43 collaborating researchers from TU/e, WUR, UU and UMC Utrecht received 260.000 euros of seed funding for cross-disciplinary collaborations within seven projects. The aim of the funding is to drive forward the development and application of Artificial Intelligence (AI) to the benefit of society. The main focus is on the priority areas of the alliance, preventive health and circular society. The projects are innovative and interdisciplinary.
The alliance offers researchers and lecturers the opportunity to explore new interdisciplinary connections between the partner institutions. This call stimulates the development of research projects that will contribute to the innovative development and application of trustworthy AI. The money will be invested in initiatives strengthening the transition to a healthy and sustainable society.
Awarded projects
- SMASH: Automated segmentation of stomach contents in MRI images with the use of deep learning
- PROMISE: PRediction of Outcome with Machine Learning in Infants: a Synergistic Exploration
- Trustworthy AI for MRI safety and conductivity mapping as novel cancer biomarker
- AI@HomeCare: Preventing adverse patient outcomes in home care nursing through predictive proces >> to project
- Savor the Flavor: towards a better understanding of the link between sensory profiles of older adults with olfactory dysfunction and diet quality, to prevent non-communicable diseases >> to project
- TakePart: An AI-driven Digital Twin Platform for Circular Green Infrastructure
- Learning-based Design and Control of Green energy System for Vertical Farm Production
SMASH: Automated segmentation of stomach contents in MRI images with the use of deep learning
The project objective is to build and validate an AI-based software tool that can perform automatic segmentation of the stomach contents on abdominal MRI images. This AI solution contributes to more knowledge on gastric digestion and thereby the development of optimized foods for target groups such as elderly, athletes and infants. It also sets the stage for better characterization of gastrointestinal physiology and disorders involving altered gastric emptying rate and gastric juice production. Research team: Maureen van Eijnatten (TU/e), Paul Smeets (WUR), Elise van Eijnatten, (WUR), Guido Camps (WUR), Duco Veen (UU), Wilbert Bartels (UMC Utrecht), Jan Monkelbaan (UMC Utrecht)
PROMISE: PRediction of Outcome with Machine Learning in Infants: a Synergistic Exploration
At the neonatal intensive care unit of UMC Utrecht, up to 80 newborns per year are born extremely preterm (<28 weeks of gestation), with high risk for brain damage and long-term consequences such as behavioral impairment. There is a need for early personalized prognosis of behavioral outcomes for the individual patient. This research project aims to develop a prediction model for preterm born infants at high risk of behavioural impairment. And to ensure that this is conform to the state-of-the-art values of trustworthy AI. Once validated, this prediction model will be made accessible to a larger network of clinicians through a web-based service. Research team: Mykola Pechenizkiy (TU/e), Rick Bezemer (TU/e), Clara Belzer (WUR), Chantal Kemner (UU), Albert Salah (UU), Maria Luisa Tataranno (UMC Utrecht), Manon Benders (UMC Utrecht), Bauke van der Velde (UMC Utrecht), Bob Walraad (UMC Utrecht)
Trustworthy AI for MRI safety and conductivity mapping as novel cancer biomarker
Quantitative MRI (qMRI) techniques are the foundation of a paradigm change in MRI imaging, as they provide objective tissue parameters to be used as imaging biomarkers. This projects focusses on tissue conductivity, a property of biological tissues measurable with MRI. This property has the potential to distinguish healthy tissue from pathological tissue (for example cancerous tissues) and may allow non-invasive assessment of cellular viability in response to therapy much earlier than clinical, qualitative MRI methods. This conductivity mapping helps with better and objective characterization of pathologies. Furthermore it results in shorter, thus cheaper MRI examinations; as few qMRI images may be sufficient in diagnostic settings instead of long qualitative MRI exams. It also facilitates precise and personalized treatments. Research team: Alexander Raaijmakers (TU/e), Riccardo Levato (UU), Stefano Mandija (UMC Utrecht), Nico van den Berg (UMC Utrecht), Ettore Flavio Meliado (UMC Utrecht)
AI@HomeCare: Preventing adverse patient outcomes in home care nursing through predictive process
The global shortage of nursing staff poses a major threat to health care. Indeed, nursing, especially in the home setting, offers a model of person-centered, preventive and coordinated care that can reduce hospitalizations and help people stay in their own homes. The application of AI and data science can fill some of this gap in the area of early detection of adverse events, such as falls. However, little research in the field of AI and data science is particularly focused on nursing care. In this project a multidisciplinary team of experts will explore how nursing knowledge can be incorporated into a high-quality prediction model. Research team: Boudewijn van Dongen (TU/e), Renata Medeiros de Carvalho (TU/e), Iris Beerepoot (UU), Lisette Schoonhoven (UMC Utrecht), Nienke Bleijenberg (UMC Utrecht) To projectpage
Savor the Flavor: towards a better understanding of the link between sensory profiles of older adults with olfactory dysfunction and diet quality, to prevent non-communicable diseases
Olfactory dysfunction (OD) is a temporary condition for many COVID-19 patients, but about 3-22% of the population experience chronic (long-term) OD. Among older adults, that percentage even rises to 75% and is related to the aging process. OD can lead to reduced appetite and suboptimal food choices, and ultimately, for older adults, to ‘anorexia of aging’. In this project, a team of experts investigates the relationship between the sensory profile of older adults with OD and their dietary behaviors, and how innovative tools can stimulate improvement of diet quality and prevent noncommunicable diseases. Research team: Yuan Lu (TU/e), Desiree Lucassen (WUR), Parvaneh Parvin (WUR), Elbrich Postma (WUR), Hanna Hauptman (UU), Digna Kamalski (UMC Utrecht) To projectpage
TakePart: An AI-driven Digital Twin Platform for Circular Green Infrastructure
Rapid urbanization has led to several sustainable challenges including the degradation of ecosystems and urban-rural inequality around the world. Climate change and grey infrastructure development also make urban areas more vulnerable to extreme weather events such as floods, droughts and heat waves that cause social, economic and ecological damage. There is a growing consensus on using nature-based solutions, especially Green Infrastructure to tackle these challenges and enable the transition to a circular society. Rain gardens, permeable pavements, green roofs, infiltration planters, trees, tree boxes, and rainwater harvesting systems are some examples. The recent development of Digital Twin and Artificial Intelligence provides new opportunities to address these problems. Research team: Qi Han (TU/e), Hendrik Baier (TU/e), Alexander Klippel (WUR), Marian Stuiver (WUR), Pınar Yolum (UU), Yanliu Lin (UU)
Learning-based Design and Control of Green energy System for Vertical Farm Production
Vertical farm, the practice of growing crops indoors in vertically stacked layers in a highly controlled environment, represents a solution to produce high-quality fresh vegetables anytime and anywhere, especially in urbanized areas where arable land is scarce. This comes at the cost of not benefitting from natural light. Artificial light results in high energy usage of VF associated costs and when fossil fuels are used in high emissions of carbon dioxide a key factor in climate change. Introducing green energy like solar panels, wind turbines or hydrogen batteries as alternative energy sources for VF is a sustainable solution. In this project, necessary preliminary research on these questions is conducted through developing a prototype of VF with green energy system. Research team: Phuong Nguyen (TU/e), Eldert van Henten (WUR), Congcong Sun (WUR), Frank Kempkes (WUR), Shihan Wang (UU)