Enhancing Precision and Accuracy of Positron Emission Tomography: Leveraging Variational Methods and Machine Learning for Advanced Static and Dynamic PET Image Reconstruction from Raw Data

• Applicant: Professor Dr. Reinhard Heckel
• Subject Area: Communication Technology and Networks, High-Frequency Technology and Photonic Systems, Signal Processing and Machine Learning for Information Technology
• Term: since 2026
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 569420668

This research project aims to enhance the quality of static and dynamic brain positron emission tomography (PET) image reconstruction. It tackles PET imaging's inherent challenges, such as high noise levels in the acquired data due to limited acquisition times and dose restrictions, by integrating Machine Learning (ML) and traditional model-based iterative reconstruction techniques. The project emphasizes the development and validation of both advanced ML and classical non-ML methods, ensuring a balance between innovative and robust approaches for static and dynamic PET reconstruction. A key component of the project is the creation of a high-quality, diverse, and open PET raw data database and developing open-source computational tools to support global research efforts. This infrastructure will facilitate the assessment of both ML-based and classical reconstruction methods, fostering innovation and collaboration within the research community. Additionally, organization of a reconstruction benchmark challenge aims to encourage the exploration and fair evaluation of new algorithms, thereby improving the diagnostic quality of PET imaging. By combining ML with classical methods and a deep understanding of PET physics and reconstruction, this multidisciplinary effort seeks to advance clinical applications of PET imaging, benefiting patients and the scientific community.

• DFG Programme: Research Grants
• International Connection: Austria, Belgium
• Partner Organisation: Fonds zur Förderung der wissenschaftlichen Forschung (FWF)
• Cooperation Partners: Professor Dr. Martin Holler; Professor Dr. Georg Schramm