In deze aflevering van de Snoek op Zolder podcast vertelt Marcel van Gerven van de Radboud Universiteit en het het Donders AI for Neurotech Lab, over machine learning methods for brain reading and brain writing technologies, AI over vijf en vijftien jaar, “krijgen we straks robots met neurale implantaten en AI technologie?”, “AI, HBO-studenten en het mkb” en “wie was Frans Donders?”
Over Snoek op Zolder
Snoek op Zolder is de tweewekelijkse wetenschapspodcast van ICAI en de Nederlandse AI Coalitie (NL AIC). Hennie Huijgens duikt met een onderzoeker van een publieke of private organisatie in de wereld van kunstmatige intelligentie. Zijn belangrijkste vraag is ‘wat is de stand van zaken in AI onderzoek, en wat betekent dat voor mij en voor de samenleving?’
The e/MTIC AI-Lab focuses on improving personalized treatment in healthcare. In this article the lab provides an update of their latest state-of-the-art initiatives: the Health Data Portal and the ‘From Bench to Bedside’ project.
Future diagnostics, treatments and prevention in healthcare are supported by AI systems that are trained by large data sets. This requires a professional and structural approach for a data platform, not only from a functional ICT perspective but also from a non-functional perspective in data and cyber security, privacy, liability, robustness, ownership, access control and many other aspects.
e/MTIC AI works with a unique mixture of industry, clinical partners and researchers to increase the value of AI for clinical practice and improve personalized treatment. The research and innovation, conducted by the five e/MTIC partners, are increasingly ‘data driven’. Breakthrough innovations are based on insights obtained from combining and analyzing data sets from various domains and sources.
e/MTIC Health Data Portal
To safely share the medical data from these multiple institutions, e/MTIC established a scalable collaboration platform called the Health Data Portal (HDP). The e/MTIC HDP is the first health data platform in the Netherlands that will be able to bring together data from different disciplines and institutes to speed up health innovations by facilitating large amounts of data from complementary sources to be stored, shared and researched in a secure, reliable and privacy-respecting way.
This year the e/MTIC HDP has progressed sufficiently to take the next step in the direction of integration in national health infrastructures. With this, it will play an important role in the national network of the Health-RI project, financed by the National Growth Fund.
In practice, with the e/MTIC Health Data portal, PhD students can spend more time on research instead of arranging and collecting data and sorting out all kinds of legal aspects.
From Bench to Bedside
With such solid data infrastructure in place, e/MTIC – Fast track to clinical innovation – takes shape in many projects, amongst which ‘From Bench to Bedside‘. This project focuses on accelerating digital innovation by co-creating in 6 months innovation cycles with a multidisciplinary team (Catharina Hospital, Philips Research and the TU/e).
Newly developed solutions need to have a practical application in healthcare and preferably implemented quickly and as impactfully as possible. However, every innovation has a long journey, from the first idea to a product or a solution. This innovation circle can be reduced considerably by using existing and new data combined with AI. The Bench to Bedside methodology covers 4 phases: identifying clinical requirements, identifying technical requirements, followed by building and testing a proof of concept. These 4 phases come in form of innovation cycles of only six months.
e/MTIC is a large-scale research collaboration between the Catharina Hospital, Maxima Medical Center, Kempenhaeghe Epilepsy and Sleep Center, Eindhoven University of Technology and Philips Eindhoven.
November 9, 2021ICAI InterviewComments Off on ICAI Interview with Marjan van den Akker: Using algorithms to future-proof the Dutch public transport system
The Utrecht AI & Mobility Lab addresses complicated planning puzzles in public transport. Marjan van den Akker: ‘We are in a quadrangle with learning from data, optimization algorithms, agent-based simulations and human-centered AI.’
Marjan van den Akker is Scientific Director of ICAI’s Utrecht AI & Mobility Lab and is Associate Professor at the Information and Computing Science department of Utrecht University.
There are quite a few problems with public transport in the Netherlands right now. Mainly, that it’s overloaded. What kinds of problems is the AI & Mobility Lab addressing?
Marjan van den Akker: ‘One of the things we are investing is the planning for the service locations of the Dutch railways. At these locations the trains are parked when they are not running. They are cleaned there and small maintenance check and operations are carried out. These locations are in big city areas, close to the railway stations. Because of the enormous passenger growth, they are really overloaded.
And with the Dutch bus company Qbuzz we look into issues related to the energy transition and electric vehicles. Currently an electric bus cannot drive all day without charging, so you have to incorporate this in the schedule. We have to answer questions like: Do we charge often, which is good for the batteries? Or do we charge less, which makes the scheduling less complicated?’
How can these problems be tackled with AI techniques?
‘What we see at the service locations of the NS is that the problems are so complex that we need a hybrid approach. We have to combine optimization algorithms and learning algorithms. Another challenge is that all these planning algorithms are incorporated in decision support systems. They are used by humans in two ways. One way is on a strategic and policy level where people use the algorithms to estimate capacities of the transport system. The other way is in the actual operations where human planners need to work together with the system. The system does all these complicated calculations and suggests solutions, but it may happen that the human operator has to alter the plan because of a sudden change.’
Is this approach unique in the Netherlands?
‘Yes, to have all these different approaches in one computer science department is rather unique. Most places in the Netherlands use Operation Research in a mathematical way. But we use a hybrid approach of computational AI and Operation Research algorithms.’
Can you already tell us something about the lab first results?
‘We are a long-term lab and it’s founded on the bases of research that has already been running for some years. Four years ago one of our PhD students, Roel van den Broek, started on an algorithm for the planning of the service locations of the NS. The NS is currently running a pilot with this algorithm and intends to take it into use. This algorithm plans everything on the service locations: where the arriving trains have to be parked, when they go into the maintenance facility and the cleaning platform and which train units have to be coupled or decoupled. And that all has to be arranged in this highly packed area.’
You have been a technology consultant at the National Aerospace Laboratory for five years. Does that experience help you in working with companies?
‘Yes, I think I have more insight in the application domain. The goals of companies are a bit different from the goals of the scientists. A company of course, is mostly interested in the results and not in the paper that we write.’
What are the ambitions of the lab?
‘We want to extend in the field of logistics. We have conversations with new companies that are involved with mobility as a service. For example a company that organizes the use of shared cars and bikes and also gives travel advice. We try to connect as much as possible with all kinds of organizations in the new changing mobility area.’
Utrecht University has founded the AI Labs, of which the Mobility & AI Lab is part, and is ambitious in the field of innovative AI techniques. Can you tell us something about these plans?
‘Labs are a good instrument to achieve research. The UU started out with the Police Lab a few years ago, and that was very successful. So we are founding AI labs now in all kinds of areas. Besides the mobility theme, we are working on setting up labs in the fields of sustainability, health, media and the humanities. In Utrecht we can provide multidisciplinary research, in a way that a university of technology couldn’t, because we have more possibilities to take a human-centered approach.’
On November 18, 2021, the Utrecht AI & Mobility Lab will talk about their current work during the lunch Meetup of ‘ICAI: The Labs’ on AI and Mobility in the Netherlands. Want to join? Sign up!
Snoek op Zolder is the biweekly science podcast of the Dutch AI Coalition (NL AIC) and ICAI. In this week’s episode #11, host of the podcast Hennie Huijgens talks to Jan-Jacob Sonke on the use of AI for radiotherapy in the Netherlands Cancer Institute, ‘sloppy cancer cells’, the role of doctors and patients in AI research, and more. The podcast is in Dutch.
Future Impact, a tech-job focused platform for young talent, and ICAI will collaborate in the Launch Pad programme. Launch Pad is initiated by ICAI to connect young AI talent to the Dutch ecosystem. Together with Future Impact and the Dutch AI Coalition, ICAI wants to further expand Launch Pad into a pro-active support programme for AI careers in the Netherlands.
ICAI believes that the Netherlands offers great opportunities in the field of AI, but that AI talent and the organizations that need this talent are not yet able to find each other. The aim of Launch Pad is to connect AI talent to the Dutch ecosystem by providing a matchmaking process between AI-PhD students and Dutch companies looking for AI talent. Future Impact will fulfill the role of matchmaker.
All partners in the Launch Pad collaboration have a specific expertise and role in the matchmaking process. ICAI will use its network of ICAI labs to connect with PhD students who are about to enter the labor market. Future Impact will focus on the recruitment and matching of young AI talent. And the Dutch AI Coalition (NLAIC) will provide a network of organizations who are involved with AI in the Netherlands.
Awareness of AI opportunities
The Launch Pad programme wants to create awareness amongst students of the possibilities in the Dutch ecosystem. At the moment, many trained PhD students go (back) abroad, without being aware of the possibilities and favorable living conditions in the Netherlands. ICAI wants more students to stay in the Netherlands after pursuing their PhD.
Future Impact as matchmaker
Future Impact will act as matchmaker and introduce AI talent to Dutch based partners. The platform has a broad network of relevant organizations looking for AI talent. In addition to the matchmaking role, Future Impact offers support throughout the whole matchmaking and application process. This includes coaching candidates in finding their areas of interest, helping them to prepare for job interviews and negotiating contracts.
One of the missions of ICAI is to create and nurture a national AI knowledge and talent ecosystem. ICAI Launch Pad is the next practical step in carrying out this mission.
On the 27th of October ICAI organizes the ICAI Day: A Deep Dive into AI. This hybrid event will take place on location in Den Bosch and online. The focus of this ICAI event will be on the technological side of AI. Registration for the event is now open for everybody who is interested. You can register here.
Together with the ELSA Labs community of NLAIC, we organize a lunch event as part of the ICAI day for all the labs. In small table settings we will deep dive into specific area’s and how to work on AI with trustworthiness integrated in the technology. Introductions will come from the Police Lab and ELSA Lab. You must be physically present to attend this part of the programme.
We have speakers from outside and inside the labs who will dive into the latest technologies of AI and show work on Geometric Deep Learning: from Euclid to drug design (Michael Bronstein, Imperial College & Twitter) and graph convolution networks (Xie Weiyi, Radboud MC/Thira Lab). Finally our experts in the labs, from academia and industry, will share insides on lessons learned from the collaborations in the ICAI labs.
Topics of the lunch table discussions: – Inclusive society with data engineering – Autonomous systems in mobility – Robotics & autonomous agents – Computer vision in healthcare – Using AI in education and governmental org. – Online personalization and impact
13:45 – 17:00 Part 2: ICAI plenary event 13:45 – 14:00 Welcome by chair Nathan de Groot and director of ICAI Maarten de Rijke 14:00 – 14:45 Keynote Michael Bronstein Geometric Deep Learning: from Euclid to drug design (Twitter, Imperial College)
14:45 – 15:00 Break
15:00 – 15:30 Lecture Xie Weiyi(Thira Lab) – Graph Attention Networks for airway labeling 15:30 – 15:35 Short videos of different ICAI labs 15:35 – 16:20 Discussion table ICAI labs –Lessons learned in collaboration: Elvan Kula (ING, AI for Fintech Lab), Georgios Tsatsaronis (Elsevier, Discovery Lab), Cees Snoek (UvA, QUVA, AIM & Atlas Lab) 16:20 – 16:30 Closing words
ICAI is very proud to be able to expand the network of ICAI with the LTP ROBUST program “Trustworthy AI systems for sustainable growth”, supported by NWO in the new Long Term Program with €25 million.
AI technology promises to help with many tough societal challenges. For the technology to be adopted and benefit everyone, it is essential that the AI systems that we develop are trustworthy. The ROBUST Long-Term Program addresses this challenge and gets the opportunity to build the program.
First and foremost, ROBUST focuses on attracting talent to work on the challenges of trustworthy AI. Talent is the core of any AI ecosystem. Second, it makes trustworthy AI research and innovation a shared responsibility between knowledge institutes, industry, governmental organizations, and other societal stakeholders. And third, it practices learning by doing in the Dutch context, through use-inspired research, connections with startups and SMEs, and an extensive knowledge sharing efforts.
17 new ICAI labs
The ROBUST program builds on ICAI, the Innovation Center for Artificial Intelligence. It intends to add 17 labs to ICAI’s current ecosystem of 30 labs, in areas as diverse as health, energy, logistics, and services. The labs that make up ROBUST are driven by economic opportunities and contributions to the UN’s sustainable development goals. They will develop AI-algorithms that advance the state of the art in accuracy, reliability, repeatability, resilience, and safety of AI algorithms – all essential hallmarks of trustworthy AI.
ROBUST is a collaboration of 21 knowledge institutes, 23 companies, and 10 societal organizations. ROBUST is supported by the Netherlands Organisation for Scientific Research (NWO) and the AiNed National Growth Fund Investment Program.
The project leader for the ROBUST program is prof. Maarten de Rijke of the University of Amsterdam and ICAI. The co-applicants are prof. Mark van den Brand (Technical University Eindhoven), prof. Arie van Deursen (Delft University of Technology), prof. Bram van Ginneken (RadboudUMC), dr. Eva van Rikxoort (Thirona), prof. Clarisa Sánchez Gutiérrez (University of Amsterdam), and prof. Nava Tintarev (Maastricht University).
Ben Luijten is halfway through his PhD research at e/MTIC AI-Lab and is already working with his team on a number of prototypes of Philips ultrasound devices incorporating their algorithms. Luijten: ‘We work really close to the clinicians right now to find out what the best image quality is for them.’
Ben Luijten is a PhD Candidate at the Biomedical Diagnostic Lab at Eindhoven University of Technology and is a member of ICAI’s e/MTIC AI-Lab.
e/MTIC AI-Lab is a collaboration between Eindhoven University of Technology, Catharina Hospital, Maxima Medical Center, Kempenhaeghe Epilepsy and Sleep Center and Philips.
What can artificial intelligence and deep learning techniques mean for ultrasound imaging?
‘At the core of our research, we are trying to maximize image quality of ultrasound images. Ultrasound imaging has been around for almost fifty years now. It’s a fantastic technique that makes it possible to convert sound reflections into images, and take a look inside the human body in real-time. Technicians however, have always struggled with image quality. MRI and CT scans have a very high image quality, but they don’t give real-time feedback, and are very expensive. We are now trying to improve ultrasound image quality with the use of AI.’
Why is real-time image processing so hard?
‘Our devices have to operate within a fraction of a second. Ultrasound imaging needs at least thirty frames a second, and sometimes even up to a thousand frames a second in the case of blood flow measurements for example. In order to process all this information in real-time, the reconstruction algorithms have to be very small and lightweight in order to run on medical devices.’
What is your approach to this problem?
‘We look at the algorithms early on in the signal chain, so before the image formation. That way we are close to the signal processing. The signal processing is everything that happens in between the measurement and the image formation; the sampling of the signal, putting it into a digital form, filtering it, etc. Since these techniques are already well understood, we try to implement intelligent solutions that stay close to these conventional steps. In doing so, we can improve the image quality in a robust way, with relatively compact neural networks, and a small margin of error.’
How far have you already come with improving the image quality?
‘Well, the first question here is: what actually is the best image quality? Sometimes, what we as technicians find really good images, with very high contrast and resolution for example, the doctors don’t like at all, because they don’t see the same things as they did before. So we work really close to the clinicians right now to find out what the best image quality is for them. At this point we already have some good working AI algorithms that we started to implement in prototype systems.’
How will the next generation of ultrasound devices look like?
‘We want to head into the direction of image processing with small, portable ultrasound devices. That way a doctor could go to a patient’s home to do some basic scanning with lightweight AI running on his or her smartphone. And more complex processing could be done in the cloud. This could be a solution to the triage problem we saw during Covid for example. We did a side project on automatic assessment of Covid-severity, based on ultrasound scans of the lungs. And it worked pretty good. Eventually, the development of these portable ultrasound devices could change the way we use diagnostic tools.’
The e/MTIC AI-Lab promises ‘to provide a fast track to high-tech health innovations’. What does this ‘fast track’ look like?
‘e/MTIC connects a lot of collaborations and people in one lab. e/MTIC Lab tries to create a knowledge hub to minimize the fraction between all the research teams, the industry partners and the hospitals. It really lowers the boundaries of getting in touch with each other. If I have a question on a certain image, they can connect me to a doctor who can help me with that specific image or question.’
What’s next for deep learning in ultrasound imaging?
‘We are going to a certain point where the difference between conventional signal processing and deep learning becomes smaller and smaller. But within medical imaging we’re not likely going towards AI that can do everything. Instead, the focus will be on assisting the doctor in his or her work. In our case, this means developing fast, light-weighted neural networks, that get the most information out of the ultrasound measurements as possible.’
On September 16, 2021, Ben Luijten will talk about ‘Deep learning for ultrasound signal processing’ during the Lunch at ICAI Meetup on Deep Learning in the Netherlands. Want to join? Sign up!
LUMO Labs announces a TTT.AI investment in Autoscriber, a Dutch health tech software startup developed in a clinical setting. Autoscriber is developing AI-supported voice recognition software to capture and summarize healthcare professional-patient consultations.TTT.AI is part of the ICAI Venture Program.
Autoscriber’s value proposition is at the intersection of three crucial healthcare trends:
affordable and accessible healthcare for all
growing importance of structured/discrete data capture to support data-driven healthcare initiatives
increasing desire for understanding and self-determination among patients
Health professionals access Autoscriber as a subscription based software-as-a-service (SaaS) solution to large hospitals and practices, smaller practices and General Practitioners. LUMO Labs’ pre-seed funding will allow Autoscriber to go live in multiple hospitals during the next 12 months.
The technology, which promises to streamline clinical interactions into a seamless experience for patients and caregivers, was developed in collaboration with the Clinical Artificial Intelligence and Research Lab (CAIRELab) at Leiden University Medical Center.
“We are very excited to work so closely with the LUMC. Every design choice we make we validate with the physician in a clinical setting.” said Koen Bonenkamp, co-founder and CTO.
Autoscriber software records, transcribes and extracts clinical concepts during consultations. It allows for automated summaries and integration in the patient’s Electronic Health Record that can be easily edited by the physician, providing real-time support for diagnostics and personalized care.
LUMO Labs is investing because Autoscriber meets and/or exceeds their investment fundamentals, including a strong entrepreneurial founding team with profound expertise, proof-of-concept and the promise to dramatically improve the lives of caregivers and patients.
“The problem Autoscriber is solving is universal: reducing time and money spent on repetitive, administrative tasks by physicians while increasing transparency, comprehensibility and human interaction in deeply personal treatment situations,” said LUMO Labs founding partner Andy Lürling. “Their solution is dynamic and highly scalable because of the strong technological and human-centered set-up.”
The TTT.AI consortium is looking for 4 Business Developers AI (Amsterdam, Utrecht, Nijmegen and Eindhoven) to help set up and supervise academic start-ups and spin-offs.
Together with the TTT.AI initiative, ICAI is working on a programme where employees of the universities can apply for support. This ICAI Venture programme has the aim to stimulate PhD students and staff of the knowledge institutes to look into the possibilities of starting a business with the solutions that are build.
Are you an experienced business developer in the field of software and digital innovations, and do you have an affinity with Artificial Intelligence (AI)? Does the sound of working in a dynamic working environment with top scientists, using your knowledge and experience to bring AI innovations to market appeal to you? Then take a look at the position of AI Business Developer for the new national TTT.AI programme. The application deadline is September 19.