Paris, France. He is an author on over 250 publications, and serves as a reviewer for the main journals (e.g. IEEE TMI, IEEE TPAMI, IEEE TIP, and J. MedIA) and program / review committee member for the main conferences in his area (e.g. MICCAI, IPMI, SPIE MI, IEEE ISBI, IEEE ICCV, IEEE CVPR). He organized several international workshops on mathematical methods for medical image analysis, geometry for anatomy, and functional medical image computing.
Current Research Focus
Dr. Hamarneh’s research focuses on developing intelligent computer vision and machine learning methods capable of automatically processing, quantifying and interpreting medical and biological imaging data. Primarily, his team develops new technologies that aim to mimic and surpass human vision, providing fast, reproducible, and accurate automatic solutions to basic medical research and clinical healthcare applications. Their artificial intelligence based computational methods target performance levels at par or better than those of highly-trained domain experts under stringent performance guidelines to overcome problems in areas such as computer aided diagnostics, robotic and minimally invasive intervention, precision medicine and big data analytics.
Example Project(s)
“Novel Deep Learning Models for Imaging and Image Interpretation of Cancer” High-dimensional medical image and clinical meta-data is creating an unprecedented opportunity to advance our understanding of disease. My group has taken a special interest in developing and validating deep learning based methods to tackle problems related to early diagnosis and monitoring of treatment efficacy of cancer.
“Advanced Radiomics for Quantitative Analyses of Biomedical Image Data” My group’s research involves designing algorithms to automatically and robustly extract various quantitative measures from imaging data, e.g. morphometrics and static structural properties (size, location, shape, and appearance of cells, tissues and organs, etc.) and dynamic functional characteristics (motion, deformation, radiotracer uptake, oxygenation changes, etc.). Such quantification very often requires solving semantic image segmentation and registration problems, an area in which we have made various contributions.
Research Keywords
Medical Image Analysis, Artificial Intelligence, Deep Learning, Computer Vision, Radiomics, Cancer
