The Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop has been running annually at MICCAI since 2010. The 17th edition will be held in conjunction with MICCAI 2026 in Strasbourg, France — bringing together researchers (engineers, biophysicists, mathematicians) and clinicians working on statistical analysis of cardiac morphology and dynamics, computational modelling of the heart and fluid dynamics, data/models sharing, personalisation of cardiac electro-mechanical models, quantitative image analysis and translational methods into clinical practice.
Keynote speaker
Chen (Cherise) Chen, Lecturer (Assistant Professor) at the University of Sheffield, UK
Title: Limited Resources, Unlimited Impact: Multimodal AI for Healthcare
Abstract: Recent progress in AI has been driven by large-scale datasets and high-performance computing, leading to the development of foundation models, including multimodal and generative approaches, as well as emerging applications such as digital twins in healthcare. In the medical domain, however, key challenges remain: data are often limited, annotations are costly and imbalanced, biases across populations and acquisition settings are common, and modalities may be missing. These constraints require methods that are not only accurate but also robust, data-efficient, and reliable in practice.
In this talk, I will present our recent work on multimodal AI for healthcare, viewing these challenges as opportunities for model design, with examples from cardiovascular imaging. Specifically, I will show: (1) how multimodal generative models and clinical knowledge, such as anatomical atlases, can improve cardiac segmentation under limited data; (2) how multimodal learning can enhance single-modality analysis by leveraging complementary information from other modalities; and (3) how to design models that remain effective when inputs are missing, together with methods for improved uncertainty estimation to better support human decision-making in the loop.
Short bio: Chen (Cherise) Chen is a Lecturer (Assistant Professor) at the University of Sheffield, UK, and an ELLIS Scholar in Robust Machine Learning Program at the European Laboratory for Learning and Intelligent Systems. Her research focuses on robust machine learning for healthcare, with a particular emphasis on cardiovascular diseases (CVDs). She has developed many advanced methods to improve robustness and generalisation in complex clinical decision-making systems, including medical image and signal analysis, addressing challenges such as data heterogeneity, distribution shift, and reliability in real-world deployment.
Chen has substantial research experience across both academia and industry. She was previously a postdoctoral researcher at Imperial College London and the University of Oxford, and has worked as a Research Scientist at Infervision Inc. before her PhD and at HeartFlow after her PhD. She has published over 60 papers in leading venues, including MICCAI, ICCV, ECCV, Nature Machine Intelligence, IEEE Transactions on Medical Imaging, and Medical Image
Analysis, with around 5,000 citations. She has served as Program Chair for MIDL 2025 and Area Chair for IJCAI 2026 and MICCAI (2024–2025), and has organised several MICCAI workshops and challenges, including ADSMI, DALI, and the CMRxMotion Challenge. In 2025, her work received the Best Paper Award at an international AI in healthcare conference. https://cherise215.github.io/.
Challenge Partners
EchoRisk Challenge
EchoRisk is part of the MICCAI 2026 Cardiac Imaging Thematic Focus. Develop AI methods for cardiac function estimation and early prediction of therapy-induced cardiotoxicity from echocardiography data.
Learn more →CMRxRecon2026 Challenge
Dramatically accelerate 4D Flow MRI acquisition and reconstruction, enabling high-fidelity magnitude, phase, and hemodynamic imaging for routine clinical use.
Learn more →