PhD defence M.P.A. (Martijn) Starmans

Healthcare is shifting from a uniform approach to personalized medicine based on the unique characteristics of each patient. In this aspect, medical imaging such as CT and MRI are playing an increasing role. Extracting quantitative, objective measurements from these images and relating them to biological processes, clinical outcomes, or diseases, is however difficult. To address this, the field of radiomics extracts quantitative characteristics from medical images with computer algorithms and combines this with artificial intelligence to create predictive models. The goal of this thesis is to streamline radiomics research, facilitate its reproducibility, and simplify its application. To this end, we developed an adaptive radiomics framework, which automatically find the optimal combination of radiomics methods from a wide range of available methods to create a predictive model. We demonstrate the use of our framework in eight different, independent clinical applications, and have made both the software and several datasets publicly available. The resulting predictive models for the respective diseases have the potential to in the future improve the diagnostic trajectory and treatment planning of these patients.

The PhD defences will not take place publicly in the usual way. A live stream link has been provided to candidate. The ceremony will begin exactly at 13.00.