Magnetic Particle Imaging (MPI) is an emerging, radiation-free imaging technique that utilizes
superparamagnetic iron oxide nanoparticles (SPIONs) for quantifiable imaging. MPI’s strengths
include high sensitivity, quantitative capabilities, and minimal signal attenuation. However, its
relatively low resolution and the lack of standardized analytical methods affect its translation
into clinical practice. In recent years, various artificial intelligence (AI) methods have
increasingly been used to enhance biomedical imaging by improving the speed, quality, and
efficiency of imaging processes and analysis. This talk will cover recent developments in the
integration of machine learning (ML) and deep learning (DL) techniques in MPI image
reconstruction and analysis, which enhance the diagnostic capabilities and research potential of
this cutting-edge imaging modality. These methods are particularly valuable for applications
such as denoising, reconstruction, and image augmentation, enabling better imaging quality and
analysis. As the field of MPI continues to evolve and datasets grow, the amalgamation of AI-
based approaches will play a vital role in advancing disease diagnosis and treatment planning.
Meanwhile, it is essential to address challenges related to data availability, model
interpretability, and regulatory compliance to fully harness the potential of AI in MPI. With
continued research, collaboration, and responsible implementation, these technologies have the
potential to reshape the future of MPI in various applications.

Presenter Biography:
Ping Wang is a tenure-track Assistant Professor in the Department of Radiology and Precision Health Program at Michigan State University (MSU). Before joining MSU in 2018, he was an instructor at Harvard Medical School (2014-2017) after obtaining his postdoctoral training at the Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital (2009-2014). Dr. Wang’s research focuses on image-guided cell-based therapy for type 1 diabetes (T1D). Over the past several years, he initiated several projects aimed at developing novel imaging techniques for monitoring human induced pluripotent stem cell (iPSC)-derived islet organoid transplantation in T1D animal models. His group has successfully developed machine learning and deep learning algorithms for imaging data analysis and predictions for these cell therapy applications. Dr. Wang is a member of the Academy for Radiology & Biomedical Imaging Research CECI2 (2022-2023) and a Scialog: Advancing Bioimaging Fellow (2021-2023).

Author