Yasmeen George |

Co-organized the 7th MICCAI DeCaF Workshop on Distributed, Collaborative and Federated Learning

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

On 1 October 2026 we held the 7th MICCAI Workshop on Distributed, Collaborative and Federated Learning (DeCaF 2026) at in Strasbourg — a series I have co-organised since its beginnings as DCL in 2020 (see also ). Data sharing across hospitals is often impractical because of privacy regulations and data ownership, so DeCaF is a forum for methods that train and deploy models collaboratively without sharing raw data: federated and distributed learning, multi-agent and agentic systems across institutions, federated fine-tuning of foundation models, collaborative inference, privacy, security and fairness, and benchmarks for real-world federated learning.

Programme (local time, Strasbourg)

Time	Session
08:00	Introduction to the DeCaF workshop
08:10	Poster preview (14 posters)
08:25	Keynote 1 — Evelyn Trautmann, Apheris, Germany
09:15	Keynote 2 — Marco Lorenzi, Université Côte d’Azur, France
10:00	Coffee break and poster session
10:30	Oral presentations (7 papers)
12:00	NVIDIA presentation
12:15	Awards and closing remarks

NVIDIA sponsored a DGX Spark for the best paper and Brev credits for the runner-up. Accepted papers appear in the Springer LNCS proceedings of the MICCAI 2026 satellite events.

Organisers: Meirui Jiang (Ant Group), Xiaoxiao Li (University of British Columbia), Shadi Albarqouni (University Hospital Bonn), Spyridon Bakas (Indiana University School of Medicine and MLCommons), Holger Roth (NVIDIA), Alex Karagyris (MLCommons), (Monash University) and Pramit Saha (University of Oxford). Details: .

Co-organized the MICCAI 2026 SAFER Workshop on Trustworthy Medical Foundation Models

Sun, 27 Sep 2026 00:00:00 +0000

On 27 September 2026 we held the first SAFER workshop — Stable Adaptation and Faithful Evaluation of Reasoning — at in Strasbourg. As medical AI moves beyond performance-driven optimisation, SAFER brings together researchers from academia, industry and clinical practice around medical foundation and vision–language models that explain their reasoning transparently, ground their outputs in verifiable medical evidence and adapt reliably across imaging domains and modalities. Key themes are hallucination detection and grounding in radiology and surgical vision, trust and evaluation of reasoning for image-based diagnosis, and stable adaptation to unseen imaging domains.

Programme (Room Curie B)

Time (CEST)	Session
08:00	Opening remarks
08:15	Oral session 1: Robust adaptation and grounding in medical foundation models (4 papers)
09:15	Keynote 1: Beyond Performance: Evaluating Foundation Models for Trustworthy Medical AI — Annika Reinke, German Cancer Research Center (DKFZ)
10:00	Coffee break
10:30	Keynote 2: Promise Versus Performance: A Faithful Benchmark of Vision-Language Foundation Models Against Specialized AI for Lung Cancer Prediction — Pierre Baudot, Median Technologies
11:15	Oral session 2: Trustworthy reasoning and evaluation in medical VLMs (5 papers)
12:15	Closing remarks
12:30	Lunch and poster session

Organisers: Dwarikanath Mahapatra (Khalifa University), Imran Razzak (MBZUAI), Miguel O. Bernabeu (University of Edinburgh), Shadi Albarqouni (University of Bonn) and (Monash University). Outreach committee: Hongxi Yang, Jianghao Wu, Jiayi Chen and Trang Pham (Monash University) and (University of Bonn). Details: .

Our Lab at MICCAI 2026 in Strasbourg

Sun, 27 Sep 2026 00:00:00 +0000

Our lab was at MICCAI 2026 in Strasbourg, France! This year, we contributed across research, workshops, and the broader MICCAI Society. It was great to see these efforts come together, from developing new methods to creating spaces for discussion, collaboration, and exchange.

Papers at MICCAI

Our lab had two papers accepted at the main conference:

— Adea Nesturi, David Dueñas Gaviria, Jiajun Zeng, and Shadi Albarqouni

Adea Nesturi and David Dueñas Gaviria presented the work as poster W-AM-192. The paper introduces PromptGate, a vision-language gating framework that filters out-of-distribution samples before active learning. This helps reduce unnecessary annotation and improves the quality of selected medical images while preserving patient privacy across institutions.
— Jiajun Zeng and Shadi Albarqouni

Jiajun Zeng presented K-MaT as poster W-AM-193. The work studies high-to-low generalization in medical imaging, transferring knowledge from high-end to low-end modalities without access to low-end labels. These posters attracted considerable interest and led to many engaging discussions with researchers at the conference.

Co-organized workshops

We also co-organized two workshops:

(September 27), with Yasmeen George, Dwarikanath Mahapatra, Imran Razzak, among others.
(October 1), with Holger R. Roth, Spyridon Bakas, Xiaoxiao Li, Yasmeen George, Meirui Jiang, and others.

Workshop Satellite Event

In addition, Prof. Shadi Albarqouni served as one of the Workshop Chairs of MICCAI 2026, overseeing the workshop satellite events that brought together researchers and organizers from across the community.

Overall, it was a great week for the group: reconnecting with familiar faces, meeting new people, and having many interesting conversations throughout the conference. We look forward to the next one!