DATE

9-12 DECEMBER 2020

COVID-19 may still have some impact on the organization of our course in December.
In any case, we have a scenario to continue with a live course for a max of 100 participants,
with respectful application of the social distancing and hygiene measures.
The organizers and venue are adhering to RIVM (Dutch Health Authority) guidelines
and we ask our participants to follow them as well.

ABOUT US

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. Whether you are a researcher in the field or are interested about fostering this type of research in your clinic, during this 4-days immersive course you will be able to attend lectures and workshops from world-class experts in Radiomics, Deep Learning and Synthetic Data.  Clinicians will receive basic training in the methods of Quantitative Image Analysis and will be able to interactively design a clinical trial.  Researchers will receive in-depth lectures about the state of the art and deeper training in commonly used algorithms.  Researchers can also bring your own curated dataset 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.

Quantitative Image Analysis looks at the phenotypic expression of genes, which results in particular imaging features or signatures able to characterize the imaged tissue and the underlying biology.  By converting standard medical images into mineable data, the processes and methods of data science can be applied to them. Imaging features are distilled through machine learning into ‘signatures’ that function as quantitative imaging biomarkers. A major challenge for the community is the availability of data in compliance with existing and future privacy laws. Synthetic data and virtual clinical trial offer a solution to this issue and will also form a part of the methods explored in this course.

COURSE IN THE CONTEXT OF

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

COURSE CONTENT

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 point is 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 tract will 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 tract will 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.

YOUR DATASET / HACKATHON

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.

TARGET AUDIENCE

  • 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

LEARNING OBJECTIVES

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

  • Understand the fundamentals of big data analysis
  • Understand the advantages and pitfalls of synthetic data generation
  • Critically evaluate the literature and review published articles
  • Understand how to implement a simple AI algorithm in order to answer a clinical question to augment a human decision
  • Gain the tools to plan and evaluate an imaging-based clinical trial
  • Gain basic understanding of regulation and privacy laws.
  • Gain basic understanding of increasing the interpretability of AI models
READ MORE

ORGANISERS

philippe.lambin@maastrichtuniversity.nl

Philippe Lambin - Course director, Maastricht University

h.woodruff@maastrichtuniversity.nl

Henry C. Woodruff , Maastricht University
c.oberije@maastrichtuniversity.nl
Cary Oberije, Maastricht University

FACULTY 2020

  • Philippe Lambin, Maastricht University, The Netherlands (Course Director)
  • Henry Woodruff, Maastricht University, The Netherlands (Course Co-director)
  • Cary Oberije, Maastricht University, The Netherlands (Organiser)
  • Andrey Fedorov, Harvard Medical School, USA
  • Mark Gooding, Mirada Medical, USA
  • Andrew Maidment, University of Pennsylvania School of Medicine, USA
  • Fanny Orlhac, Laboratoire d’Imagerie Translationnelle en Oncologie (LITO), France
  • Max Seidensticker, Klinikum der Universität München, Germany
  • David Townend, Maastricht University, The Netherlands
  • Bram van Ginneken, Radboud UMC, The Netherlands
  • Harini Veeraraghavan, Memorial Sloan Kettering Cancer Center, USA

The teaching faculty is being updated.

VIDEOS

Eurocat

Decision Support Systems: of The D-Lab

Radiomics

Distributed learning

SOCIAL PROGRAMME

All participants are invited to the course dinner on
Thursday evening.

This event is for delegates and faculty only. 

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

SPONSORSHIP

What are your benefits of sponsoring the course on AI4Imaging:

BRANDING

Invest in your brand equity by supporting our community

TALENT ATTRACTION

Connect with researchers, clinicians, engineers, analysts, data scientists at the forefront of AI, Imaging, deep learning, synthetic data and radiomics

THOUGHT LEADERSHIP

Demonstrate your company’s leadership and innovation chops in front of the brightest minds in the field

The two first editions (2018 and 2019) were a big success with the max amount of participants.
Come and tell our audience what your company has to offer them.
 

Consult our sponsorship prospectus or send your sponsorship request to Mieke at info@ai4imaging.org