AI Metrics
Andrew Smith, M.D., Ph.D., is an abdominal radiologist and oncologic imager at the University of Alabama at Birmingham. He serves as vice chair of Clinical Research, chief of Body CT, and director of Artificial Intelligence, Tumor Metrics, and Entrepreneurship in Radiology. Dr. Smith completed a radiology residency and fellowship at the Cleveland Clinic. Dr. Smith divides his time between clinical research and clinical radiology, with expertise in body, oncologic, and aortic imaging, including radiographs, CT, MRI, PET imaging, oncologic imaging, ultrasound, and fluoroscopy.
Dr. Smith’s research expertise is in AI algorithm development, advanced cancer response assessment, and CT imaging biomarkers for cancer response assessment and chronic liver disease. He has multiple U.S. and international patents (pending and issued) related to advancements in radiology. Dr. Smith has been the primary investigator on multiple grants, including NIH small business grants and industry-sponsored grants. He has run multiple retrospective and prospective clinical studies, including several multi-institutional studies, and he has mentored numerous students, residents, fellows, and research scientists and faculty.
At a national level, Dr. Smith is a fellow of the Society of Abdominal Radiology (SAR) and Society of Advanced Body Imaging (SABI). He is co-chair of the SAR Emerging Technology Commission on Artificial Intelligence and serves on several committees and panels for academic and clinical societies within the radiology profession including the SAR Disease-Focused Panels on Hepatic Fibrosis and Renal Cell Carcinoma. Smith is active in multiple national organizations and is an editorial member of Radiology and reviewer for numerous national and international academic journals.
This person is not in any offices
AI Metrics
1 followers
AI Metrics brings innovative imaging software to the radiology market, powered by creative thinking, deep expertise in clinical and research environments, and a passion for crafting the tools radiologists need today to read studies faster, with higher accuracy, vastly reduced variability between studies, and robust (data-centered) output.