Robust and accurate cerebral hemisphere segmentation in non-contrast CT using a 2.5D Dense U-Net

dc.contributor.advisorKachergis, G.E.
dc.contributor.authorKleef, van, J.A.
dc.description.abstractThis work is about automatically segmenting cerebral hemispheres using a convolutional neural network. The aim is to publish the work in NeuroImage: Clinical, since it is the rst work to automatically segment cerebral hemisphere in non-contrast CT scans. Some sections can lack background information, for the sake of conciseness of being it a paper for a targeted journal. The background information that is relevant can be found in the included appendices. Also more work that is done in the framework of the extended research project is included in the appendices For the last eight months I worked on this extended research project at the Radboud Hospital Nijmegen in the Digital Image Analysis group (DIAG). Besides the fact that I learned much in this period, be it academical, medical or technical, I had a very good time here. I would like to thank this group for the excellent guidance, especially Ajay and Rashindra, who supervised me through the entire process. I would also like to thank George for supervising on behalf of the university.en_US
dc.embargo.typePermanent embargoen_US
dc.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationMaster Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.titleRobust and accurate cerebral hemisphere segmentation in non-contrast CT using a 2.5D Dense U-Neten_US
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Kleef, J.-Extended-Research-2018.pdf
5.2 MB
Adobe Portable Document Format