Daniel Sodickson

Daniel Sodickson is a Professor at New York University, affiliated with the Electrical Engineering department. His research focuses on biomedical imaging, with an emphasis on developing new techniques to enhance human health. He leads a multidisciplinary team that explores rapid continuous imaging, leveraging advancements in parallel imaging, compressed sensing, and artificial intelligence. His work applies to clinical imaging modalities such as MRI, PET, and CT. Sodickson is also involved in several research centers and initiatives, including the Bernard and Irene Schwartz Center for Biomedical Imaging and the Center for Advanced Imaging Innovation and Research.

Daniel Sodickson is a leading researcher in biomedical imaging, with a focus on advancing imaging techniques through innovative methods such as compressed sensing, parallel imaging, and machine learning. His work includes the development of fast MRI techniques like SMASH and golden-angle radial sampling, which enable rapid and high-resolution imaging. Sodickson has contributed significantly to the field through open datasets such as fastMRI, which supports research in accelerated MRI reconstruction. His research also explores the application of deep learning for parallel MRI reconstruction and the quantification of imaging parameters. His publications emphasize the integration of multiple imaging modalities to improve diagnostic accuracy and efficiency.