Ge Wang () is a medical imaging scientist focusing on computed tomography (CT) and artificial intelligence (AI) especially deep learning. He is the Clark & Crossan Chair Professor of Biomedical Engineering and the Director of the Biomedical Imaging Center at Rensselaer Polytechnic Institute, Troy, New York, USA. He is known for his research and teaching on CT and AI-based imaging. He is a Fellow of the American Institute for Medical and Biological Engineering (AIMBE), Institute of Electrical and Electronics Engineers (IEEE), International Society for Optics and Photonics (SPIE), Optical Society of America (OSA/Optica), American Association of Physicists in Medicine (AAPM), American Association for the Advancement of Science (AAAS), and National Academy of Inventors (NAI). Since January 1, 2025, he has been serving as the Editor-in-Chief of the IEEE Transactions on Medical Imaging.
Wang earned a B.E. in Signal Processing at Xidian University and an M.S. in Remote Sensing at University of the Chinese Academy of Sciences. He was awarded an M.S. and a Ph.D. in Electrical and Computer Engineering from the University at Buffalo.
Wang, a pioneer in the field of medical imaging, made contributions that initiated the development of the spiral cone-beam computed tomography (CT) during the early 1990s. His work addressed the âÂÂlong object problem,â which involves longitudinal data truncation in cone-beam CT scans.
To solve the long-object problem, Wang and his collaborators enhanced existing 2D filtered backprojection and FeldkampâÂÂDavisâÂÂKress reconstruction by introducing 3D backprojection along the actual measurement rays from a spiral cone-beam scanning trajectory. This approach, marked the earliest advancement in cone-beam spiral CT. Commercial CT systems adopted and improved the approach proposed by Wang and colleagues.
In recognition of his contributions, Wang was inducted into the National Academy of Inventors in 2019. His research output includes numerous papers on cone-beam CT, covering topics such as exact cone-beam reconstruction with a general trajectory and quasi-exact triple-source spiral cone-beam reconstruction. Notably, about 200 million medical CT scans are performed annually using the cone-beam spiral scanning mode.
After his cone-beam CT work, Wang ventured into deep tomographic imaging. In 2016, he presented the first roadmap for deep imaging, which led to a series of influential papers on deep imaging-based low-dose CT, few-view, reconstruction, artifact reduction, radiomics, foundation models, and healthcare metaverse. His team also authored the first book on machine learning-based tomographic reconstruction. Collaborating with institutions like General Electric, the Food and Drug Administration, Johns Hopkins University, Yale University, and Harvard University, WangâÂÂs group develops cutting-edge imaging algorithms for clinical and preclinical applications.
WangâÂÂs team and collaborators developed interior tomography theory and algorithms, addressing the long-standing âÂÂinterior problemâÂÂ. His team also explored omni-tomography for spatiotemporal fusion of tomographic modalities, including the concept of simultaneous CT-MRI. Additionally, Wang and collaborators pioneered bioluminescence tomography for optical molecular imaging and developed spectrography techniques for ultrafast and ultrafine tomography using polychromatic scattering data.
His scholarly output includes over 800 peer-reviewed papers in journals such as Nature, Nature Machine Intelligence, Nature Communications, and Proceedings of the National Academy of Sciences. Wang holds more than 170 issued and published patents. His research has been consistently funded by the National Institutes of Health, the National Science Foundation and General Electric, with total grants exceeding $40 million.