Affordable & Responsible AI for Global Health |

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

Tue, 01 Sep 2026 00:00:00 +0000

OpenMed Resilience Kit: AI-Augmented Open-Source Diagnostics

Mon, 01 Jun 2026 00:00:00 +0000

The OpenMed Resilience Kit is a project of the Working Group Innovation, led by Prof. Shadi Albarqouni (PI, University Hospital Bonn) and Prof. Dr.-Ing. (co-PI, Hochschule Flensburg) and funded by the Federal Ministry of Research, Technology and Space (BMFTR) through AGYA.

The project advances two open-source hardware (OSH) medical devices into AI-augmented tools for resilient diagnostics in the Arab world and conflict-affected regions.

The AI-Augmented Stethoscope extends the 3D-printed Glia design with digital sensors and an AI module for detecting lung and heart anomalies; the low-cost digital stethoscope (“Stethogram”) is developed as open-source hardware by Hochschule Flensburg on (GPL-3.0). The Smart OpenFlexure Microscope deploys a low-cost digital microscope to underserved communities for the detection of malaria, trypanosomes, other parasitic infections and microplastics.

Our lab develops the AI models; Manuel Moritz’s group (Sustainable Product Development and Design Methods, Hochschule Flensburg) contributes its expertise in open-source hardware and product development.

Mapping the integration of artificial intelligence and digital technologies in health technology assessment: a scoping review protocol of global knowledge and practices

Thu, 01 Jan 2026 00:00:00 +0000

Summer School on Biomedical Imaging with Deep Learning (BILD)

Sun, 01 Jun 2025 00:00:00 +0000

Medical imaging is central to diagnosis, yet many hospitals in North Africa and the Middle East work with portable devices, limited compute and few specialists. Training the next generation of AI researchers to build methods that work under these conditions — and connecting them across countries — is the goal of the Summer School on Biomedical Imaging with Deep Learning (BILD).

The first edition took place in Tunis, Tunisia, 1–5 September 2025, as part of , the Strategic Arab-German Network for Affordable and Democratized AI in Healthcare. It was organised by the Albarqouni Lab (University Hospital Bonn and University of Bonn) with the University of Tunis El Manar, the Lebanese American University and Duhok Polytechnic University, and funded by the German Academic Exchange Service (DAAD) with funds from the Federal Foreign Office.

Measures

Summer school for about 50 students and graduates from Germany, Lebanon, Iraq and Tunisia, selected through an open call, with around 10 faculty members.
Course modules that combine current AI research with hands-on, resource-aware exercises: deep learning for medical imaging, lightweight neural networks for portable ultrasound, and federated learning on decentralised datasets.
Expert lectures by speakers from academia and industry, including the University of Tunis El Manar, TU Munich, FAU Erlangen-Nürnberg, Imperial College London and NVIDIA.
Hands-on labs and collaborative case studies guided by tutors from Bonn, Tunis and partner institutions.
Co-mentored research projects and exchange sessions in mixed international teams, continuing the collaboration beyond the week in Tunis.

Outcomes

BILD strengthened practical skills in building and deploying AI models for medical imaging, brought together young researchers and faculty from four countries, and grew the SANAD network into a sustained transnational community of AI innovators in healthcare.

Bias and generalizability of foundation models across datasets in breast mammography