ICAI Interview with Ben Luijten: improving ultrasound images with the help of deep learning

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

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 makes first TTT.AI pre-seed investment in LUMC innovation partner Autoscriber

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.”

Vacancies for 4 Business Developers AI

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.

Read more about the ICAI Venture programme.

Read more about the vacancies and apply.

Save The Date – ICAI Day Autumn Edition – 27 October

During the second edition of the ICAI Day we will take a closer look at the way ICAI brings together knowledge institutes, industry, and government to catalyze knowledge creation in AI.

We will address questions such as: What does it look like for industry to work closely together with academia? How can you bring academic work into practice?

Experts and talent from academia, industry and government will share lessons learned on this topic. We will also hear from speakers who invest in public-private collaboration by working simultaneously on the academic and on the industry side.

27 October 2021
12:00 – 17:00 hrs
Den Bosch*

More information about the program and how to subscribe will be shared soon!

*This ICAI Day will have a hybrid format. Participation will be possible both in-person and online.

ICAI is looking for a project manager

Do you have a creative mind in setting up new projects? And do you like to work independently with multiple stakeholders? Send your application before 31 August!

The project manager will be working on a big ICAI Consortium Proposal. This consortium is an initiative of the Innovation Center for Articifial Intelligence (ICAI) and will be funded by NWO and industry. The project manager will be working closely with the researchers, business developers, industry partners and internal Faculty departments to build the full proposal.

The consortium is building around ICAI and in the ICAI way of working with ICAI labs, where researchers and industry partners work very closely on topics that are of high importance for the industry partner(s). This specific consortium and proposal is a proposal for a 10 year project in close relation to the industry in the Netherlands.

Find ouit more about the vacancy and apply here.

Netherlands Cancer Institute, Elekta and UvA launch POP-AART Lab

The Partnership for Online Personalized AI-driven Adaptive Radiation Therapy (POP-AART) is the 28th lab to join ICAI. The lab will focus on the use of artificial intelligence for precision radiotherapy.

It is a major challenge to give patients the right dose of radiation, at the right spot with least damage to healthy tissue, and while the patient and the tumor move and change shape during radiation and over time. Within the POP-AART lab six PhD researchers will develop novel AI strategies for improving the images on which the radiation treatment is based, predicting changes over time of the tumor and incorporating them in automatic treatment planning and adaptation.

POP-AART will run for five years. Research topics range from improving CT images obtained just before radiation to the level of diagnostic quality CT images, predicting deformations and segmentations of the tumor and organs at risk and incorporate these data in online and automated treatment plan optimization for each patient individually at each radiation session.

The lab will be led by scientific directors Efstratios Gavves and Jan-Jakob Sonke. Gavves is assistant professor of Computer Vision and Deep Learning at UvA. Sonke is theme leader image guided therapy at the Netherlands cancer institute and Professor by special appointment of Adaptive Radiotherapy at the Faculty of Medicine at UvA. The Governing Board will consist of academic partners Lodewyk Wessels (NKI-AvL) and Mark de Graef (UvA) and industry partner Rui Lopes (Elekta).

About the Netherlands Cancer Institute

The Netherlands Cancer Institute, founded in 1913, is among the top 10 comprehensive cancer centers, combining world-class fundamental, translational, and clinical research with dedicated patient care. Their initiatives to promote excellent translational research have been recognized by the European Academy of Cancer Sciences, when they designated the institute ‘Comprehensive Cancer Center of Excellence in Translational Research’.

About Elektra

For almost five decades, Elekta has been a leader in precision radiation medicine. Their more than 4,000 employees worldwide are committed to ensuring everyone in the world with cancer has access to – and benefits from – more precise, personalized radiotherapy treatments. Headquartered in Stockholm, Sweden, Elekta is listed on NASDAQ Stockholm Exchange. 

Find out more about POP-AART lab.

Tilburg newest ICAI location with MasterMinds Lab

MindLabs recently joined the national Innovation Center for Artificial Intelligence (ICAI). This makes Tilburg one of eight locations with an ICAI lab. Together with the partners in the MasterMinds project, MindLabs collaborates in this public-private research lab, named MasterMinds AI Lab. The MasterMinds AI Lab is one of the many initiatives within MindLabs and is dedicated to the development and evaluation of new technologies, focusing on the cross-fertilization between artificial minds and human minds.

Artificial Intelligence and Human Behavior

The ICAI is a national collaboration of several universities, companies and the Dutch government with 27 labs on eight locations. The goal  of the Dutch government and universities is to remain at the forefront of AI by knowledge development and nurturing young talent.  MasterMinds collaborates in research at the intersection of robotics and avatars, serious gaming, decision making, and virtual and augmented reality. The results of these studies are applied to realize AI solutions for the benefit of society.

Max Louwerse

Professor Max Louwerse, scientific director of the MasterMinds AI Lab: “The future of AI increasingly lies at the intersection between artificial intelligence and human behavior. The MasterMinds project works at this interface to develop new technologies and will be able to apply them immediately. This is entirely in the nature of MindLabs.”

Five MasterMinds research projects

The MasterMinds project consists of five innovative research projects, aiming to develop breakthroughs with interactive AI technologies such as serious gaming, augmented and virtual reality, intelligent tutoring systems and natural language processing and data science. Research questions include: Can we train and improve complex decision-making using serious gaming? What is the learning effect of training pilots using virtual reality? How do we effectively design AR and VR training modules? How can we develop and use intelligent tutoring systems? The project is funded to stimulate regional ecosystems to develop a resilient, sustainable, and future-proof economy with a central role for SME’s.

The MasterMinds project brings together knowledge institutions, industrial partners, and governmental organizations to work together on AI solutions that can be readily used for the partners. The project aims to develop AI technologies combined with the impact on and input from human behavior, across multiple sectors in society in the field of aerospace, logistics, maintenance, and education focusing on robotics and avatars, serious gaming and learning, language and data science technologies and virtual and augmented reality solutions. The project provides a T-shaped profile of explainable AI solutions, where depth is achieved per subproject while breadth is achieved across the five projects. The project answers questions that have been formed by the industrial partners to prepare for the technology-driven future that lies ahead.

The five MasterMinds reseach projects:

  1. Serious Games in logistics – Port of Rotterdam
  2. VR for air force simulations – Dutch Royal Airforce and MultiSIM
  3. AR & VR for production and maintenance – Actemium, Marel en CastLab
  4. Evidence-based prevention: predictive analytics – Interpolis en Gemeente Tilburg
  5. Virtual Reality in Education – WPG Zwijsen, Spacebuzz en Timeaware

MasterMinds brings together the “brightest minds” in artifical and human intelligence.

Read more on the MasterMinds Lab

ICAI Interview with Martijn Kleppe: gaining insights much quicker by combining AI and Humanities

Martijn Kleppe is a trained historian who collaborates with AI scientists. Kleppe: ‘When I was doing research as a historian, I could analyze twenty books in a month. For the computer this is a matter of seconds.’

Martijn Kleppe

Martijn Kleppe is one of the founding members of Cultural AI Lab and the head of the Research Department of the KB National Library of the Netherlands.

The Cultural AI Lab is a joint effort of the heritage institutions Rijksmuseum, Institute for Sound and Vision, the KB and knowledge institutions CWI, KNAW, UvA, VU and TNO.

What problems within the humanities can be solved with AI?

‘The biggest challenge that we face within the humanities is scale. There is a shift happening right now within historical research from close reading, which we have done for centuries, to distant reading, where we use a computer to detect patterns in all sorts of humanities data. In books, newspapers, television programs, artworks, social media outlets etcetera. This is the biggest opportunity that we have right now, but also the biggest challenge because we have to rely on other competences to make this kind of research possible.’

How is the interest in AI from the cultural world?

‘It is really gaining momentum right now. There is an ecosystem evolving with partners from the culture and media domain – like the Rijksmuseum, the National Archive – and the creative industry, that are interested in applying AI within their services or processes. And several members of our lab recently founded the working group ‘Culture & Media’ within the National AI Coalition with all sorts of cultural and media partners.’

Does the humanities also influence AI?

‘Yes, it creates new academic research questions. Most of the algorithms within the AI domain have been trained with new and high quality data. But in the datasets of the heritage institutions there is 200 year old data. Digitized newspapers from the end of the nineteenth century with a very low quality for example. And newspapers from colonial Indonesia and Suriname with a completely different vocabulary. Bringing in those kinds of datasets within the AI domain offers new perspectives and questions on polyvocal data. How can we handle these kinds of data and how can we improve them? My experience so far is that the computer scientists involved in our project love these new questions.’

At the ICAI meetup on July 8, the lab will speak about contentious words in cultural heritage collections. How does the lab approach this?

‘Handling issues like that, is the essences of our research. We try to answer the question: How can you detect bias in descriptions of artifacts of museum collections? And can you also help the museum by giving them suggestions for other kind of words? Especially last year, with the Black Lives Matter movement, we saw how relevant these questions were. How do we deal with the past? It is a technical, but also really a societal and ethical challenge.‘

Boek uit de KB collectie

As a historian, what attracts you in AI?

‘I have to ask new types of questions. Instead of doing source criticism on books, newspapers or television programs, now I have to do source criticism on algorithms. At the KB we have the Delpher.nl platform for example, where you can search in millions of digitalized texts from Dutch newspapers, books and magazines. In order to search efficiently, you have to understand the basis of the algorithm behind it. What I also really like about the AI research is the teamwork. Traditionally humanities scholars are more solitary researchers. But to be able to collaborate with other disciplines you have to be vulnerable and develop yourself.’

Does it happen that you get a new perspective on heritage collections because of the AI research?

‘Yes, for sure. During my PhD research I wrote an article about the first moment in time when a Dutch photograph was published in a Dutch newspaper. That research was based on manually going through a selection of newspapers. But then four years later I participated in a research project with a historian who was one of the firsts to start applying Computer Vision on historical newspapers. He run an algorithm that went through all the newspapers and immediately said: ‘Martijn, you were completely wrong. The first photograph was published earlier than the moment you mention in your paper.’ That was fantastic. Science is always about gaining new insights. When I did my research, those techniques did not exist yet. We now gain insights much quicker than we did before.’

On July 8, 2021, Cultural AI Lab will talk about making AI ‘culturally aware’ during the Lunch at ICAI Meeting. Want to join? Sign up here.

3 Reasons Why You Should Learn About AI

TU Delft and ICAI present the online program AI in Practice. A course developed for anyone interested in learning how AI technology can help their organizations. Why can AI be interesting for your company?

1. AI isn’t just hype

While the adoption of Artificial Intelligence (AI) was already on the increase before 2020, not surprisingly the COVID-19 pandemic has accelerated this trend. According to some studies, the ongoing crisis and lockdown measures have stepped up the digital transformation of many organizations and the adoption of AI. McKinsey’s Global Survey on AI in 2020 states that despite the economic challenges, most high-performing companies have increased their investment in AI amid the COVID-19 crisis.

The increasing use of digital tools and online activities are also uncovering new opportunities in areas as diverse as business, public administration, education and research. Elizabeth Aguado, a professional working on import operations in Peru, says:

“With the reset we are about to experience due to COVID-19, many young professionals see the necessity of upgrading their skills to stay competitive in an ever changing business world. There are definitely better career prospects for those who are skilled in new technologies and I realized that AI was something I needed to continue to be valued in the manufacturing and import/export industry.”

2. AI is for everyone

Regardless how large or small, simple or complex your organization may be, there are AI solutions available in all shapes and sizes. AI can help solve specific problems, drive efficiency and improve performance and decision-making. It can support all kinds of business needs, from automating business processes, handling and interpretation of data to engaging with customers and employees. Marian Stan, Manager Customer Support in Romania, says:

”I had been interested for some time to learn more about AI, especially to gain new ideas on how AI can be implemented in certain industries.”

AI is clearly a field that no longer concerns solely data scientists and computer programmers. With AI emerging as the most disruptive type of technology, a wide range of professionals also need to prepare for the application of AI in their organizations. This includes managers and business leaders who want to know what AI can do for their companies, or data analysts and consultants who want to understand how AI can be applied in their business processes. Zeinep Kechagia, Management Consultant in the financial sector, says:

“I am always very keen to explore the future of all complex decision-making processes in a structured way. What I have learned in the field of AI will help me to guide my clients through their transformation journey mostly by integrating their assets with state-of-the-art technology and solutions.”

3. Preparing for AI is key

AI is developing at such rapid pace that before investing in a new AI initiative, organizations need to fully understand the pros and cons of different AI technologies. Gerard Danjou, a Senior Director in a digital market place, says:

“After a career in consumer goods and traditional retail industry, I joined an E-commerce platform and became fascinated by improving search in the E-commerce industry. I wanted to understand the role AI would play in the future of E-commerce and the challenges and considerations that need to be taken into account when deploying E-commerce even further.”

Understanding the practical aspects of applying AI is key. From implementation challenges, lifecycle aspects, maintenance and management of AI applications, to potential implications such as compliance and ethical considerations. Think for instance of concerns about the potential misuse of data, security or privacy issues. Learning about the practicalities of AI can help you avoid wasting time and resources pursuing the wrong technology or taking unnecessary risks.

Month of AI

International and national initiatives, like the Month of AI, offer a wide range of options to learn about the latest in AI research and applications.  

Developed by the Innovation Center for Artificial Intelligence Academy (ICAI) and the Delft University of Technology, the online program AI in Practice presents a wide range of real cases and examples to illustrate how AI can be of value in all types of organizations. It includes more than 25 contributors from 14 different organizations, universities and companies.

Regardless of your professional background or job role, if you are, like many others, puzzled as to how to get involved with the technology, or how to apply it in your business processes and successfully integrate it in your organization, this online and self-paced program might be just what you need to be able to navigate this new technology and its integration.

UvA, TU Delft and Booking.com launch Mercury Machine Learning Lab

UvA, TU Delft and Booking.com collaborate on research into better recommendation systems

In the Mercury Machine Learning Lab, researchers from the University of Amsterdam (UvA) and Delft University of Technology (TU Delft) will be working together with Booking.com on various improved recommendation systems. The collaboration provides the unique opportunity to test AI techniques in the real world, allowing new machine learning methods to be safely developed for wide application, for example in mobility, energy or healthcare.

Every day, millions of travellers from all over the world make multiple decisions on Booking.com related to their upcoming travel plans. With all of these taps and clicks on property photos and scrolling through search results, Booking.com naturally has a wealth of data insights to help the company make changes on the platform to improve the customer experience.In addition to the responsibility of handling all of this information securely and ethically, how do you analyse all of this data properly and continue to make useful recommendations for customers? Is what works well for a Dutch traveller equally as relevant for a traveller from Japan? And how do you ensure that customers continue to receive interesting travel recommendations that are relevant to them without getting stuck in a filter bubble?

On the road to even better recommendations

One way to understand what constitutes a good recommendation is looking at what previous travellers have chosen and the experiences that their choices yielded. Machine learning techniques are well suited to learning such connections and preferences. However, the problem is that the connections and preferences found in the data are not only informed by the choices of other travellers, but also by the suggestions and selections the system showed them. In the Mercury Machine Learning Lab, researchers from the University of Amsterdam (UvA) and Delft University of Technology will work together with data scientists from Booking.com to develop methods that will ensure that this type of bias is avoided and that the learned connections remain accurate in a new or different context.

From the classroom to real-time e-commerce
Joris Mooij, scientific director of the Mercury Machine Learning Lab at the UvA: ‘It’s a huge opportunity for us as researchers to have access to a live dataset of global data and be able to experiment on Booking.com’s platform.’ Frans Oliehoek and Matthijs Spaan, scientific directors from TU Delft, agree. Oliehoek: ‘By testing AI techniques in the real world, we can better understand the limitations of current state-of-the-art methods in the field of reinforcement learning, as well as improve the application of AI in practice.’ Spaan: ‘The lab’s focus on developing better algorithms for recommender systems is highly relevant to our society as these systems guide many of our digital interactions. By addressing fundamental AI challenges, the results of the lab will also be valuable in other domains.’

Onno Zoeter, Principal Data Scientist and Booking.com scientific director adds: ‘Unlike in a hospital scenario for example, where experimenting with different types of data-driven recommendation systems can have real life-and-death consequences for patients and their suggested treatment protocols, testing approaches, models and hypotheses with travel data from Booking.com doesn’t come with the same public health implications. This means we can safely test and develop new machine-learning methods together that also have a potential impact far beyond the trips booked on our platform.’

Learnings from other languages

Artificial intelligence and natural language processing are already used to perform many important tasks in different languages, such as categorising reviews and fraud detection. The researchers will look for ways of creating a system with multiple languages in which the smaller languages can benefit from what has been learned in models and rounds of experimentation with languages that are spoken more widely. This should enable Booking.com to support all 44 languages and dialects in which their platform is available to customers in various new contexts, even more quickly.

Nurturing Dutch talent

The Mercury Machine Learning Lab will be part of ICAI, the Innovation Center for Artificial Intelligence. The Lab will provide world-class opportunities for Machine Learning graduates to stay in the Netherlands and lead innovative research, keeping important talent connected to Dutch universities and industry.

In addition to the existing researchers, the Mercury Machine Learning Lab will comprise six PhD candidates and two postdocs who will work on six different projects related to bias and generalisation problems over the course of the next five years. They will spend two days a week in the office at Booking.com doing research and actively participating in related streams of experimentation to test their hypotheses.

Find out more about Mercury Machine Learning Lab