We are pleased to share that AI-POD will be well represented at MICCAI 2025, the premier international conference on medical image computing and computer-assisted interventions. This year, our researchers and collaborators are contributing to both the main conference and several workshops, highlighting advances in trustworthy and responsible AI for medical imaging.
Main AI-POD Paper at STACOM
Our primary AI-POD contribution will be presented at the Statistical Atlases and Computational Modeling of the Heart (STACOM) Workshop:
Ajay Mittal, Raghav Mehta, Omar Todd, Philipp Seeböck, Georg Langs, Ben Glocker
Cardiovascular disease classification using radiomics and geometric features from cardiac CT Images
This work combines radiomics and geometric analysis to improve classification of cardiovascular disease from CT imaging, directly contributing to AI-POD’s mission of enhancing clinical decision support with reliable AI.
Several additional papers with AI-POD co-authors will be presented at the MICCAI 2025 main conference, addressing key challenges in safe deployment, uncertainty quantification, segmentation, and generative modeling:
Mélanie Roschewitz, Raghav Mehta, Charles Jones, Ben Glocker
Automatic dataset shift identification to support safe deployment of medical imaging AIRaghav Mehta, Karthik Gopinath, Ben Glocker, Juan Eugenio Iglesias
UNSURF: Uncertainty Quantification for Cortical Surface Reconstruction of Clinical Brain MRIsRaghav Mehta, Fabio De Sousa Ribeiro, Tian Xia, Melanie Roschewitz, Ainkaran Santhirasekaram, Dominic C. Marshall, Ben Glocker
CF-Seg: Counterfactuals meet SegmentationTian Xia, Matthew Sinclair, Andreas Schuh, Fabio De Sousa Ribeiro, Raghav Mehta, Rajat Rasal, Esther Puyol-Antón, Samuel Gerber, Kersten Petersen, Michiel Schaap, Ben Glocker
Segmentor-guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis
AI-POD Co-authored Papers at MICCAI Workshops
Beyond the main conference, AI-POD researchers will also present in two specialized MICCAI workshops:
Emma A.M. Stanley, Raghav Mehta, Mélanie Roschewitz, Nils D. Forkert, Ben Glocker
Exploring the interplay of label bias with subgroup size and separability: A case study in mammographic density classification
(FAIMI – Fairness of AI in Medical Imaging Workshop)Omar Todd, Sooha Kim, Katherine Mackay, Raghav Mehta, Fabio De Sousa Ribeiro, David Bernstein, Alexandra Taylor, Ben Glocker
Delineation Uncertainty from Clinician Ranges in Cervical Cancer Radiotherapy Planning
(CAPI – Computer-Aided Pelvic Imaging for Female Health Workshop)Christoph Fürböck, Paul Weiser, Branko Mitic, Philipp Seeböck, Thomas Helbich, Georg Langs No Modality Left Behind: Dynamic Model Generation for Incomplete Medical Data. MICCAI Workshop on Machine Learning in Clinical Decision Systems ML-CDS
Jeanny Pan, Philipp Seeböck, Christoph Fürböck, Svitlana Pochepnia; Jennifer Straub; Lucian Beer; Helmut Prosch; Georg Langs Disentanglement of Biological and Technical Factors via Latent Space Rotation in Clinical Imaging Improves Disease Pattern Discovery. (MICCAI Workshop on Applications of AI in Medicine AMAI 2025)
Branko Mitic, Philipp Seeböck, Helmut Prosch, Georg Lang AREPAS: Anomaly Detection in Fine-Grained Anatomy with Reconstruction-Based Semantic Patch-Scoring (MICCAI Workshop on Machine Learning in Medical Imaging MLMI 2025)
AI-POD Impact at MICCAI 2025
These contributions demonstrate AI-POD’s growing impact across the medical imaging community. From robust cardiovascular disease modeling to dataset shift detection, uncertainty quantification, counterfactual reasoning, and fairness in AI, our research is helping build a future where AI in healthcare is not only powerful, but also safe, interpretable, and equitable.
We look forward to engaging with the community at MICCAI 2025 and advancing discussions on the responsible development of medical AI.