Current PhD vacancies

The gut microbiome is crucially important for human health. It is capable to produce anti-inflammatory short-chain fatty acids (SCFAs) that balance our immune responses at systemic level. In this project, we aim to uncover the pillars of high-performing SCFA producer microbiota, model both natural and synthetic gut communities, and – with help of these models - engineer even more effective microbial functions. We will use machine learning and network science to identify the most efficient consortia and metabolic community models to identify SCFA production bottlenecks.

Join us for a fully funded 4-year computational PhD position to investigate how to boost the health benefits of our gut microbiota (WWTF, EnhanceFun).

You'll conduct computational modeling at the Medical University of Vienna, be part of the AIML (artificial intelligence and machine learning) student network on campus and partner up with a second PhD candidate, who covers the experimental side of the study (University of Vienna, David Berry Lab).

We expect that this combination of microbiota modeling and engineering will open new avenues for treatment and prevention of inflammatory diseases and will teach us how to control and manage bacteria to improve human health.

The Widder Lab is part of the Research Division Infection Biology/Department of Medicine I of the Medical University of Vienna, located in one of the most livable cities worldwide. You will be embedded in an international team of like- and open-minded colleagues with a great passion for science and microbiome research. The diverse aspects of the project will allow you to gain experience in a variety of exciting (modeling) technologies and scientific topics of high clinical and societal importance.

A common roadblock in AI based glioma research and a cross-cutting issue in many AI and healthcare developments is the small sample size. The aim of this project is to develop strategies for the curse of dimensionality often faced in machine learning (ML) applied to medical imaging, i.e. having feature-rich data but a small amount of training data. In this project different strategies will be developed to increase the quantity of training data, e.g. diagnostic and follow up MRI, dynamic FET-PET/MR data, PET/CT scans as well as preclinical imaging data of glioma. Techniques will include image transformations, the generation of synthetic images with different architectures of General Adversarial Networks (GANs) and stable-diffusion based methods using a variety of on-site as well as publicly available datasets. A goal is also to have a better understanding of the requirements for the quality and quantity of synthetic medical imaging data in order to be beneficial for deep learning in glioma imaging. We will also gain insights about domain adaptation between different medical imaging tasks (e.g. MR <-> PET, preclinical <-> clinical data). Finally, we will define best practice data+ML-workflows for glioma data, depending on imaging modality and clinical questions.

Embedment of the PhD Project

This PhD position is part of the CONGLIOMERATE project, which aims to improve glioma diagnosis by integrating histopathology, multiparametric MRI, PET, and clinical data using AI methodologies. The project is one of five connected PhD positions, supervised by experts in medical imaging, AI, and clinical research from the Medical University of Vienna and the University of Applied Sciences Technikum Wien.

The selected candidate will work within an interdisciplinary and international research team, with opportunities for collaboration through regular retreats, joint courses, and team-building activities. Additional training includes clinical observation days, presentations at international conferences, and funding for research visits to other institutions. This specific project will be carried out at the Competence Center for Artificial Intelligence & Data Analytics (AIDA) of the University of Applied Sciences Technikum Wien.

Skills and Expertise Gained Through the PhD

• Medical Imaging Expertise – In-depth knowledge of PET and MRI technology, including image acquisition, reconstruction, and analysis.
• Nuclear Medicine and Tumor Biology – Understanding of tracer pharmacokinetics, radiopharmaceuticals, and their applications in oncology and other medical fields.
• AI and Data Analysis for Imaging – Experience with machine learning, deep learning, and other AI techniques applied to medical image processing and data interpretation.
• Interdisciplinary and Intercultural Communication – Experience working in multidisciplinary teams with experts from medicine, physics, engineering, and computer science, often in an international research environment, requiring strong scientific and technical communication skills in multiple languages.
• Research Methodology and Data Interpretation – Experience in designing and conducting experiments, handling large datasets, and drawing meaningful conclusions from research findings.
• Project Management and Problem-Solving – Skills in managing long-term projects, developing research strategies, and addressing complex technical challenges.
• Scientific Communication and Writing – Ability to present research findings clearly through scientific publications, conference presentations, and technical reports.

This combination of technical expertise, analytical skills, and strong communication abilities prepares PhD graduates for careers in academia, industry, and healthcare innovation.

The aim of this study is to assess treatment-specific responses on tumor characteristics using multimodal PET/MR imaging in preclinical glioma models. This research seeks to enhance our understanding of the interrelationships between the biological background of glioma and the imaging data obtained through MRI and PET, bridging clinical, pre-clinical, and basic research domains. To achieve this, the candidate will first evaluate [18F]FET uptake kinetics in glioma cells in vitro, both before and after therapy. Next, we will generate orthotopic glioma models by injecting glioma cells into the brains of male and female mice. Simultaneously, we will apply [18F]FET-PET with multiparametric MRI to study tumor anatomy, microvasculature, cellularity, hypoxia, and metabolism. [18F]FET-PET images will be analyzed by the candidate using kinetic modeling based on insights from human data analysis. The candidate will explore the relationships between MR parameters and [18F]FET-PET metrics, focusing on aspects such as changes in the microvasculature and the [18F]FET influx rate constant. Subsequently, mice will be treated with anti-cancer drugs and the candidate will evaluate treatment-specific responses. At the end of the study histology images will be matched with PET/MR images to provide a comprehensive understanding of the tumor. Ultimately, this study aims to provide new insights into complex tumor characteristics and their interplay through simultaneous PET/MRI. 

Embedment of the PhD Project

This PhD position is part of the CONGLIOMERATE project, which aims to improve glioma diagnosis by integrating histopathology, multiparametric MRI, PET, and clinical data using AI methodologies. The project is one of five connected PhD positions, supervised by experts in medical imaging, AI, and clinical research from the Medical University of Vienna and the University of Applied Sciences Technikum Wien.

The selected candidate will work within an interdisciplinary and international research team, with opportunities for collaboration through regular retreats, joint courses, and team-building activities. Additional training includes clinical observation days, presentations at international conferences, and funding for research visits to other institutions. This specific project will be carried out at the Center for Medical Physics and Biomedical Engineering, Medical University of Vienna.

Skills and Expertise Gained Through the PhD

• Medical Imaging Expertise – Advanced knowledge of PET and MRI technology, including imaging principles, acquisition, reconstruction, and analysis.
• Preclinical Imaging and Tumor Biology – Understanding of preclinical imaging procedures, disease modeling, and tumor biology in oncology research.
• Interdisciplinary and Intercultural Collaboration – Experience working in multidisciplinary teams across medicine, physics, engineering, and AI, often in an international research environment, requiring strong communication skills.
• Research Methodology and Data Interpretation – Expertise in experimental design, data acquisition, statistical analysis, and interpretation of research findings.
• Project Management and Problem-Solving – Ability to plan and execute long-term research projects, develop innovative solutions, and address complex technical challenges.
• Scientific Communication and Writing – Skills in publishing research, presenting findings at international conferences, and writing technical reports.

This combination of specialized knowledge, analytical skills, and interdisciplinary experience prepares PhD graduates for careers in academic research, industry, and healthcare innovation.

One of the most pressing challenges in the follow up of glioma patients after therapy is pseudoprogression which mimics true progression in the imaging of glioma with their differentiation having a great impact on the further disease management. This project aims to develop an Machine Learning (ML)-based framework to differentiate true progression from pseudoprogression in treatment response monitoring using multi-modality imaging data, i.e. dynamic FET-PET and MR as well as data from the initial diagnostic assessment. The database consists of simultaneously acquired dynamic [18F]FET PET/MR data, separately acquired MR and PET/CT data from follow up scans, plus data from the initial diagnostic assessment as well as publicly available datasets. Multi-modality data preparation will include developing workflows for auto-registration, tumor segmentation and feature extraction algorithms. The ML-framework shall identify the underlying subvisual tumor fingerprint encoded in the functional imaging information and use attention-based fusion modules to evaluate performance alongside interpretability. The goal is to provide a clinically relevant ML framework to differentiate pseudo progression from true progression embedded in an automated workflow to reduce time burden in preparing multi-modality data for ML tasks. 

Embedment of the PhD Project

This PhD position is part of the CONGLIOMERATE project, which aims to improve glioma diagnosis by integrating histopathology, multiparametric MRI, PET, and clinical data using AI methodologies. The project is one of five connected PhD positions, supervised by experts in medical imaging, AI, and clinical research from the Medical University of Vienna and the University of Applied Sciences Technikum Wien.

The selected candidate will work within an interdisciplinary and international research team, with opportunities for collaboration through regular retreats, joint courses, and team-building activities. Additional training includes clinical observation days, presentations at international conferences, and funding for research visits to other institutions. This specific project will be carried out at the Competence Center for Artificial Intelligence & Data Analytics (AIDA) of the University of Applied Sciences Technikum Wien.

Skills and Expertise Gained Through the PhD

• Medical Imaging Expertise – In-depth knowledge of PET and MRI technology, including image acquisition, reconstruction, and analysis.
• Nuclear Medicine and Tumor Biology – Understanding of tracer pharmacokinetics, radiopharmaceuticals, and their applications in oncology and other medical fields.
• AI and Data Analysis for Imaging – Experience with machine learning, deep learning, and other AI techniques applied to medical image processing and data interpretation.
• Interdisciplinary and Intercultural Communication – Experience working in multidisciplinary teams with experts from medicine, physics, engineering, and computer science, often in an international research environment, requiring strong scientific and technical communication skills.
• Research Methodology and Data Interpretation – Experience in designing and conducting experiments, handling large datasets, and drawing meaningful conclusions from research findings.
• Project Management and Problem-Solving – Skills in managing long-term projects, developing research strategies, and addressing complex technical challenges.
• Scientific Communication and Writing – Ability to present research findings clearly through scientific publications, conference presentations, and technical reports.

This combination of technical expertise, analytical skills, and strong communication abilities prepares PhD graduates for careers in academia, industry, and healthcare innovation.

Adult-type diffuse glioma comprises multiple tumor types sharing diffuse infiltrative growth with destruction of large parts of the brain, and poor patient outcome. Their diagnosis and prognosis is based on the systematic integration of magnetic resonance imaging,  histological imaging features and molecular markers including DNA sequence, structural alterations and methylation patterns.

In this PhD project you will  develop novel machine learning methods (specifically representation learning methods) to link these modalities for individual diagnosis, and prognosis. We want to understand how they together predict the future of individual patients, and what their associations can tell us about the molecular mechanisms, that shape the phenotype, its change over time, and the possible response to treatment.

Techniques you will learn: As part of the PhD you will learn to develop novel cutting-edge methods in the area of machine learning, image- and molecular data analysis. You will become proficient in working in interdisciplinary teams, and understand state of the art approaches in sequencing- and molecular- data analysis, and medical image analysis.

You will  be part of a network: You will be member of the CIR Lab, and the newly founded Comprehensive Center of AI in Medicine (https://caim.meduniwien.ac.at). This will enable you to interact with a vibrant community of ML researchers across different medical fields. Your position is funded by the Austrian Science Fund (FWF) as part of a multi-disciplinary FWF funded doc.fund.connect program, and you will join together with 4 other students, enabling close interaction and joint work during your PhD studies. 

Glioma encompasses a wide range of brain tumors with different levels of aggressiveness. MRI is commonly used for glioma diagnosis but has limitations, particularly for low-grade gliomas and recurrence prediction. FET PET with the amino acid tracer 18F-fluoroethyltyrosine (FET) provides functional imaging to address these limitations. This project aims to develop an automatic pixel-wise kinetic modeling tool for dynamic FET PET to improve the diagnosis and follow-up of gliomas. To achieve this, the candidate will develope an AI-assisted tool that predicts personalized input functions based on factors such as age, gender, and size. Further, the candidate will develop an automatic processing pipeline for pixel wise kinetic modelling of dynamic FET PET/MRI data. The tool’s performance will be assessed and validated using existing PET/MRI and PET/CT datasets, along with histopathological data. Further, the project will explore the relationships between kinetic parameters and tumor characteristics observable through MRI. The final goal is to develope new evaluation tools for assessing glioma and improving the understanding of how FET uptake correlates with MRI-based tumor assessments, ultimately enhancing glioma diagnosis and monitoring.

Embedment of the PhD project

This PhD position is part of the CONGLIOMERATE project, which aims to improve glioma diagnosis by integrating histopathology, multiparametric MRI, PET, and clinical data using AI methodologies. The  PhD project is one of five connected PhD positions, supervised by experts in medical imaging, AI, and clinical research from the Medical University of Vienna and the University of Applied Sciences Technikum Wien.

The selected candidate will work within an interdisciplinary and international research team, with opportunities for collaboration through regular retreats, joint courses, and team-building activities. Additional training includes clinical observation days, presentations at international conferences, and funding for research visits to other institutions. This specific project will be carried out at the Center for Medical Physics and Biomedical Engineering, Medical University of Vienna.

Skills and Expertise Gained Through the PhD

• Medical Imaging Expertise – In-depth knowledge of PET and MRI technology, including image acquisition, reconstruction, and analysis.
• Nuclear Medicine and Tumor Biology – Understanding of tracer pharmacokinetics, radiopharmaceuticals, and their applications in oncology and other medical fields.
• AI and Data Analysis for Imaging – Experience with machine learning, deep learning, and other AI techniques applied to medical image processing and data interpretation.
• Interdisciplinary and Intercultural Communication – Experience working in multidisciplinary teams with experts from medicine, physics, engineering, and computer science, often in an international research environment, requiring strong scientific and technical communication skills.
• Research Methodology and Data Interpretation – Experience in designing and conducting experiments, handling large datasets, and drawing meaningful conclusions from research findings.
• Project Management and Problem-Solving – Skills in managing long-term projects, developing research strategies, and addressing complex technical challenges.
• Scientific Communication and Writing – Ability to present research findings clearly through scientific publications, conference presentations, and technical reports.

This combination of technical expertise, analytical skills, and strong communication abilities prepares PhD graduates for careers in academia, industry, and healthcare innovation.

The AI Institute / Center for Medical Data Science is recruiting an ambitious PhD student who wants to pursue a scientific career in the domain of Machine/Deep Learning for Medical Imaging with applications in eye care. The position is on automated detection and profiling of retinal disease from longitudinal multimodal imaging as part of an exciting new ERC project HealthAEye: Health-monitoring with AI-enabled smartphone-based imaging of the eye.

Research topic will span the Deep Learning areas of Foundation Models, Image Domain Adaptation, and Uncertainty Quantification. The candidate will be immersed in a multidisciplinary environment working closely with a team of AI experts, software engineers, and medical doctors in the fascinating and interdisciplinary field of AI in Retina. The output will have a real-world impact on healthcare by enabling a groundbreaking approach to home-based monitoring of patients suffering from retinal diseases, leading causes of blindness today.

The lab is embedded in a vibrant network of a rapidly growing cluster of AI researchers dedicated to addressing the challenges of AI in medicine, and benefit from the methodological expertise in machine/deep learning at the AI Institute. Throughout their PhD journey, the student will acquire in-depth knowledge and hands-on experience in advanced deep learning methodologies and statistical modelling. They will develop the skills to apply these techniques to complex and high-dimensional medical imaging datasets, gaining expertise in designing, implementing, optimizing and evaluating machine learning models for healthcare.

We offer

• Opportunity to work and do cutting-edge research in deep learning for medicine and healthcare.

• Immersion into an interdisciplinary and international research environment, and a multi-cultural lab.

• Access to large multi-modal, curated, and annotated medical imaging datasets.

• Access to a dedicated high-performance computing (HPC) cluster containing the latest generation GPUs.

• Collaboration with several renowned academic institutions, as well as partnership with imaging device companies.

Metastasis is the leading cause of cancer related deaths. Specific cancers have a prevalence to metastasize to specific organs. The underlying mechanisms for this organotropism are poorly understood. In this project you will investigate how tumor and metastatic cells and their immune-microenvironment are different in different host organs and how malignant cells remodel distant tissue niches. We are focusing on finding ways to empower the immune system to combat metastasis using cutting-edge single-cell and spatial omics technologies. We use clinically highly relevant disease models of metastasis and patient samples to investigate the complex interplays of tumor and immune cells in metastasis. The use of modern omics technologies makes it possible to discover new tumor immune cell interactions in metastasis that have not been described before. By studying these interactions between metastatic cancer cells and immune cells, we hope to uncover new insights that could lead to improved treatments for cancer patients.

Techniques you will learn: Our interdisciplinary approach combines different expertise to tackle the complex interplay of tumor and immune cells in metastasis including experimental and computational biology, as well as translational research. As a member of our team, you will receive training in both experimental and computational biology that are equally important skill sets for modern cancer researchers. You will be trained to generate and analyze single-cell and spatial omics data using the latest technologies, learn how to generate scientific hypothesis and to validate your hypothesis in appropriate advanced in vitro organoid and in vivo metastasis models systems. You will have the opportunity to present your work at conferences and collaborate with researchers from around the world, helping you grow professionally and make valuable connections in the field.

You will be part of a network: And as part of the unique SHIELD PhD program, you will have access to coordinated courses and workshops and a network of experts in immunology and cancer, providing even more opportunities for learning and collaboration.