Automated Machine Learning in Medical Image Segmentation
C.S.O. van Gruijthuijsen (TU Delft - Mechanical Engineering)
Wei Pan – Mentor (TU Delft - Robot Dynamics)
Martijn Starmans – Mentor (Erasmus MC)
Karin van Garderen – Mentor (Erasmus MC)
Stefan Klein – Graduation committee member (Erasmus MC)
Martijn Wisse – Coach (TU Delft - Robot Dynamics)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Semantic Segmentation of medical images are used to improve diagnosis and treatment. In recent years, the application of machine learning methods are increasingly used. However, the design of these models is difficult and time-consuming. In this thesis, we investigated the automation of this process using an Automated Machine Learning (AutoML) algorithm called Bayesian Optimization with HyperBand (BOHB). We found several hyperparameters significantly influencing the performance and confirmed that BOHB is applicable to these kind of problems. However, we did not find a significant difference between BOHB and Random Search on a small search, stressing the need of matching the search space to the search strategy. Finally, our approach was only slightly worse than the current state-of-the-art, which shows that AutoML has potential in this field.