Reconstruction and Imaging Motion Estimation (RIME)

Workshop Description

Advances in medical imaging have revolutionized diagnostic and interventional medicine, providing unprecedented insights into anatomical and functional characteristics of the human body. However, accurate image reconstruction and motion estimation remain critical challenges, particularly in dynamic and real-time imaging scenarios.
The workshop focuses on the intersection of image reconstruction and motion estimation, which play pivotal roles in improving the accuracy, robustness, and speed of medical imaging modalities and will provide a dedicated forum for researchers to exchange ideas, share the latest advancements, discuss challenges, and foster collaborations that drive innovation in this critical field.
The workshop will explore a broad range of topics at the intersection of reconstruction and motion estimation in medical imaging. In the realm of image reconstruction, we seek advancements in computational methods, including iterative, variational, and model-based approaches, as well as innovations in deep learning and hybrid machine learning techniques.
In the domain of motion estimation and compensation, the workshop will cover both model-based and data-driven approaches, with a focus on motion-aware reconstruction. Strategies to address respiratory and cardiac motion correction in MRI and CT are of particular interest.
We are especially interested in synergistic approaches that jointly address reconstruction and motion estimation. Contributions may include frameworks that integrate these tasks, end-to-end learning-based pipelines for motion-robust imaging, and the use of physics-informed machine learning for motion tracking and image enhancement.
Additionally, the workshop will consider applications in various imaging contexts, such as brain imaging, cardiovascular imaging, abdominal imaging and functional imaging (e.g., fMRI), and possible movement including cardiac and respiratory motion and patient movement especially on challenging cases such as infant and fetal scans.
Finally, the workshop aims to bridge the gap between research and practice by highlighting clinical and translational studies. These include case studies demonstrating the real-world impact of advanced reconstruction and motion estimation methods, and discussions on overcoming challenges in adopting new imaging technologies in clinical workflows.
The goal for this workshop is to promote the exploration of novel applications, including translational research that bridges theoretical advancements with practical, clinical implementation. By providing a platform for discussion, the workshop seeks to build a strong research community, facilitating mentorship and collaboration opportunities for early-career researchers while encouraging dialogue about future directions and open challenges in the field.

Topics of interest

• Advancements in image reconstruction: iterative, variational, model-based, deep learning, and hybrid machine learning methods.
• Motion estimation: model-based and data-driven approaches, motion-aware reconstruction, and motion correction for cardiac and respiratory motion in MRI and CT.
• Synergistic approaches that integrate reconstruction and motion estimation, including end-to-end learning pipelines and physics-informed machine learning.
• Applications in various imaging contexts, such as brain, abdominal, and functional imaging (e.g., fMRI), as well as challenges related to patient movement in complex datasets (including infants and fetuses).
• Clinical translation and integration of new imaging technologies into clinical workflows.