MSc project “Learning to learn: meta-learning for medical image segmentation”

Imagine you have experience with two medical imaging applications (for example, segmentation in brain MR images, and segmentation of cells in histopathology images) in medical imaging, and you know that different (deep) learning methods work best in each application. Can you decide which method to use on a third application, for example segmentation of vessels in retinal images, without trying all the possibilities first?

In machine learning this idea of predicting which methods will perform better on a given dataset is called “meta-learning”. This can be done by charactering each (dataset, method) pair with several “meta-features”, which describe the data (for example, the variance of each feature) and the method (for example, how many layers a neural network has). The label of this pair is the performance of the method on the dataset. This way, a meta-classifier can learn what type of data and classifiers perform well together.

An important open question is how to choose the meta-features for this problem. In this MSc project, you will investigate how to adapt meta-learning features from the literature to medical imaging problems, and engineer specialized features that might not be applicable to other types of data. You will work on a set of publicly available medical imaging datasets (e.g. Kaggle), and implement your methods in the OpenML platform (http://www.openml.org).

Some experience with machine learning is required, experience with Python is preferred but experience with another programming language and willingness to learn Python is also sufficient. Experience with medical imaging is preferred but not required.

This project will be jointly supervised by me and Dr. Joaquin Vanschoren (Data Mining, Department of Computer Science)