Computational Medical Imaging Research (Albarqouni Lab)

Clinic for Diagnostic and Interventional Radiology

University Hospital Bonn

Faculty of Medicine

University of Bonn

The Albarqouni Lab, based at the Clinic for Diagnostic and Interventional Radiology at the University Hospital Bonn, conducts research at the intersection of medical imaging, artificial intelligence, and collective intelligence.
The lab’s mission is to develop the next generation of computational imaging algorithms that improve clinical decision-making while remaining privacy-preserving, robust, and globally accessible.

Inspired by principles of distributed intelligence, the lab views AI systems not as isolated models, but as collaborative ecosystems—where knowledge is learned locally, shared responsibly, and aggregated to benefit patients and healthcare systems worldwide. This perspective directly informs the lab’s work in federated learning, affordable AI, and trustworthy medical imaging.

The Albarqouni Lab is affiliated with the Munich School for Data Science (MUDS), the Medical Imaging Center Bonn (MIB), and the European Laboratory for Learning and Intelligent Systems (ELLIS).

Research Focus Areas

Research at the Albarqouni Lab is structured around three complementary pillars:

• Computational Medical Imaging
  The lab develops automated and data-efficient imaging methods that enhance accuracy, robustness, and reproducibility in clinical workflows. Key challenges addressed include limited and noisy annotations, inter- and intra-observer variability, class imbalance, scanner heterogeneity, and domain shift across institutions.

• Federated Learning in Healthcare
  The lab advances decentralized learning frameworks that enable multiple institutions and AI agents to learn collaboratively without sharing raw data. Research topics include robustness to data heterogeneity, explainability, quality control, resilience to adversarial or poisoning attacks, and reliable deployment in real-world clinical environments.

• Affordable AI for Global Health
  A core commitment of the lab is to design AI solutions that remain effective under resource constraints, including low-quality data, limited infrastructure, and point-of-care settings. This work aims to ensure that advances in medical AI are inclusive, scalable, and impactful beyond high-resource healthcare systems.

Meet the lab members

Computational Imaging Reserach (Albarqouni Lab)

Principal Investigator

Shadi Albarqouni

Professor of Computational Medical Imaging Research at University of Bonn | fmr. AI Young Investigator Group Leader at Helmholtz AI | Affiliate Scientist at Technical University of Munich

AI in Medicine, Federated Learning, Affordable AI and Healthcare

Researchers

Adea Nesturi

PhD Candidate

Deep Learning for Medical Image Analysis., AI for Healthcare., Computer Vision

Amine Ben Dhiab

Master Thesis Student

Ashkan Shakarami

Postdoctoral Fellow

Artificial General Intelligence, Computer Vision, Neural Networks, Computer-Aided Diagnosis, Histopathology, Ophthalmology

David D. Gaviria

PhD Candidate

Machine Learning for Medical Imaging, Computer Vision

Jiajun Zeng

PhD Candidate

AI4Health, Computer vision, Vision language models, Machine learning

Malek Al Abed

Research Associate

Artificial Intelligence for Healthcare, Deep Learning, Computer Vision

Mayar Abdeldayem

Master Thesis Student

Somayeh Zamani

Research Associate

Clinical AI Assistants for Healthcare, Machine Learning for Medical Applications, Graph Neural Networks, Explainable AI

Clinical Collaborators

Barbara Wichtmann

Fachärztin für Radiologie at Universitätsklinikum Bonn

Hemmen Sabir

Professor and Head of Experimental Neonatology

Hyun Ko

Radiology Clinician Reseacher at Peter MacCallum Cancer Centre, Australia

Martina Herwig-Carl

Professor, Oberärztin der Augenklinik am Universitätsklinikum Bonn

Valentin Schäfer

Professor and Head of the Department of Rheumatology and Clinical Immunology at the Clinic of Internal Medicine III at Universitätsklinikum Bonn

Alumni

Anna Bodonhelyi

Research Assistant (HiWi)

Anna Lisitsyna

Research Scientist

Aya ELGebaly

Master’s Thesis Student

Carlos Fernández Del Cerro

Visiting PhD Student

Cosmin Bercea

Researcher

Diletta Chiaro

Visiting PhD Student

Elodie Germani

Postdoctoral Researcher

Elyes Farjallah

Research Assistant (HiWi)

İlayda Selin Türk

Master Thesis Student

Mazen Soufi

Visiting Scientist

Mert Ikinci

Master Thesis Student

Mohammad Taha

Bachelor Student

Nada El Darra

Visiting Scientist

Parinishtha Bhalla

Master Thesis Student and Research Assistant (HiWi)

Pranav Kirti

Visiting Researcher & Fulbright Scholar

Qiongkai Xu

Visiting PhD Student and Research Fellow of Security in NLP

Razieh Rezaei

Researcher

Sarah Schaab

Master Student and Research Assistant (HiWi)

Simone Löhlein

Master Student

Tariq Bdair

Researcher

Tobias Bernecker

Master Student

Ziqi Wang

Visiting PhD Student

Latest News

• Our two submitted papers got accepted at the 29th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in Strasbourg, France (Accpetance rate: 29%)
• Shadi delivered an Invited Talk at FAIBI workshop at IEEE ISBI in London, UK
• Shadi has been appointed as an Associate Editor at IEEE Transaction on Medical Imaging (IEEE TMI)
• Shadi is serving as an Area Chair at NeurIPS'26
• Our Paper on PDAC got accepted at Scientific Report – Congrats to David and Pari
• Our three submitted papers got accepted as Oral Presentations at The 23rd IEEE International Symposium on Biomedical Imaging (ISBI), London, United Kingdom
• One Paper got early accepted (Top 9%) at The 28th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025), Daejeon, South Korea

Research Themes

Active Research Themes. Thanks to our great collaborators!

MRIQT

Physics-aware diffusion model for uLF-to-HF image quality transfer in neonatal MRI.

Affordable AI and Healthcare

We are also interested in developing affordable AI solutions suitable for poor-quality data generated by low infrastructure and point-of-care diagnosis.

Follow Contribute

Deep Federated Learning in Healthcare

This 5 years Helmholtz funded project to advance the field with Federated Learning algorithms in Medicine (2020-2025)

Follow Contribute

Learn from Crowds

Crowdsourcing, Gamification

Follow Contribute

Learn from Prior Knowledge

Manifold Learning, Graph Convolutional Networks

Follow Contribute

Learn to Adapt

Domain Adaptation, Style Transfer

Follow Contribute

Learn to Learn

Meta-Learning, Few-Shot Learning

Follow Contribute

Learn to Reason and Explain

Interpretable ML, Disentangled Representation, Fairness

Follow Contribute

Learn to Recognize

Detection, Classification, Segmentation, Anomaly Detection, Semi-/Weakly-Supervised Learning

Follow Contribute

Funded Research Projects

Thanks to the 3rd party funding from EU, DFG, DAAD, BMBF, AGYA, GIZ and BaCaTec

Symposium on AI in Medicine & Food Science

Time: All times correspond to local Bonn time (CET) Day 1 — Tuesday, 9 December 2025 Arrival & Check-in 📍 Youth Hostel Bonn, Haager Weg 42, 53127 Bonn Day 2 — Wednesday, 10 December 2025 Symposium on AI in Medicine

Summer School on Biomedical Imaging with Deep Learning (BILD)

DAAD Funded Project (2025-2025)

Strategic Arab-German Network for Affordable and Democratized AI (SANAD)

DAAD Funded Project (2025-2025)

Application of AI and Advanced MRI for a Better Prediction of Disease Progression in Neurological Disorders

Bonn International Fellowships (2024 - 2025)

Summer School on Affordable AI (SAAI)

BMBF Funded Project with the Arab-German Young Academy for Science and Humanities (2024-2024)

Open Medical Inference (OMI)

BMBF Funded Project through Medical Informatics Initaitive (MII) consortia (2024-2028)

Affordable AI and Collaborative Federated Learning for Global Healthcare (EEDA)

DAAD Funded Project with Beirut Arab University, Lebanon (2023-2023)

Deep learning to estimate aging from chest imaging

The 3-year DFG Funded project with UniKlinikum Freiburg (2023-2026)

Utilising Artificial Intelligence in Cancer Imaging To Improve Patient Outcomes

Bonn-Melbourne Research Excellence Fund (2023-2024)

Development of a Deep Learning Toolkit for MRI-Guided Online Adaptive Radiotherapy

The 3-year DFG Funded project with LMU and TU Munich (2022-2025)

BigPicture Project

The 6-year EU Funded €70 million project called BIGPICTURE will herald a new era in pathology

Deep Federated Learning in Healthcare

This 5 years Helmholtz funded project to advance the field with Federated Learning algorithms in Medicine (2020-2025)

Modelling Uncertainty in Deep Learning for Medical Applications

DAAD Funded Project with ETH Zürich and Imperial College London (2020-2022)

Telemedicine in Palestine

Telemedicine in Palestine from Shadi Nabil Albarqouni Collaboration: Funding:

Uncertainty Aware Methods for Camera Pose Estimation and Relocalization

BaCaTeC Funded Project with Stanford University and Siemens AG (2020-2021)

Students

Teaching courses, Theses, and Internships

Lab: Computational Medical Imaging (CoMI)

The Computational Imaging Research (CoMI) Lab at the University of Bonn is a project-based lab where students carry out a semester-long research project in computational medical imaging, implementing and evaluating state-of-the-art algorithms on real medical data.

Shadi Albarqouni

Last updated on Jul 7, 2026

Seminar: Artificial Intelligence in Radiology: Applications and Research

The Computational Imaging Research (Albarqouni Lab) at the Clinic of Diagnostic and Interventional Radiology at the University Hospital Bonn is pleased to present a seminar on Artificial Intelligence in Radiology: Applications and Research. This cutting-edge seminar, spanning two semester hours per week (2 SWS), is specially curated for medical students to explore the transformative role of deep learning in medical imaging, with a focus on tasks such as classification, detection, segmentation, reconstruction, tracking, and disease progression.

Shadi Albarqouni

Last updated on Jul 7, 2026

Block Course: AI in Medicine (AiM): Foundations, Methods, and Critical Perspectives

This AiM block course offers an intensive introduction to artificial intelligence in medicine, with a focus on modern deep learning methods for biomedical and clinical applications. Designed as an interdisciplinary format, the course combines concept-driven lectures with interactive labs, allowing students to engage both with the theoretical foundations of AI and with practical challenges in medical data analysis.

Adea Nesturi, David D. Gaviria, Jiajun Zeng, Pranav Kirti, Malek Al Abed, aditya-rastogi, Elodie Germani, Shadi Albarqouni

Last updated on Jul 7, 2026

Seminar: Computational Medical Imaging (CoMI)

The Computational Imaging Research (CoMI) Seminar at the University of Bonn explores current research in Computational Medical Imaging, including classical algorithms and deep learning-based approaches. Students critically analyze state-of-the-art research and develop both technical and presentation skills.

Shadi Albarqouni

Last updated on Jul 7, 2026

Special Version: AI in Radiology – From Pixels to Decisions (AiR-GUC Edition)

A special joint seminar between the University of Bonn and the German University in Cairo (GUC), delivered under the Joint Teaching Initiative. This interdisciplinary course explores AI in Radiology from both technical and clinical perspectives, combining computational medical imaging and deep learning to foster cross-cultural collaboration, innovation, and sustainable academic exchange.

Adea Nesturi, mohammed-salem, shereen-afifi, Shadi Albarqouni

Last updated on Jul 7, 2026

See all

Community Engagement

Professional Services and Invited Talks

Our Lab at MICCAI 2026 in Strasbourg

At MICCAI 2026 in Strasbourg, our lab had two papers (PromptGate and K-Mat) and co-organized the SAFER and DeCaF workshops.

Sep 27, 2026 — Oct 1, 2026 Strasbourg, France

David D. Gaviria, Adea Nesturi, Jiajun Zeng, Shadi Albarqouni

Follow

Two Awards to Attend MICCAI 2026 in Strasbourg

Both David Dueñas Gaviria and Adea Nesturi have awarded the 2026 MICCAI Society Registration Grant and the University of Bonn’s funding for the Participation in International Conferences, respectively. Both awards will support their attendance at MICCAI 2026 in Strasbourg, where they will present their accepted paper PromptGate.

Sep 27, 2026 — Oct 1, 2026 Strasbourg, France

David D. Gaviria, Adea Nesturi, Shadi Albarqouni

Invited Talk at Karman Conference on Innovations in non-invasive and computational imaging

I had the pleasure of delivering an invited talk on Foundation Models in Medicine at the Karman Conference on Innovations in non-invasive and computational imaging, RWTH Aachen University. Interested in hearing about our recent work? Come to #MICCAI2026 in Strasbourg MICCAI Society. My team members will present their accepted papers on Active Learning and Multi-modal data!

Sep 7, 2026 09:00 — Sep 9, 2026 16:30 Aachen, Germany

Shadi Albarqouni

Follow

BONFOR Symposium & Promotionsbörse in Bonn

David represented our lab at the BONFOR Symposium 2026 in Bonn, presenting our research at the Promotionsbörse (doctoral thesis fair) and connecting with students looking for a doctoral thesis topic.

Jun 16, 2026 — Bonn, Germany

David D. Gaviria, Shadi Albarqouni

HAICON 2026 – AI for Science Conference

Malek and Adea attended the Helmholtz AI conference, HAICON 2026, where they presented posters of the lab recent accepted papers.

Jun 8, 2026 — Jun 10, 2026 Munich, Germany

Adea Nesturi, Malek Al Abed, Jiajun Zeng, Shadi Albarqouni

See all talks

Featured Publications

When multi-institutional dataset aggregation masks shortcut-like behavior in Foundation Models for medical imaging

Elodie Germani, Fatima Zeineddine, Charbel Mourad, Shadi Albarqouni

Cite

Federated CT foundation models for multi-center detection of lymph node metastasis in pancreatic cancer

Parinishtha Bhalla, David D. Gaviria, Patrick Kupczyk, Ali Seif Amir Hosseini, Lena Conradi, Uli Fehrenbach, Matthaeus Felsenstein, Dou Ma, Alexander Semaan, Shadi Albarqouni

Cite

Editorial for the Special Issue on the 2022 Medical Imaging with Deep Learning Conference

Shadi Albarqouni, Christian Baumgartner, Qi Dou, Ender Konukoglu, Bjoern Menze, Archana Venkataraman

Cite

Lvm-med: Learning large-scale self-supervised vision models for medical imaging via second-order graph matching

Obtaining large pre-trained models that can be fine-tuned to new tasks with limited annotated samples has remained an open challenge …

Duy MH Nguyen, Hoang Nguyen, Nghiem Diep, Tan Ngoc Pham, Tri Cao, Binh Nguyen, Paul Swoboda, Nhat Ho, Shadi Albarqouni, Pengtao Xie, others

PDF Cite Code Project Project

Digital staining of white blood cells with confidence estimation

Chemical staining of the blood smears is one of the crucial components of blood analysis. It is an expensive, lengthy and sensitive …

Agnieszka Tomczak, Slobodan Ilic, Gaby Marquardt, Thomas Engel, Nassir Navab, Shadi Albarqouni

PDF Cite Project Project

Guest Editorial Special Issue on Federated Learning for Medical Imaging: Enabling Collaborative Development of Robust AI Models

Federated Learning (FL) could solve the challenges of training AI models on large datasets for medical imaging due to data privacy and …

Holger R Roth, Nicola Rieke, Shadi Albarqouni, Quanzheng Li

PDF Cite Project

FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings

Federated Learning (FL) is a novel approach enabling several clients holding sensitive data to collaboratively train machine learning …

Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Shadi Albarqouni, others

PDF Cite Code Project

Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering

Collecting large-scale medical datasets with fully annotated samples for training of deep networks is prohibitively expensive, …

Duy MH Nguyen, Hoang Nguyen, Mai TN Truong, Tri Cao, Binh T Nguyen, Nhat Ho, Paul Swoboda, Shadi Albarqouni, Pengtao Xie, Daniel Sonntag

PDF Cite

Federated disentangled representation learning for unsupervised brain anomaly detection

With the advent of deep learning and increasing use of brain MRIs, a great amount of interest has arisen in automated anomaly …

Cosmin Bercea, Benedikt Wiestler, Daniel Rueckert, Shadi Albarqouni

PDF Cite Project DOI URL

What can we learn about a generated image corrupting its latent representation?

Generative adversarial networks (GANs) offer an effective solution to the image-to-image translation problem, thereby allowing for new …

Agnieszka Tomczak, Aarushi Gupta, Slobodan Ilic, Nassir Navab, Shadi Albarqouni

PDF Cite

Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study

Deep unsupervised representation learning has recently led to new approaches in the field of Unsupervised Anomaly Detection (UAD) in …

Christoph Baur, Stefan Denner, Benedikt Wiestler, Nassir Navab, Shadi Albarqouni

PDF Cite Code Project

FedPerl: Semi-Supervised Peer Learning for Skin Lesion Classification

Skin cancer is one of the most deadly cancers worldwide. Yet, it can be reduced by early detection. Recent deep-learning methods have …

Tariq Bdair, Nassir Navab, Shadi Albarqouni

PDF Cite Project

Multi-task multi-domain learning for digital staining and classification of leukocytes

oking stained images preserving the inter-cellular structures, crucial for the medical experts to perform classification. We achieve …

Agnieszka Tomczak, Slobodan Ilic, Gaby Marquardt, Thomas Engel, Frank Forster, Nassir Navab, Shadi Albarqouni

PDF Cite Project Project

The Future of Digital Health with Federated Learning

Data-driven Machine Learning has emerged as a promising approach for building accurate and robust statistical models from medical data, …

Nicola Rieke, Jonny Hancox, Wenqi Li, Fausto Milletari, Holger Roth, Shadi Albarqouni, Spyridon Bakas, Mathieu N Galtier, Bennett Landman, Klaus Maier-Hein, others

PDF Cite Project

Fairness by Learning Orthogonal Disentangled Representations

Learning discriminative powerful representations is a crucial step for machine learning systems. Introducing invariance against …

Mhd Hasan Sarhan, Nassir Navab, Abouzar Eslami, Shadi Albarqouni

PDF Cite Project Project

Seamless Virtual Whole Slide Image Synthesis and Validation Using Perceptual Embedding Consistency

Stain virtualization is an application with growing interest in digital pathology allowing simulation of stained tissue images thus …

Amal Lahiani, Irina Klaman, Nassir Navab, Shadi Albarqouni, Eldad Klaiman

PDF Cite Project

Recent Publications

Quickly discover relevant content by filtering publications.

Elodie Germani, Fatima Zeineddine, Charbel Mourad, Shadi Albarqouni (2026). When multi-institutional dataset aggregation masks shortcut-like behavior in Foundation Models for medical imaging. Medical Image Analysis.

Cite

Claus-Jurgen Bauer, Sarah Schaab, Pranav Kirti, Shadi Albarqouni, Valentin Sebastian Schafer (2026). Artificial intelligence for ultrasound-based detection of giant cell arteritis. INNERE MEDIZIN.

Cite

Mert Ikinci, Luna Toma, Karin U Loeffler, Leticia Ussem, Daniela Süsskind, Julia M Weller, Yousef Yeganeh, Martina C Herwig-Carl, Shadi Albarqouni (2026). INTERACT-CMIL: Multi-Task Shared Learning and Inter-Task Consistency for Conjunctival Melanocytic Intraepithelial Lesion Grading. 2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI).

Cite

Jiajun Zeng, Shadi Albarqouni (2026). K-MaT: Knowledge-Anchored Manifold Transport for Cross-Modal Prompt Learning in Medical Imaging. arXiv preprint arXiv:2603.06340.

Cite

M Coerper, P Bhalla, D Duenas Gaviria, P Kupczyk, L Conradi, A Seif, D Ma, S Jacob, I Pozios, M Felsenstein, others (2026). KI-gestützte datenschutzkonforme multizentrische Vorhersage lymphogener Metastasierung beim Pankreaskarzinom mittels eines föderierter CT-Foundation-Modelle. Zeitschrift für Gastroenterologie.

Cite

See all publications

Open Positions

Admin., Research Assistants, PhDs, Postdocs, and Medical Research Assistants. We do accept applications on an on-going basis, so feel free to send your motivation letter, resume, and your transcript via email or here.

CIR/01/2026: Ph.D. position in AI in Medicine: Foundation Models (m/f/d)

starting April 2026 or as agreed upon. The position is initially limited to three years, with the possibility of extension.

Shadi Albarqouni

Last updated on Jul 7, 2026

Contact

• Baunscheidtstr. 17, Bonn, DE- 53113
• Floor 2, BonnJour