PhD Candidate in Explainable AI and Foundation Models for CT Imaging

PhD Candidate in Explainable AI and Foundation Models for CT Imaging

• Our goal: To develop novel AI methods for explainability in medical imaging, including diffusion-model-based approaches, and to advance foundation models for CT through model development, training, evaluation, and external validation.
• Your colleagues: You will join the Department of Precision Medicine at Maastricht University, embedded within GROW and the Faculty of Health, Medicine and Life Sciences. You will work in an interdisciplinary environment connecting artificial intelligence, medical imaging, and clinical translation.

What you do
As a PhD candidate, you will undertake a four-year doctoral research project leading to a PhD thesis. You will develop and evaluate new methods for explainable AI in medical imaging, with particular attention to the use of diffusion models for explanation and interpretation. You will also contribute to the design, training, adaptation, and external validation of foundation models for CT images.

Are you ready to set the course for the years ahead? Then we’d love to meet you.

What you bring
We’re not looking for checkboxes; we’re interested in who you are and what you bring. Do you recognize yourself in this?

You are an analytical and curious researcher with an interest in technically innovative research at the intersection of artificial intelligence, medical imaging and clinical translation. You enjoy tackling complex problems and working in an interdisciplinary and international environment, while taking ownership of your work and developing as an independent researcher. You approach research systematically and have experience developing well-structured, well-documented and reproducible research code and organising experiments in a way that enables results to be reproduced and your work to be understood and further developed by others. You are motivated to further develop as an independent researcher and successfully complete your PhD within the appointment period.

Furthermore, you bring:

• You hold, or will shortly obtain, a Master’s degree in Artificial Intelligence, Computer Science, Biomedical Engineering, Medical Image Analysis, Applied Mathematics, Data Science, or a closely related field.
• You have a solid theoretical and practical background in machine learning and deep learning, including experience developing, training and evaluating models, preferably for image analysis tasks.
• You have strong programming skills in Python, including the ability to develop and adapt code for machine-learning experiments, train and evaluate deep-learning models, and process and analyse experimental results. You have hands-on experience using a deep-learning framework, preferably PyTorch to develop and adapt code, train deep-learning models, and evaluate their performance.
• You have knowledge of, or a strong interest in, the principles of generative modelling and an interest in applying and further developing generative approaches, including diffusion models, for medical imaging.
• You have a C1 level of proficiency in written and spoken English, according to the Common European Framework of Reference for Languages (CEFR).

The following qualifications are considered advantageous:

• Experience with explainable AI, uncertainty estimation, trustworthy AI, or model interpretability.
• Experience with generative models, particularly diffusion models.
• Experience with foundation models, self-supervised learning, representation learning, or large-scale pretraining.
• Experience with medical imaging, particularly CT, and associated image formats or processing workflows.
• Familiarity with DICOM, NIfTI, image registration, segmentation, or radiological image-analysis pipelines.
• Experience with high-performance computing, distributed training, or working with large imaging datasets.
• Experience evaluating models on heterogeneous or multi-centre data.
• A master’s thesis, publication, research internship, or open-source project relevant to the position.

PhD Candidate in Supramolecular Hydrogels for Biomaterials and Tissue Engineering

PhD Candidate in Supramolecular Hydrogels for Biomaterials and Tissue Engineering

• Our goal: To develop dynamic, molecularly designed biomaterials for applications including 3D cell culture and bioprinting. The project will combine molecular self-assembly with covalent reinforcement to create biomimetic hydrogels whose mechanics, dynamics, and functionality can be controlled in space and time.
• Your colleagues: You will join the “BioMatt” group of Dr. Matthew Baker (https://merlninstitute.com/discover-merln/departments-and-groups/research-groups/biomatt-polymeric-biomaterials). The BioMatt group is part of MERLN’s Department of Instructive Biomaterials Engineering (IBE), which develops biomaterials that actively interact with and guide biological systems. Within this environment, BioMatt combines molecular and polymer design with cell biology and tissue engineering to create dynamic materials for biomedical applications. Working at MERLN means you will join an international network of researchers from ~25 nationalities spanning multiple disciplines. We are a collaborative and interdisciplinary group with diverse expertise, including biomaterials, chemistry, tissue engineering, microfabrication, and cell biology. We work in newly renovated laboratory facilities with state-of-the-art equipment. We have a long history as leaders in the field of tissue engineering and are particularly well-known for our orientation towards translational research.

What you do
This position focuses on the synthesis and characterization of novel supramolecular materials with tunable properties for biomedical applications. The successful candidate will:

• Develop new synthetic routes for supramolecular polymers.
• Characterize supramolecular polymer structure-property relationships using advanced analytical techniques.
• Engineer dynamic hydrogel systems with tailorable mechanical and chemical properties.
• Design hydrogels and formulations to create injectable, 3D printable, and patternable materials.
  The supramolecular materials developed will ultimately be applied to create controllable 3D environments for tissue engineering applications ranging from vascularization and osteochondral regeneration to living materials with microbial components.

Are you ready to set the course for the years ahead? Then we’d love to meet you.

Scientific Background
Supramolecular materials have incredible potential for recreating life-like materials to interface with living cells, yet their weak mechanical properties and difficulty in controlling dynamics and functionalization limit their use. Our research explores how to tune the dynamics and assembly of supramolecular hydrogels by combining dynamic-covalent bond formation with supramolecular chemistry principles. We have shown significant breakthroughs in reinforcing supramolecular polymers to create tough materials that allow for 3D fabrication of tissue constructs. Currently, the impact of molecular structure, processing conditions, and reaction mechanisms on natural and synthetic supramolecular scaffolds is poorly understood. We are looking to expand our fundamental understanding of these materials through polymer synthesis and characterization.

This work will be a close collaboration within the framework of an ERC Consolidator project (SupraValent), embedded within a multidisciplinary team (BioMatt Group). The fully funded 4-year PhD position provides an opportunity to develop expertise in advanced supramolecular/polymer chemistry while contributing to biomedical innovation.

Key references:

• Francis LC Morgan, Ivo AO Beeren, Jurica Bauer, Lorenzo Moroni, Matthew B Baker. JACS, 2024, 146, 27499–27516. https://doi.org/10.1021/jacs.4c08099
• Shahzad Hafeez, Monize Caiado Decarli, Agustina Aldana, Mahsa Ebrahimi, Floor AA Ruiter, Hans Duimel, Clemens van Blitterswijk, Louis M Pitet, Lorenzo Moroni, Matthew B Baker. Advanced Materials, 2023, 35, 2301242. https://doi.org/10.1002/adma.202301242
• Floor AA Ruiter, Francis LC Morgan, Nadia Roumans, Anika Schumacher, Gisela G Slaats, Lorenzo Moroni, Vanessa LS LaPointe, Matthew B Baker. Advanced Science, 2022, 9, 2200543. https://doi.org/10.1002/advs.202200543

What you bring
We are interested in the combination of experience, motivation, and perspective you would bring.

The ideal candidate has a strong foundation in organic or polymer chemistry and is motivated to connect molecular design with material function. Prior experience in biomaterials is very welcome but not required; more important is confidence in experimental materials and synthesis, careful data interpretation, and an interest in collaborative work at the chemistry–bioengineering interface. You enjoy working in an open, collaborative, and interdisciplinary environment.

Furthermore, you bring:

• MSc (or equivalent) in Organic/Polymer Chemistry, Materials Science, Chemical Engineering, or related field. Candidates with an equivalent research qualification from an educational system without a separate Master’s degree are also encouraged to apply; eligibility will be assessed individually.
• Demonstrated knowledge and/or hands-on experience in organic and/or polymer synthesis, acquired through an MSc thesis, extended research project, advanced coursework, or relevant internship. You should have experience with multi-step synthetic under supervision, standard purification techniques (e.g., column chromatography, precipitation, extraction), and maintaining structured laboratory records with clear reporting of experimental results.
• Demonstrated knowledge of or hands-on experience with polymer and small-molecule characterization methods, such as NMR, GPC, rheology, or mechanical testing. This experience may have been gained through an MSc thesis, extended research project, advanced coursework, or relevant internship. While not required, the ability to independently operate at least one of these techniques, interpret and report experimental data, and relate characterization results to polymer structure and material properties is highly desirable.
• Interest in applying supramolecular and polymer chemistry to bioengineering and soft matter applications, with demonstrated exposure to biomaterials, hydrogels, self-assembly systems, or structure–property relationships in polymeric materials.
• Experience with characterization of self-assembled or dynamic systems, such as UV-Vis spectroscopy, fluorescence spectroscopy, DLS, or (cryo-)electron microscopy, and/or analysis of reaction or binding kinetics, is considered an advantage.
• Excellent command of scientific English (minimum CEFR level C1), with strong proficiency in reading, writing, listening, and speaking, as English is the working language of the group.

Availability to start the position on short notice is highly desirable; however, the start date remains flexible for highly qualified applicants.

PhD Candidate in NeuroAI for Auditory Neuroscience

PhD Candidate in NeuroAI for Auditory Neuroscience

• Our goal: Understand how the human brain recognizes and interprets complex natural auditory scenes and to uncover computational principles shared by biological and artificial systems. The PhD project is part of NASCE (Natural Auditory SCEnes in Humans and Machines), an ERC Synergy project conducted in collaboration with Dr. Bruno Giordano (CNRS, Marseille). NASCE brings together cognitive neuroscience, advanced neuroimaging, behavioural research, and artificial intelligence to investigate natural sound perception in humans and machines.
• Your colleagues: You will join the AuditoRy Cognition in Humans and MachInEs (ARCHIE) lab, an interdisciplinary and international research team led by Prof. Elia Formisano at the Faculty of Psychology and Neuroscience, Maastricht University. You will work closely with researchers with complementary expertise in auditory neuroscience, neuroimaging, and AI/NeuroAI.

In this role you will bridge human neuroimaging and computational modelling. You will collect and analyse neuroimaging data (7 Tesla fMRI) acquired during natural sound perception and use state-of-the-art AI models to investigate how the human brain transforms acoustic information into meaningful representations. By comparing representations in the brain and artificial neural networks, you will contribute to a better understanding of the computational principles underlying auditory intelligence in humans and machines.

What you do
As a PhD candidate, you will:

• Acquire and analyse human neuroimaging data, with a primary focus on high-field fMRI of natural sound perception.
• Develop and apply AI/NeuroAI models, including deep neural networks, to model auditory processing.
• Relate representations learned by AI models to behavioural and brain data using multivariate and representational modelling approaches.
• Contribute to the design and execution of neuroimaging and behavioural experiments.
• Develop your expertise across neuroscience and AI, with intensive training in the field that is less familiar to you at the start of the PhD, while collaborating with researchers across the interdisciplinary NASCE consortium.
• Present your findings at international conferences and publish them in peer-reviewed journals.
• Contribute to open and reproducible research through well-documented analysis pipelines, models and data products.
• Contribute up to 0.1 FTE to teaching or supervision at Maastricht University.

Are you excited to work at the interface of neuroscience and artificial intelligence while developing expertise across both fields? Then we’d love to meet you.

What you bring
We’re not looking for checkboxes; we’re interested in who you are and what you bring. Do you recognize yourself in this?

We are looking for a curious and analytically minded researcher who is driven to deepen our understanding of both biological and artificial intelligence. You are comfortable working independently, while also valuing collaboration and contributing actively within an interdisciplinary and international team. With a proactive and growth-oriented mindset, you are motivated to continuously develop new skills, expand your expertise, and explore new areas of knowledge.

Furthermore:

• You hold a Master’s degree in cognitive or computational neuroscience, artificial intelligence, computer science, biomedical engineering, cogntitve sciences with a strong quantitative focus, data science, or a related field.
• You have relevant experience in at least one of the two core areas: human neuroimaging or AI/machine learning/NeuroAI. For candidates with a neuroimaging background, this may include experience with data acquisition, preprocessing, and/or analysis; experience with fMRI is preferred, but candidates with experience in other neuroimaging techniques are also encouraged to apply. For candidates with an AI background, we expect practical experience in implementing, training, and evaluating machine-learning or deep-learning models. You are not expected to already be an expert in both areas,
• You are genuinely motivated to develop expertise in the complementary field: If your background is in neuroimaging, you are willing to develop your expertise in AI and deep learning. If your background is in AI, you are eager to develop your knowledge of cognitive neuroscience, experimental design, and fMRI analysis.
• You have a strong quantitative background, including a solid understanding of statistics and data analysis; prior experience with multivariate or computational modelling methods is an advantage. You have good programming skills, preferably in Python, and are able to independently write and adapt code for data processing, analysis, and visualization. Experience with deep learning and frameworks such as PyTorch, TensorFlow, or JAX is an advantage.
• You have strong English language skills, with proficiency at a minimum of C1 level (CEFR).

Promovendus - Medische beeldanalyse en AI in hemostase onderzoek

Promovendus medische beeldanalyse en AI in hemostase onderzoek

• Ons doel: het ontwikkelen van een geautomatiseerde, high-throughput analyse van flowkamerbeelden met behulp van kunstmatige intelligentie. Hiermee willen we de analyse van trombusvorming versnellen, standaardiseren en verder verbeteren voor zowel wetenschappelijk onderzoek als toekomstige klinische toepassingen.
• Jouw collega’s: je wordt onderdeel van de afdeling Biochemie van de Faculty of Health, Medicine and Life Sciences (FHML), het Cardiovascular Research Institute Maastricht (CARIM) en werkt nauw samen met het Centraal Diagnostisch Laboratorium (CDL) van het Maastricht UMC+. Je maakt deel uit van een multidisciplinair team bestaande uit onderzoekers, analisten, klinisch chemici, hematologen, data scientists en ICT-specialisten.

Je vervult een centrale rol in de ontwikkeling van AI-methoden voor de automatische analyse van beelden afkomstig uit de Maastricht Flowkamer. Dit vormt de kern van je onderzoek. De Maastricht Flowkamer is een technologie waarmee trombusvorming onder (patho)fysiologische stromingssnelheden in real-time wordt gevisualiseerd en vervolgens geanalyseerd. Benieuwd hoe deze techniek werkt? Bekijk de korte video "Let it flow: what flowing blood is telling us about blood clotting": https://www.youtube.com/watch?v=m22Mw7HQ7tA. Daarnaast pas je vergelijkbare AI- en datagedreven benaderingen ook toe op andere biomedische datasets, en draagt zo bij aan een breder onderzoeksprogramma dat methodologische ontwikkeling, medicatiestudies en klinische vertaling omvat, evenals aan voortgangsrapportages en wetenschappelijke publicaties.

Wat jij doet

• Je analyseert de huidige (semi-)geautomatiseerde beeld- en data-analyse van de Maastricht Flowkamer en identificeert mogelijkheden voor verbetering.
• Je ontwikkelt AI-modellen voor de automatische segmentatie, kwantificatie en classificatie van flowkamerbeelden, met deep learning- en self-supervised technieken die ook ongelabelde data benutten.
• Je automatiseert de verwerking en analyse van grote datasets afkomstig uit flowkamerexperimenten
• Je valideert de ontwikkelde AI-modellen en vertaalt deze naar een robuuste high-throughput analysemethode, die aansluit bij klinische vraagstukken binnen de hematologie, zoals de diagnostiek van onbegrepen bloedings- en stollingsafwijkingen.
• Afhankelijk van de voortgang van het project pas je vergelijkbare data science- en AI-methoden toe op andere complexe laboratoriumdatasets op gebied van hemostase en trombose.
• Je werkt nauw samen met laboratoriumonderzoekers, clinici en data scientists om AI-oplossingen optimaal aan te laten sluiten bij klinische en wetenschappelijke vragen.
• Je presenteert onderzoeksresultaten op (inter)nationale congressen en publiceert in internationale wetenschappelijke tijdschriften.

Wat jij meebrengt
Bij de Universiteit Maastricht geloven we dat talent zich op verschillende manieren ontwikkelt. We zoeken een nieuwsgierige onderzoeker met een sterke affiniteit voor AI, medische (beeld)analyse en data science, die graag bruggen slaat tussen computationele methoden en klinische toepassingen. Herken jij jezelf hierin?

• Je hebt een afgeronde masteropleiding, bij voorkeur in een biomedisch-technologische, (bio)medische of een aanverwante richting, zoals geneeskunde, systeembiologie, klinische gezondheidswetenschappen, (clinical) data science of bio-informatica.
• Je hebt aantoonbare ervaring met data-analyse en programmeren (bijvoorbeeld Python of R), bijvoorbeeld via projecten, stages of werkervaring waarin je datasets hebt geanalyseerd. Ervaring met machine learning of deep learning (bijv. met scikit-learn, TensorFlow of PyTorch) en/of (medische) beeldanalyse (zoals segmentatie of classificatie) is een sterke pré.
• Je hebt interesse in hemostase, trombose en laboratoriumgeneeskunde, en begrijpt dat succesvolle AI-oplossingen beginnen met een goed begrip van het onderliggende klinische probleem. Eerdere ervaring op deze gebieden is niet vereist, maar je dient gemotiveerd te zijn om de benodigde biologische en klinische kennis te ontwikkelen.
• Je beschikt over uitstekende communicatieve vaardigheden in het Engels, mondeling én schriftelijk. Beheersing van het Nederlands is een sterke pré.
• Je bent zelfstandig, nieuwsgierig en proactief en werkt graag samen binnen een multidisciplinair team van onderzoekers, klinisch chemici, medisch specialisten, ICT-professionals en andere zorgprofessionals.

Deze functie betreft in de basis een promotieplaats. Tegelijkertijd staan wij open voor sterke kandidaten met een relevante AI-/data science-achtergrond die niet per se een promotietraject willen volgen, zoals ervaren data scientists of AI engineers. In dat geval kan de invulling van de rol worden besproken als een onderzoeksgerichte functie binnen hetzelfde project.

PhD candidate - Medical image analysis and AI in hemostasis reseach

PhD candidate – Medical image analysis and AI in hemostasis reseach

• Our goal: to develop an automated, high-throughput analysis pipeline for flow chamber images using artificial intelligence. By doing so, we aim to accelerate, standardize, and further improve the analysis of thrombus formation under flow conditions for both scientific research and future clinical applications. The generated data will be used to study clinically relevant hemostatic phenotypes, treatment effects, and the potential value of flow chamber testing in patients with bleeding disorders.
• Your colleagues: you will become part of the Department of Biochemistry within the Faculty of Health, Medicine and Life Sciences (FHML), the Cardiovascular Research Institute Maastricht (CARIM), and work closely with the Central Diagnostic Laboratory (CDL) of Maastricht UMC+. You will join a multidisciplinary team of researchers, laboratory analysts, clinical chemists, hematologists, data scientists, and IT specialists.

You will play a central role in developing AI methods for the automated analysis of images generated by the Maastricht Flow Chamber. This will be the primary focus of your research. The Maastricht Flow Chamber is a technology that enables real-time visualization and analysis of thrombus formation under physiological flow conditions. Curious to learn more about this technique? Watch the short video, "Let it flow: what flowing blood is telling us about blood clotting":
https://www.youtube.com/watch?v=m22Mw7HQ7tA. You will also apply similar AI- and data-driven approaches to other biomedical datasets, contributing to a broader research programme covering methodological development, medication studies, and clinical translation, as well as to progress reports and scientific publications.

What you do

• Analyze the current (semi-)automated image and data analysis workflow of the Maastricht Flow Chamber and identify opportunities for improvement.
• Develop AI models for the automated segmentation, quantification, and classification of flow chamber images, using deep learning and self-supervised techniques that also leverage unlabeled data.
• Automate the processing and analysis of large datasets generated from flow chamber experiments.
• Validate the developed AI models and translate them into a robust high-throughput analysis method that aligns with clinical questions in hematology, such as the diagnosis of unexplained bleeding and clotting disorders.
• Depending on the progress of the project, apply similar data science and AI methods to other complex laboratory datasets in the field of hemostasis and thrombosis.
• Collaborate closely with laboratory researchers, clinicians, and data scientists to integrate imaging results with clinical and laboratory data and help translate these findings into clinically relevant conclusions.
• Present your findings at national and international conferences and publish your work in leading international scientific journals.

What you bring
At Maastricht University, we believe that talent comes in many forms. We are looking for a curious researcher with a strong affinity for artificial intelligence, medical image analysis, and data science, who enjoys bridging computational methods and clinical applications. Do you recognize yourself in the following?

• You hold a completed Master's degree, preferably in biomedical engineering, biomedical sciences, medicine, systems biology, clinical health sciences, (clinical) data science, bioinformatics, or a related discipline.
• You have a demonstrated affinity for data analysis and programming (e.g. Python or R), e.g. via projects, internships or other work experience where you’ve analysed datasets. Experience with machine learning, deep learning (e.g. scikit-learn, TensorFlow or PyTorch), or medical image analysis (e.g. segmentation or classification) is considered a strong advantage.
• You have a clear interest in hemostasis, thrombosis, and laboratory medicine, and understand that successful AI solutions start with a thorough understanding of the underlying clinical problem. Prior experience in these fields is not required, but you should be motivated to develop the necessary biological and clinical understanding.
• You possess excellent communication skills in English, written and spoken. Proficiency in Dutch is a strong advantage.
• You are independent, curious, and proactive, while also enjoying working in multidisciplinary teams with researchers, clinical chemists, medical specialists, IT professionals, and other healthcare professionals.

This position is essentially a PhD position. At the same time, we are open to strong candidates with a relevant AI/data science background who are not necessarily looking to pursue a PhD track, such as experienced data scientists or AI engineers. In that case, the role can be discussed as a research-oriented position within the same project.