Close this search box.

AI will be “lane assist” for healthcare professionals in ultrasound scans of pregnant women

23 May 2024

AI will be “lane assist” for healthcare professionals in ultrasound scans of pregnant women

After two years of collaboration, a team of researchers from Danish universities has developed an artificial intelligence capable of evaluating the quality of ultrasound scans of pregnant women, drawing insights from experienced physicians. This innovation aims to enhance the quality of scans not only within Denmark but also in developing nations.

Ultrasound scanning during pregnancy is a challenging discipline. Many practitioners have dedicated their careers to capturing precise fetal images using only a small probe and a screen. The pursuit of detecting fetal anomalies is often challenged by factors such as ultrasound beam alignment, layers of fat, and organ positioning, contributing to the difficulty in achieving clear and interpretable images.

Presently, there exists considerable variability in the quality of ultrasound scans of pregnant women, with evidence indicating a correlation between the expertise of clinicians and the detection of growth abnormalities. This underscores the need to standardise scan quality across clinicians and medical facilities. Here, artificial intelligence can serve as a mentor to less experienced practitioners.

Doctors train the algorithm

As part of the EXPLAIN-ME project, a group of researchers has been working since 2021 to create an explainable artificial intelligence (XAI) designed to guide healthcare professionals in performing high-quality scans without deep expertise. A significant milestone in the project has been the development of an algorithm that, based on criteria set by experienced doctors, matches the level of experienced clinicians in selecting quality scan images.

“Ultrasound scanning requires substantial expertise and specialized skills. Obtaining high-quality images is challenging, leading to great variations in scan quality across different hospitals. We hope that our project can level out these quality differences,” says Aasa Feragen, project leader of the EXPLAIN-ME project and professor at DTU Compute.

Close collaboration between theory and practice

With an effective AI model in place and eighteen months remaining until the project’s completion, the focus is now to determine the best way of conveying the model’s guidance to healthcare professionals—an aspect often overlooked in the research world.

“We work very closely with doctors and sonographers. It’s crucial for us, as technical researchers, to understand what is needed for our models to make a real impact in society,” says Aasa Feragen.

The PhD student Jakob Ambsdorf has gained invaluable insights into healthcare professionals’ needs through his engagement with the Copenhagen Academy for Medical Education and Simulation (CAMES) at Rigshospitalet.

“I’ve spent a lot of time in the clinic at Rigshospitalet to identify the challenges faced by staff. We’ve learned that sonographers don’t necessarily need help with diagnosis but rather with enhancing image quality. Thus, instead of trying to imitate human decisions, we aim to refine the surrounding factors. For instance, we recommend slight adjustments to the probe’s positioning or settings to enhance image clarity. It’s like a lane-assist for sonographers and doctors,” he says.

Potential for global expansion

With the project set to conclude in 2025, the primary objective is to expand upon the XAI model to equip less experienced healthcare personnel worldwide with the tools for conducting advanced scans. The XAI model, developed by the University of Copenhagen, has already undergone trials using data from Tanzania and Sierra Leone.

“In the long term, the model can be used in areas with limited access to high-quality equipment and specialised personnel,” concludes Jakob Ambsdorf.

DIREC has provided support to the EXPLAIN-ME project with a grant of DKK 7.39 million. Beyond ultrasound scans, the project also addresses the diagnosis of kidney tumors and robotic surgery.

What is explainable artificial intelligence (XAI)?

Explainable artificial intelligence aims to explain the rationale behind AI model outputs, fostering trust in their decisions. As machine learning models grow in complexity and are increasingly employed for critical decisions, XAI enables users to understand the data on which they were trained and assess the accuracy of the output.


Is there a digital architect present?

16 May 2024

Is there a digital architect present?

Focusing on user-centered design can give Denmark a unique competitive advantage, positioning us as the leading country in Europe for developing innovative digital solutions. The best IT solutions are those where technology seamlessly integrates into the background, enabling us to accomplish our tasks effortlessly.


In the Danish TV program “Is there an architect present?”, Ane Cortsen asks: How could an architect design such a controversial building? The same question can be posed about many IT solutions being rolled out in Denmark. Was there an IT architect present?

There are many parallels between building design and IT development. Just as glass, stone, concrete, and steel can be combined into beautiful and inspiring structures — or the complete opposite — software can be developed to either simplify our lives or create frustrating user experiences that may lead us to abandon the digital solution entirely, if that’s even possible.

The Danish architect Jan Gehl is renowned for his human-centered approach to urban planning and the interaction between people. Similarly, it is crucial to incorporate the human element in technology design.

The best solutions 

The best IT solutions are those where technology seamlessly integrates into the background, helping us accomplish the tasks we need. It is the smartphone that unlocks automatically with advanced facial recognition software, the payment app that facilitates transactions easily via the phone, the health card always available on the phone, and the many online shops that allow us to order items with just a few clicks.

Unfortunately, there are also many counter-examples. Recently, I had to pay a library fine of 20 DKK. From the moment I clicked the payment link and was asked to log in with MitID, I had to navigate through the municipality’s debt collection system before finally being redirected to MobilePay, where I could transfer the 20 DKK. The media are full of similar examples.

Unlike a building, a digital solution can be rolled out to a large group of people in a very short time. Thus, both good and bad solutions quickly impact many users. To ensure that all of Denmark benefits from the digitalisation wave, the primary challenge is not necessarily the digital technology itself but the lack of user involvement and thoughtful design before a new digital solution is implemented.

Where is the architect?

In Denmark, we have more than 40 years of experience in designing digital solutions with a human-centered approach as an academic discipline at our universities. Now is the time to leverage all that knowledge and experience and include the users’ perspectives from start to finish, as they possess the in-depth domain knowledge, experiences, insights, and skills crucial for creating successful IT solutions.

Our experience in researching user-centered digital design can become a unique competitive advantage, positioning Denmark as one of the leading nations in Europe for developing new digital products.

Our goal should be to develop IT solutions and technologies that are not just technological achievements but primarily aim to make our daily lives easier and more efficient.

We should celebrate the user-friendly digital solutions we currently have in Denmark because, unfortunately, there are enough poorly designed solutions to warrant a new program titled: “Is there a digital architect present?”


This column was featured in ITWatch on 15 May 2024.


D3A 2.0 – Open call for session proposals

8 March 2024

D3A 2.0 – Open call for session proposals

Mark your calendars for October 22-23, 2024, as we gear up for another great community-driven conference in Nyborg – Danish Digitalization, Data Science and AI 2.0 – also called D3A 2.0.  

We invite you to contribute to the program of the conference by submitting a proposal for a parallel session.

You are not required to be active in the Danish Data Science Academy, Pioneer Centre for AI or DIREC to propose a session or participate in D3A 2.0.

We encourage people from different disciplines to work together to create synergies through their sessions.

If you are looking for new collaborators or a co-organizer, you can join our D3A LinkedIn group to connect with other researchers and professionals from the Danish digitalization, data science, and AI communities.

Find more info and submit your proposal

D3A – Danish Digitalization, Data Science, and AI is a new scientific conference where the newest research and insights will be discussed.


DIREC annual report 2023

7 March 2024

DIREC annual report 2023

In 2023, there was a significant breakthrough in digitisation, particularly in generative AI, which became a widespread topic of conversation. The introduction of ChatGPT allowed everyone to explore the possibilities of interacting with advanced language models. 

While AI is of course a major focus in DIREC, we also emphasise that digitisation encompasses more than just AI. It involves developing skills that not only align with current trends but also anticipate the themes of tomorrow. In simpler terms, although the spotlight is on AI, advancements are not limited to that field; they also extend to areas such as robotics, user interfaces, programming languages, software architecture, cybersecurity, and blockchain. We are therefore proud of the diversity of projects in DIREC. 

In 2023, our centre reached full speed. Our 40+ projects are well underway, and the results are starting to materialise. 

Read our annual report


Automated Sensitivity Analysis Enhances Trustworthiness of Probabilistic Programs

6 March 2024

Automated Sensitivity Analysis Enhances Trustworthiness of Probabilistic Programs  

Probabilistic programs, a fundamental concept in modern computing, have gained increasing attention due to their versatile applications across various domains, including machine learning, cryptography, and statistics. However, ensuring the reliability and trustworthiness of these programs poses significant challenges, particularly in understanding their probabilistic nature and analysing their sensitivity to input changes.

A recent study led by researchers Alejandro Aguirre from Aarhus University and Christoph Matheja from DTU has made strides in addressing these challenges. With funding from DIREC – Digital Research Centre Denmark, their project, titled “Automated Verification of Sensitivity Properties for Probabilistic Programs,” explores the feasibility of using automated program verification techniques to analyse the sensitivity and robustness of probabilistic programs.


Christoph Matheja, DTU (left) and Alejandro Aguirre, Aarhus University (right)

Robustness is paramount

At the heart of probabilistic programs lies the ability to sample from probability distributions and make decisions based on the outcomes, injecting randomisation into computations. While this randomness is essential for various applications, it also introduces complexities in understanding and quantifying the distributions produced by these programs. Moreover, ensuring the robustness of probabilistic programs against input changes and variations in sampling distributions is paramount for their reliability.

The project emphasizes the importance of sensitivity analysis in assessing the trustworthiness of probabilistic programs. Sensitivity, defined as the degree to which a program’s output changes in response to small changes in its inputs, serves as a crucial metric for evaluating program robustness. Trustworthy programs exhibit low sensitivity, indicating that minor input fluctuations do not yield significantly different results.

Bridging the gap between theoretical insights and automated analyses techniques

The research project leverages the automated verification tool Caesar and the relational weakest preexpectation calculus, which has been developed by the researchers, to analyse sensitivity properties of probabilistic programs. By encoding theoretical proof systems into practical verification tools, the researchers have bridged the gap between theoretical insights and automated analysis techniques.
As a case study, the researchers applied their methodology to analyse the rate of convergence of the Q-learning algorithm, a popular reinforcement learning algorithm widely used in various fields, including automated driving and text generation. By examining how the algorithm’s estimates converge over iterations, they demonstrated its theoretical convergence properties and validated its practical performance.

Future directions

The project’s findings were presented at VeriProp, an international workshop focusing on the verification of probabilistic programs, showcasing the potential impact of automated sensitivity analysis in enhancing the reliability of probabilistic programs.
Future applications include the analysis of more advanced machine learning and sampling algorithms, such as the Stochastic Gradient Descent Algorithm and Markov Chain Monte Carlo. Additionally, efforts will be directed toward making verification tools more accessible to engineers, thereby empowering a broader community to ensure the trustworthiness of probabilistic programs in diverse applications.

By advancing automated sensitivity analysis techniques, this research not only contributes to the theoretical understanding of probabilistic programs but also paves the way for their practical implementation with enhanced reliability and trustworthiness. 

What are probabilistic programs?

Probabilistic programs are computer programs that can sample from probability distributions, for example, by flipping a fair coin, and make decisions based on the outcome. Probabilistic programs thus inject randomization into computations.

Randomization is a ubiquitous concept in modern computing, with applications in machine learning, where the quality of the learned result heavily relies on the quality of samples; the design of randomized algorithms, which leverage sampling to be, on average, more efficient than their non-randomized counterparts; and cryptography, where randomness is needed for encoding secrets. In statistics, probabilistic programming languages have become popular modelling tools that are more expressive and accessible than classical graphical models.



The award goes to…

13 December 2023

The award goes to....  

PhD Student Axel Christfort and Supervisor Associate Professor Tijs Slaats from the University of Copenhagen won the Process Discovery Contest at the 5th International Conference on Process Mining with their DisCoveR miner.

In a remarkable achievement, PhD student Axel Christfort and his supervisor, Associate Professor Tijs Slaats, won the Process Discovery Contest at the 5th International Conference on Process Mining.

Their cutting-edge DisCoveR miner produced the most accurate models and stood as the sole algorithm to successfully complete discovery and classification tasks within the stipulated time.

Process discovery algorithms play a crucial role in analyzing event logs, generating human-readable models that elucidate the behavior captured in the log. This includes understanding how individuals sequence activities in their work processes. The ICPM Conference, organizers of the Process Discovery Contest, evaluate submissions based on accuracy, requiring participants to mine models for a diverse range of logs and correctly classify corresponding ground truth traces.

This is the third prize in the Process Discovery Contest for the Process Modelling and Intelligence group from the Department of Computer Science, University of Copenhagen. In 2021, they secured awards for the best overall and the best imperative miner. The DisCoveR miner.

DisCoveR originated from a M.Sc. thesis by Viktorija Sali and Andrew Tristan Parli, supervised by Professor Slaats. The algorithm has undergone further refinement by Industrial PhD Student Christoffer Olling Back from ServiceNow, with ongoing enhancements by Axel Christfort. Funding from Independent Research Fund Denmark, DIREC – Digital Research Centre Denmark, and Innovation Fund Denmark has been instrumental in supporting this groundbreaking work.

Axel Christfort and Tijs Slaats are nominated Process Discovery Contest Winners

The industrial application of DisCoveR has been demonstrated through its implementation by DCR Solutions. The algorithm’s efficacy and utility have been validated in real-world scenarios, emphasizing its practical significance. Ongoing contributions from PhD Vlad Paul Cosma and Professor Thomas Hildebrandt have further extended and improved the miner, adding to its robustness.

Looking ahead, the Process Modelling and Intelligence group is eager to build upon these achievements to secure additional funding and foster novel collaborations. The team is already gearing up for the next iteration of ICPM, aiming to continue their winning streak and further advance the field of process discovery.


Associate Professor Tijs Slaats is the project manager of the DIREC project ‘AI and Blockchain for complex business processes’.

Together with industry, the project aims to develop methods and tools that enable the industry to develop new efficient solutions for exploiting the huge amount of business data generated by enterprise and blockchain systems, with a specific focus on tools and responsible methods for the use of process insights for business intelligence and transformation.  


It requires collaboration with people of different expertise to push your idea forward

11 December 2023

It requires collaboration with people of different expertise to push your idea forward  

Kurt Nielsen is one of the pioneers behind encryption and blockchain technology for protecting sensitive data while in use, and co-founder of Partisia. Here, he tells about the journey from researcher to CEO.

It all began as two research projects at Aarhus University, where a small team of researchers with diverse backgrounds in cryptography, business economics, and software development joined forces. The collaboration resulted in a groundbreaking cryptography technology, and in 2008, the tech company Partisia was born.

The CEO and partner Kurt Nielsen with a background in mathematics and economics, was involved from the beginning – from the first idea conceived by Professor Ivan Damgård at the Department of Computer Science at Aarhus University to the foundation of Partisia, which is now a leader in advanced cryptography and blockchain technologies for the financial sector, 15 years later.

At that time, Kurt Nielsen was fully engaged in his PhD when he got into a conversation with Professor Ivan Damgård. Over the following years, they worked closely on developing and deploying the new encryption technology, and a collaboration with the food producer Danisco became their major breakthrough.

Danisco, undergoing extensive restructuring at the time, became the first company to adopt the new encryption technology. The collaboration was the industry breakthrough that the research team had been working towards for years – both technologically and commercially. From then, things gained momentum, and more public and private collaborations followed.

From technological breakthrough to entrepreneurial adventure

From thinking you have the solution to creating a viable business is a long journey, says Kurt Nielsen. Partisia was an early adopter of a completely new technology, and it took many years before the market was ready to embrace it, he explains.

Along the way, one encounters a lot of resistance and difficult discussions about everything from strategy to finance. One must be prepared for that, and to have a chance at success, it requires the team to challenge each other, listen, and compromise when necessary.

What does it mean to have a background as a researcher when establishing a company?

“In my work as a researcher and lecturer at the University of Copenhagen, new ideas constantly emerge. I am driven by these ideas and gain energy from them. I believe that many researchers have the same driving force—the key to success with a product or a company lies in the commercial approach, and it varies greatly from researcher to researcher.

Not everyone has it, but there are incredibly talented basic researchers who have a good understanding of how to take an idea forward and who understand that it requires collaboration with people with different expertise to advance one’s idea.

Personally, throughout my university career, I have always been an ‘entrepreneur,’ and early in my career, I helped some friends start a company. However, the dot-com bubble burst, and I returned to the university for a PhD. while considering my future options.

Being an entrepreneur is a state of mind. You must constantly look for new opportunities and be interested in assembling strong teams.

This applies internally in a company and at the university when working together on research projects. The team is crucial.”

Where does this entrepreneurial spirit come from?

“That’s a good question. I have always sought out opportunities, trying to create something through my work and not be locked into a specific job for a lifetime. In reality, I have never considered myself an employee, even though I have received and continue to receive a salary as a researcher. It is the desire to create and develop that drives me.”

About Partisia
Partisia is a spinout from Aarhus University established by internationally renowned researchers and experts in advanced cryptography, business economics, and software development, with experience bringing research ideas to market. The combination of skills enables Partisia to deliver solutions that are both robust and highly innovative in a timely manner.

As a pioneer, Partisia has been selling secure multiparty computation (MPC) and other software solutions for privacy protection since 2008. Initially focusing on secure auctions for commodities such as production contracts, energy-related products, and auctions used for the sale of spectrum licenses.

Since the first commercial use, MPC technology has matured significantly, becoming more agile and notably faster, gradually transforming MPC into a generic infrastructure for privacy-preserving computations.

In parallel with this development, Partisia has developed infrastructure for managing encryption keys and a generic infrastructure for secure computation, as well as various applications across platforms from cloud computing to blockchain technologies.

As part of the commercialization strategy, selected companies have been moved and matured into separate spinouts alongside investors and other business partners, namely (cryptographic key management) and Partisia (applications and infrastructure combining MPC and blockchain technologies). In 2022, Sepior was sold to a major American blockchain company, Blockdaemon, and Partisia is now actively scaling up, focusing on quantum computers.

Read about DIREC’s focus area Digital Tech Startups

The Partisia team assembled in the summer of 2023


ChatGPT ushers research into a new era – calling for new rules of the game

1 December 2023

ChatGPT ushers research into a new era – calling for new rules of the game

Language models like ChatGPT will change how we conduct research. To ensure transparency and maintain trust in research, a code of conduct should be drawn up, writes the Royal Academy in Altinget, an online Danish political review.

Authors of the opinion piece:

  • Kim Guldstrand Larsen, professor, Department of Computer Science, Aalborg University, member of Royal Academy
  • Susanne Ditlevsen, chair of the natural sciences class at the Royal Academy and professor at the Department of Mathematical Sciences, University of Copenhagen
  • Thomas Sinkjær, secretary general, Royal Academy and professor at the Department of Medicine and Health Technology, Aalborg University
  • Kristoffer Frøkjær, head of communications, Royal Academy

Israeli researchers recently produced a research paper in less than an hour with the help of ChatGPT.

Fluent and insightful, the article adhered to the expected format of scientific articles. The results, however, were nowhere near close to being novel. This will change in the future.

Read the Altinget opinion piece


Lack of digital skills can impede the Danish quantum adventure

29 November 2023

Lack of skills can impede the Danish quantum adventure

Quantum technology opens up a world of possibilities, but we must acknowledge that the path forward may not necessarily be easy. Denmark can play a crucial role in the development, but to realize this potential, focused investments and, above all, competent digital specialists are needed.

This opinion was published in Børsen on 29 November 2023

Thomas Riisgaard Hansen, Director, Digital Research Centre Denmark
Allan Grønlund, co-founder, Kvantify
Michael Kastoryano, Associate Professor, ITU
Jaco van de Pol, Professor, Aarhus University

Quantum computers will not replace our existing computers; they will complement them. They will be particularly effective for highly specialized tasks, where they can perform complex calculations significantly faster than conventional computers.

Read more (in Danish)


Swarms of robots are being deployed on the fields – What does it take to expand the use of them?

21 November 2023

Swarms of robots are being deployed on the fields – What does it take to expand the use of them?

Danish farmers are ready to embrace new technologies to support the green transition and ensure smarter production. Multi-robot systems are a crucial part of the solution, but barriers need to be dismantled and teething problems eliminated for seamless interaction between farmers and robots.

Self-driving robots are replacing diesel-powered giant machines, and multi-robot systems enable several robots to collaborate in the fields. Precision spraying of fertilizers and pesticides reduces the use of spray chemicals.

There are both environmental and efficiency gains in entrusting fieldwork to robots, and technology plays a vital role in the agricultural green transition.

“One of the major problems in agriculture is that farm machinery is getting larger and larger. However, when large machines traverse the ground, they compact the soil, requiring a significant amount of energy to repair the damage they cause. If instead, we deploy smaller, autonomous robots, we can increase efficiency without causing damage to the environment.”

– Anders Lyhne Christensen, Professor, University of Southern Denmark, UAS Center

The development imposes new requirements on both technology and users. In the HERD project, funded by DIREC – Digital Research Centre Denmark, Aalborg University’s expertise in designing user interfaces, University of Southern Denmark’s (SDU) knowledge of robotics, and Copenhagen Business School’s (CBS) insights into market creation and business models are combined with use cases from various companies developing robot systems.

AGROINTELLI, a Danish scaleup, is one such company working to break down barriers preventing farmers from adopting new technologies. Alea Scovill, R&D Manager at AGROINTELLI, emphasizes the importance of addressing factors like price, robustness, and user-friendliness to facilitate wider robot adoption.

“At AGROINTELLI, efforts are being directed towards breaking down some of the barriers currently preventing several farmers from adopting new technologies – a challenge encountered by the majority of field robot companies in the EU, says R&D Manager Alea Scovill from AGROINTELLI.

“If farmers cannot see how the robot fits into the farm and can be used without significant instruction, sales are lost. Price, robustness, and user-friendliness are other parameters influencing the adoption and serving as barriers for more farmers to embrace the robots,” explains Alea Scovill, who is in close dialogue with the involved researchers from CBS.

The role of CBS researchers in the project is precisely to explore the market challenges and commercial opportunities in the technology, and what it takes to mature the market. PhD student Alexandra Hettich, for instance, has interviewed various stakeholders such as sales personnel and dealers, and will soon interview the farmers. 

“Agriculture is particularly interesting as a domain. With the introduction of robots, the farmer’s work is significantly altered, and the obstacles to a successful implementation of this groundbreaking technology vary in nature. Therefore, we need to analyze the diversity of obstacles before developing concrete solutions to overcome them,” says Alexandra Hettich, PhD student at CBS.”

The collaboration uncovers various aspects of the technology

According to Professor Anders Lyhne Christensen from the University of Southern Denmark, the project leader for the project, the results are particularly interesting because they cover all aspects of technology, focusing on both the technological challenges, user experience, and the commercial aspects of agricultural robots as a business area.

“At SDU, we work with multi-robot systems and focus on how to make robots do what they need to do and provide the user with the information they need. Aalborg University works on user interfaces and user interfaces, such as how users can keep track of what robots have done, what they are currently doing, and what they will do in the future. In other words, how to give the user the right buttons to turn. Finally, CBS focuses on the business part for companies developing these robots and what business models may be promising for them. How can they access the market, and what happens at the other end with the organizations that need to use multi-robot systems, how do they change?” explains Anders Lyhne Christensen.

The focus is largely on users’ understanding and use of the technology, he elaborates.

“We can certainly create robots and program them to do this and that, but getting them to work in the real world requires that people can control them. What we are working on is therefore the interaction between the AI in the robots, the people who have to control the robots, and the organizations around them.”

“It doesn’t work if the farmer has to keep an eye on the robot while it performs the task – not much is gained then. Instead, it is important to be able to oversee what several robots are doing at once.”

It may also be that the farmer himself does not have to monitor the robots, but a company that monitors robots for 50 farmers at a time, and then it changes those organizations because new job functions and responsibilities come with the technology.”

Alea Scovill is pleased with the collaboration with the researchers. It works well, says the R&D manager.

“The flow of information between the partners in the project has been relatively smooth. At AGROINTELLI, we have primarily worked with CBS and Aalborg University because their research areas fit well with our situation. CBS is investigating the market obstacles for ROBOTTI. And at Aalborg University, the researchers have developed a new proposal for a user interface for remote monitoring of multiple robots, and they will soon interview an agricultural school about the experience of the new user interface,” says Alea Scovill.



In the HERD project, researchers, along with industrial partners, aim to develop technologies that enable end-users to engage and control systems consisting of multiple robots. The goal is to enhance the value of industrial products by enabling faster and more cost-effective completion of current tasks and addressing entirely new tasks that require coordinated robot efforts.

Project period: 2021 to 2025 
Budget: DKK 17.08 million 
Partners: University of Southern Denmark, Aalborg University, Copenhagen Business School, AGROINTELLI, ROBOTTO, and the Danish Technological Institute. 

More about the project