Defence of dissertation in the field of Computer and Information Science, Nicolau Gonçalves, M.Sc.
Advances in Analysis and Exploration in Medical Imaging
Map © OpenStreetMap. Some rights reserved.
M.Sc. Nicolau Gonçalves will defend the dissertation ”Advances in Analysis and Exploration in Medical Imaging” on 5 December 2014 at 12 noon in lecture hall TU1, Otaniementie 17, Espoo. The thesis proposes novel developments in machine learning approaches to the analysis of magnetic resonance images of the brain. Those methods are also successfully applied to the study of brain lesions, from both a functional and a structural change perspectives.
With an ever increasing life expectancy, diseases capable of disrupting normal cognitive processes have become a major problem. Their diagnoses are difficult, and occur usually after daily living activities have already been compromised. This leads to serious costs in health care, and a significant decrease in quality of life.
This dissertation proposes a set of machine learning methods, useful for the study of the neurological implications of brain lesions. Two main research directions are proposed. The first, a brain tissue segmentation approach, identifies brain tissues, and provides early lesion detection. The second, a document mining framework, is applied to neuroscientific publications. This framework allows for an intelligent harvesting and summarisation of research results dealing with neural activity. The aforementioned research directions are based on the retrieval of consistent information from neuroimaging data.
Opponent: Dr. Kristoffer H. Madsen, Danish Research Centre for Magnetic Resonance, Denmark
Custos: Professor Erkki Oja, Aalto University School of Science, Department of Information and Computer Science
Electronic dissertation: http://urn.fi/URN:ISBN:978-952-60-5948-8
School of Science, electronic dissertations: https://aaltodoc.aalto.fi/handle/123456789/52