Healthcare challenges are spread across many different areas such as precision medicine, big data and data management, wellness and prevention, or the social and ethical implications of advances in healthcare. Mathematics tools are often required do deal with these problems and are essential to derive effective solutions.
Ana Paula Rocha / FCUP, Portugal
André Dias Pereira / UC, Portugal
Bart Romeny / Eindhoven University of Technology, Netherlands
Inês Sousa / UM, Portugal
Isabel Figueiredo / UC, Portugal
João Malva / UC, Portugal
Ribeiro Ribeiro / ESTeSL – IPL, Portugal
Rui Rodrigues / FCT Nova Lisbon, Portugal
Wil Schilders / President of EU-MATHS-IN.
The inaugural lecture by the IEEE EMBS Distinguished Lecturer, Prof. Bart ter Haar Romeny, set the pace of discussion presenting recent advances on medical imaging and deep learning. The contribution of engineering to tackle complex problems using novel approaches and the vital support of mathematics was made evident by the lecturer and led to a discussion that will last over the end of the meeting. The role of engineering in this process was made clear and opened the door for collaborations between the different groups attending the conference. It was also inspirational to all, but with a particular focus on young researchers and students. Discussions continued over the coffee breaks and lunchtime where about 100 people gather together in fruitful conversations around the conference theme.
Some photos of our participation:
Date and Time
- Date: 07 Jun 2019
- Time: 08:00 AM to 08:00 PM
- All times are (UTC+00:00) Edinburgh
- Add Event to Calendar
- Praça Dom Dinis
- Coimbra, Centro
- Portugal 3001-501
- Building: Department of Mathematics
- Room Number: Sala Pedro Nunes
On the neuro-mathematics of deep learning
The success of deep learning neural networks is evident, leading to a revolution in the field. The breakthrough is enabled by the discovery of how to train a multi-layered neural net with backpropagation, by the advent of cheap GPU processing power and the availability of huge amounts of curated training data.
The first part of the lecture will focus on examples of important convolutional neural networks today. Then, we zoom in on 'brain-inspired computing', with an important biomedical application: the large-scale screening for diabetes by automatic analysis of retinal fundus images. With the progression of diabetes, blood vessels begin to leak, and this can be detected at high resolution and at low cost in the retina. Especially in Asia diabetes is exploding, with China now close to 12%. It is a major source of blindness. The Sino-Dutch RetinaCheck project aims to screen millions of people in the province Liaoning, China. I will carefully explain the brain-inspired image analysis tools we successfully developed for automated and quantitative biomarker analysis.
The second part will focus on the intrinsic mathematics of deep learning. How does the incremental contextual processing actually work? We can learn a lot from modern brain research, where optical and physiological recording techniques shed new light on what the functional circuits in the brain may be computing. Bridging the fields of computational models in deep learning artificial intelligence, and biological models of brain research is highly rewarding. The biomedical engineer, speaking both languages, is just the right professional to benefit from and contribute to these developments.
The lecture will be highly visual and is aimed to a broad audience. The speaker is known for his excellent educational skills.