Project Overview
MultiGeoMed is a cutting-edge, multidisciplinary research project at the intersection of artificial intelligence, medical imaging, and geometric deep learning. The project aims to advance fundamental knowledge in multimodal geometric deep learning — a rapidly evolving field that explores how different geometric representations can be combined to improve performance in medical imaging tasks. Our mission is to push the boundaries of how machines understand and process complex anatomical structures.
What is MultiGeoMed About?
Medical imaging data can be represented in various geometric forms, each offering unique advantages. MultiGeoMed investigates how to simultaneously leverage multiple geometric representations, including:
- 🧊 Voxel grids — the standard 3D pixel-based representation used in most medical scans.
- 🕸️ Surface meshes — capturing the shape and topology of anatomical structures.
- 🌐 Point clouds — sparse sets of 3D points representing objects.
- 🧠 Implicit neural representations — continuous functions learned by neural networks to represent shapes and volumes.
By combining these modalities, we aim to develop more robust and generalizable AI models for medical image analysis.
Goals
- Determine which geometric representation provides the most benefit for specific medical imaging tasks.
- Develop strategies to fuse multiple representations for enhanced performance in geometric deep learning models.
- Create scalable algorithms for integrating diverse geometric modalities into clinical workflows.
- Improve diagnostic accuracy and enable personalized treatment through advanced AI-driven shape analysis.
Principal Investigator
The project is led by Marek Wodziński, PhD, Assistant Professor at AGH University of Kraków and Senior Researcher at Sano - Centre for Computational Personalized Medicine. Dr Wodziński specializes in medical image analysis, computer vision, and deep learning, with a strong focus on geometric methods for healthcare applications.
Funding and Hosting
MultiGeoMed is funded by the National Science Centre, Poland under SONATA Grant no: 2024/55/D/ST6/02081. The project is hosted at the Sano Science Research Center, enabling collaboration with leading experts in AI and medical imaging.
Impact and Clinical Relevance
Medical imaging is central to modern healthcare, from diagnostics to treatment planning. By improving how AI models interpret and learn from complex anatomical data, MultiGeoMed has the potential to enhance diagnostic accuracy, enable more personalized treatment, reduce the need for invasive procedures, and contribute to a deeper understanding of human anatomy through data-driven insights.