Dr. Jae Sohn is a radiologist who specializes in cardiothoracic (heart and chest) imaging.
Sohn has a special interest in the intersection of radiology and big data (extremely large data collections whose analysis requires advanced computer capability). He is specifically interested in natural language processing and cardiothoracic imaging. As a doctor with an engineering background, he has been involved in projects that use mathematical techniques to tackle research questions in radiology. His current research projects involve natural language processing, biomarker discovery in chest imaging for lung cancer, deep survival analysis, and the integration of machine learning innovations into patient care in radiology.
Sohn completed his medical degree at the Geisel School of Medicine at Dartmouth College. At UCSF, he completed a residency in diagnostic radiology, a research fellowship in big data and radiology, and a fellowship in cardiothoracic imaging. He also has a master's degree in applied mathematics from Johns Hopkins University.
Sohn co-founded a research team focused on big data in radiology that is now part of the UCSF Center for Intelligent Imaging. He mentors undergraduate and medical students from around the world who wish to pursue data science projects in radiology.
Sohn's work has earned coverage in the Washington Post, the United Kingdom's Times, Scientific American, AuntMinnie.com (a site for medical imaging professionals) and other publications. He enjoys participating in machine learning competitions, and scored in the top 2 percent in the Kaggle Data Science Bowl for lung cancer detection. He has won the global oncology award in the Stanford Health++ hackathon.