DWI/FLAIR Mismatch An Automated, Continuous & Clinically Viable Approach
PhD defence by Jacob Johansen
Assessment Committee
Professor Stefan Sommer, Computer Science, University of Copenhagen (Chairperson)
Associate Professor Dimitrios Papadopoulos, DTU Compute
Associate Professor Daniele Ravi, University of Messina
Supervisors
Professor Sune Darkner
Associate Professor Melanie Ganz-Benjaminsen
CTO Akshay Pai
Department
Department of Computer Science
Place
Building: Pioneer Center for AI (P1), Room: Seminar Room, Øster Voldgade 3, 1350 København
Email address to gain access to the thesis: jj@di.ku.dk.
You will either receive a copy of the thesis or be informed where you can read a physical copy.
Recipients of copies of the thesis are not allowed to share or distribute it due to copyright compliance.
Short description of the thesis
This thesis explores an automatic, applicable and non-binary solution for determining DWI/FLAIR mismatch, used in treatment selection of unknown onset ischemic stroke patients.
We present a simple method that can be validated in real time by physicians and show that it is comparable to other current methods which rely on complex black box methods.
Lastly, we explore the impact of a non-binary selection criteria and what it might mean for treatment selection going forward