ShapeMI MICCAI 2026: Workshop on Shape in Medical Imaging

ShapeMI

We gladly announce the workshop on Shape in Medical Imaging (ShapeMI), which is held in conjunction with the conference on Medical Image Computing and Computer Assisted Interventions (MICCAI 2026) in Abu Dhabi, UEA. This workshop is the sixth instance of ShapeMI, after successful ShapeMI'18, ShapeMI'20, ShapeMI'23, ShapeMI'24, and ShapeMI'25.

This workshop aims to present leading methods and applications for advanced shape analysis and geometric learning in medical imaging. It will provide a venue for researchers working in shape and geometric modeling, learning, analysis, statistics, classification, and applications to share novel ideas, present recent research results, and interact with each other. Today’s medical image data typically represent three-dimensional geometric structures and dynamic, time-varying anatomical processes. Shape and geometry processing methods continue to play a crucial role because of their sensitivity to subtle morphological variations. Data-driven differential geometry for shape and spectral analysis and modeling remains a central focus of this workshop. At the same time, rapid advances in deep learning research are reshaping how the mathematical foundations of computational anatomy are used. A new theme of ShapeMI 2026 is how shape is being integrated with modern AI architectures. Recent progress in transformer-based point cloud models, equivariant neural networks, neural fields, and large geometric foundation models is reshaping how core concepts of computational anatomy are operationalized through applied research in healthcare. We will look forward to receiving methodology or applied research in topics that

emphasize how classical shape theory informs the design, interpretability, and generalization of modern geometric deep learning models. Furthermore, anatomical shape does not exist in isolation, and biomedical research that only includes shape will generate discoveries that will remain siloed within the structural realm. This workshop will place special emphasis on multi-modal and multi-scale shape-driven biomarkers, including the fusion of shape descriptors with multiomics data, clinical and electronic health records, longitudinal disease trajectories, and biomechanical simulations. This focus reflects a growing shift from shape analysis as a standalone methodology toward shape-informed, integrative modeling pipelines for precision medicine and population-level inference.

2025 Proceedings

https://link.springer.com/book/10.1007/978-3-032-06774-6

2024 Proceedings

https://link.springer.com/book/10.1007/978-3-031-75291-9

2023 Proceedings

https://link.springer.com/book/10.1007/978-3-031-46914-5

Best paper award winners 2026 🏆

Topics

This workshop targets theoretical contributions as well as exciting applications in medical imaging, including (but not limited to):

Academic objectives

The workshop will call for paper submissions on three different topics, or combinations thereof: methodology, applications, and software platforms in shape modeling and statistics. The best papers will be presented in oral sessions. A poster session will host the remaining accepted papers and will provide ample opportunity for in-depth discussion of all submitted topics. As in previous years, we will encourage presenters to showcase any software platform that resulted from the presented work. As a single-track workshop, ShapeMI will feature excellent keynote speakers, technical paper presentations and demonstrations of state-of-the-art software for shape processing in medical research.

Data (optional)

If you are looking for medical shapes for your work, take a look at MedShapeNet, which is a large-scale dataset of 3D medical shapes.

Organizers

Advisory Board / Program Committee

As in previous years, we will have a highly qualified advisory board, similar to ShapeMI 2018, 2020, 2023, 2024, and 2025, as listed below.

MICCAI 2026

Sponsor

TBD