Ghassan Hamarneh

Computing Science


Medical imagingComputer visionMachine learningRadiomicsImaging genetics

The overarching objective of my research is to enable computers to extract clinically useful information from medical images to improve our understanding, prevention, diagnosis, and treatment of diseases.

I work on developing computational techniques for solving real-world clinical problems through the automated processing and analysis of multi-dimensional biomedical structural and functional images. Medical images include magnetic resonance imaging (MRI, f-MRI, d-MRI) and computed tomography (X ray-CT, PET, SPECT), microscopy, and ultrasound.

I am interested in the application of machine learning, optimization, and graph theory to medical imaging and clinical applications.

My research focuses on developing techniques for: segmentation and registration, tracking and matching, shape representation and deformation analysis of anatomical structures and functional regions in medical images. I also work on building statistical, physical, and geometrical models of shape variation and on their application to automated detection of structural abnormality and pathology. I am also researching the development of controlled shape deformation techniques, and the incorporation of context-based, artificially intelligent mechanisms for image registration and segmentation using artificial life models.