11-14 DECEMBER 2019


This course on Artificial Intelligence for Imaging is a unique opportunity to join a community of leading edge practitioners in the field of Quantitative Medical Imaging. During this 4-days immersive course, you will be able to attend lectures and workshops from world-class experts in Radiomics, Deep Learning, Synthetic Data, and Distributed Learning.  You can also bring your own curated dataset with you for the hackathon (labelled, sorted by outcome, open source or fully anonymised, and cleared by ethics).  If requested ahead of time, we will perform “data matching” for attendees to facilitate external cross validation. There will be ample opportunity to network with faculty members, other participants and companies.

Medical imaging has been the cornerstone for the management of patients for decades, particularly in oncology. Imaging data such as CT, MRI or PET are routinely acquired for every cancer patient in the process of diagnosis, treatment planning, image-guided interventions and response assessment. The use of image analysis in a quantitative way is now considered as one of the most promising techniques to support clinical decisions.

Genomics aims at identifying genes and gene mutation to characterize tumor or normal tissue. Radiomics looks at the phenotypic expression of genes, which results in particular imaging features or signatures able to characterize tumor and normal tissue.  Radiomics is the high throughput extraction of large amounts of quantitative image features such as tumor image intensity, (multi-scale) texture, shape and size extracted from standard medical images (e.g., CT, MR, PET) using automatic software. These features are distilled through machine learning into ‘signatures’ that function as quantitative imaging biomarkers. Recently the radiomics approach has been enriched by Deep Learning methods, and both fields are profiting from the advancement of data augmentation and harmonization methods. A major challenge for the community is the availability of data in compliance with existing and future privacy laws. Distributed learning offers a solution to this issue and will be demonstrated. Medical imaging combined with artificial intelligence will guide personalized cancer treatment in the future.


The Marie Curie Network PREDICT, the NWO projects DuCAT and STRATEGY, the Interreg project EURADIOMICS


The course will be divided into lectures during the morning and hands on assignments in the afternoon. Parts of the course will be split into clinical and technical tracts, depending on your level of expertise. Participants of the hackathon are encouraged to come with their data and we will organize (if possible) matching data for validation from other participants on the course.

Our starting pointis an overview of the history of Medical Imaging Artificial Intelligence we then discuss the success stories but also the pitfalls.  Next, we will review the process from data acquisition, access to the DICOM objects, feature extraction, machine learning (including new developments with Deep Learning) analysis and validation.

The clinical tractwill then learn more about the clinical implementation of quantitative imaging, from acquisition protocols to software solutions and finally the implementation of decision support systems.

The technical tractwill focus on advances in synthetic data generation and harmonization techniques, new Deep Learning architectures, and current workflow solutions.

In the final part of the course, we will discuss the current challenges and directions of research in the field; in particular, the necessity of dealing with large annotated data sets, the FAIR principles and the distributed learning approach.


Participants are encouraged to bring their datasets for analysis during the hackathon. The dataset has to be fully open source (e.g. from TCIA) or anonymised and cleared by ethics (a written prove of this will be required).  If requested in advance, the organisers will perform “data matching” for attendees to facilitate external cross validation. Please contact us to check the availability of this service.

If you want to share your data with Maastricht University during the course you can fill out and sign the DTA template provided here (dta dec18-BD4I Course TEMPLATE). You can also follow the course by storing the data you bring, on your own device, in this case a DTA is not necessary.


  • clinicians in medical imaging (e.g. radiologists, oncologists, neurologists, cardiologists, ophthalmologists, dermatologists, ENT surgeons)
  • medical physicists with an interest in research
  • medical imaging researchers
  • computer scientists with an interest in medical imaging
  • academics researching quantitative imaging


Regarding Radiomics, Deep Learning, Synthetic Data (TECHNICAL TRACT), and Distributed Learning, after this course you will be able to:

  • explain the fundamentals
  • critically evaluate the literature
  • draw up an implementation plan for the clinic (CLINICAL TRACT)
  • understand the pitfalls associated with quantitative imaging
  • provide advice in designing Quantitative Image Analysis Experiments
  • make data FAIR (Findable, Accessible, Interoperable, Reusable)
  • comply with regulation and privacy laws (DGPR)


Philippe Lambin - Course director, Maastricht University

Henry C. Woodruff , Maastricht University
Cary Oberije, Maastricht University


  • Philippe Lambin, Maastricht University, The Netherlands (Course Director)
  • Henry Woodruff, Maastricht University, The Netherlands (Organiser)
  • Samir Barakat, Maastricht University, The Netherlands
  • Joe Deasy, Memorial Sloan Kettering Cancer Center, USA
  • Michel Dumontier, Maastricht University, The Netherlands
  • Olivier Gevaert, Stanford University, USA
  • Robert J. Gillies, Moffitt Cancer Center, USA
  • Mathieu Hatt, LaTIM INSERM, France
  • Andrew Maidment, University of Pennsylvania School of Medicine, USA
  • Bjoern Menze, TU München, Germany
  • Olivier Morin, UCSF & Principal Investigator of the Morin QI Lab, California, USA
  • Martin Vallières, McGill University, Canada
  • Sean Walsh, Maastricht University, The Netherlands



Decision Support Systems: of The D-Lab


Distributed learning


All participants will be invited to the course dinner on
Thursday evening 12 December 2019.

This event is for delegates and faculty only. 

It is not possible to bring any accompanying persons.  Pre-registration will be compulsory.


All sponsors are welcome to join us for this new edition on AI4Imaging.

The 2018 edition was a big success.  You do not want to miss out on the 2019 edition.  The detailed sponsorship brochure, listing all opportunities, is available here: IndustryInvitation.

For questions or suggestions for new involvement, please contact Mieke at