**Data Aggregation and Curation**
Unlike many other projects in machine/deep learning, this project works exclusively with data from scans of humans (both controls and patients).
For this reason, we have to ensure that any data set we use has to be compatible with the laws and regulations of the respective country/organization or hospital.
All data should be anonymized.
Having said that we need to:
1. Work on the same data sets ideally with the same preprocessing steps. Eventually, we will also study the influence of preprocessing on the results.
2. The plan for now is to build a preprocessing pipeline (will be made available through the GitHub) that ideally would be run on our server (AMC, Amsterdam) and made available.