Ge Wang is Clark & Crossan Endowed Chair Professor and Director of the Biomedical Imaging Center at Rensselaer Polytechnic Institute. His interests include medical imaging and artificial intelligence especially deep learning. Wang published the first spiral cone-beam/multi-slice CT method in 1991 and has systematically contributed many papers and patents in this area. Also, his group and collaborators developed interior tomography theory to solve the long-standing interior problem, and initiated research of omni-tomography with simultaneous CT-MRI as an example. In 2016, he published the first perspective on deep learning-based tomographic imaging, lead-edited the first and second IEEE TMI special issues on the theme of deep reconstruction, and with his coauthors wrote the first book on deep learning-based tomography and a series of papers on various deep imaging topics. His results were featured in Nature, Science, PNAS, and news media. He is Fellow of IEEE, SPIE, AAPM, OSA, AIMBE, AAAS, and NAI, and received the 2021 IEEE EMBS Academic Career Achievement Award and the 2021 IEEE Region 1 Outstanding Teaching Award.

• Biomedical Imaging Center
• WANG-AXIS Lab
• Google Scholar
• ORCID
• Publons

Highlights

• First paper on spiral/helical cone-beam/multi-slice CT (1991) solving "the long object problem" (longitudinal data truncation). There are ~200-million CT scans annually worldwide, with a majority in the spiral cone-beam/multi-slice mode. Many follow-up papers of ours along this direction, including superiority of spiral fan-beam CT over step-and-shoot CT (1994) and triple-source helical cone-beam reconstruction (2010)
• Bioluminescence tomography (2004) for optical preclinical & biological imaging
• Interior tomography (2007) solving the interior problem (transverse data truncation) for targeted imaging at low dose, and fast speed
• State-of-the-art multi-scale CT facility (2009) covering six orders of magnitude in terms of image resolution & object size
• Omni-tomography (2011) for spatiotemporal fusion of tomographic modalities, with simultaneous CT-MRI as an example
• Spectrography (2011) for ultrafast & ultrafine tomography from polychromatic radiation scattering (In Focus News in Nature)
• Axiomatic bibliometrics (2013) to credit coauthors (PNAS)
• Deep imaging perspective (2016) as a basis for the first (2018) and second TMI Special Issues (2021) in this emerging field
• IOP textbook on machine learning for tomographic reconstruction (410 pages, 2019)
• National Academy of Inventors (2019, inducted for contributions to spiral cone-beam/multi-slice CT)
• Deep denoising network (2019) competitive over commercial low-dose CT (Nature Machine Intelligence)
• Deep tomographic reconstruction (2020) (Nature Machine Intelligence)
• Deep radiomics (2021) predicting heart diseases with low-dose lung CT (Nature Communications)
• IOP Book Series Editor "AI in Biomedicine" (2021-)
• Best image clustering result in the world with our SPICE network (https://paperswithcode.com; 2021)
• Various academic awards, including the 2021 IEEE EMBS Academic Career Achievement Award and the 2021 IEEE Region 1 Outstanding Teaching Award
• Data: In addition to many conference/arXiv papers, Wang has >500 journal papers (1 in Nature (also reported in Nature as “In Focus News”), 2 in Nature Machine Intelligence, 1 in Nature Communications, 3 in PNAS, 1 in J of Informetrics (reported in Science and Nature respectively), 1 in Phys. Rev. Letters, and >80 in IEEE journals), Google h-index=78, >100 issued and pending patents, >$40M as PI/Contact PI/MPI, and >$30M as Co-PI/Co-I/Mentor
• Stories: AI@NIH ('18), MRI, AI-Plenary, AI-Keynote, CT4Layman, AI@Stanford, AI-Stability, SPIE Plenary, SPIE Plenary Interview, Shanghai Tech BME