The transport systems in your body form geometrical networks, which transport, for instance, blood, air or nerve impulses. The functional capacity of such a network is often closely connected with the functional capacity of the organ it is part of: If the airways in your lung do not transport air, then your lung cannot breathe; if the connective network in your brain is damaged, you lose cognitive function. We can study anatomical networks through medical images, where information about blood vessels, airways or brain connectivity is extracted from scans. In this project, I will study how these networks differ in order to classify medical images of lungs and brains with respect to various illnesses, such as smoker's lung (Chronic Obstructive Pulmonary Disease), stress and multiple sclerosis.
The purpose of this project is to develop graph kernels that can
incorporate a wide range of geometric models for biological graph structures;
cope with the structural and geometric noise often created by graph extraction techniques;
be computed fast enough to run on large bioimaging databases of airways or brain connectivity, supplied by medical partners.