“Machine learning applications for Radiomics: Towards robust non-invasive predictors in clinical oncology”

Key words: oncology, precision medicine, medical imaging, radiomic analyses, artificial intelligence, machine learning methods 

In this big-data era, like every other field, healthcare is also turning towards artificial intelligence (AI) and machine-learning (ML). In this thesis, state-of-the-art machine-learning methods were investigated for radiomic analyses. An unbiased evaluation of these advanced computational methods in terms of their accuracy and reliability is presented. Identification of optimal machine-learning methods for radiomic applications is a crucial step towards stable and clinically relevant radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor-phenotypic characteristics in clinical practice. With ever increasing patient specific data, this work could stimulate further research towards brining AI and precision medicine in routine clinical oncology.

The work presented in this thesis is made pssible by the financial support of: CTMM framework (AIRFORCE project, grant 030-103), euroCAT (IVA Interreg - www.eurocat.info), the Dutch Cancer Society (KWF UM 2011-5020, KWF UM 2009-4454) and the National Institute of Health (NIH-USA U24CA194354, and NIH-USA U01CA190234).