Dr. Sohn is a cardiothoracic radiologist focusing on lung cancer and interstitial lung disease imaging with technical emphasis on machine learning, quantitative imaging, radiological natural language processing, and clinical translation of 0.55T low-field lung MRI. As a physician with engineering background, he has been broadly involved in projects that use mathematical and engineering techniques to tackle research questions in radiology.

His work has received media coverage from Washington Post, Times UK, Scientific American, AuntMinnie Newsletter, and others. He participated in machine learning competitions, scoring top 2% in the Kaggle Data Science Bowl for lung cancer detection. He has won the global oncology award from the Stanford Health++ hackathon.

He is an education co-chair of the UCSF Center for Intelligent Imaging, and mentors undergraduate, medical students, residents, scientists, and engineers who wish to learn about data science projects in radiology. A diverse group of students have joined the team from around the world (given the remote nature of many projects in the group). Many have won the RSNA trainee research prizes, RSNA certificate of merit awards, and scholarships. They are currently at leading CS PhD programs, medical schools, and data science companies, conducting data science projects in radiology.

Current research projects span lung cancer screening, interstitial lung abnormality, big data based imaging biomarker discovery in chest imaging, clinical translation of 0.55T Lung MRI, radiological text processing, content based image retrieval, similar image and text query, and integration of machine learning innovations to clinical radiology practice. Examples projects include longitudinal lung nodule tracking & characterization from chest CT, patient level lung cancer risk stratification in lung cancer screening, generation of radiology specific word embedding, automated radiology protocoling, automated detection of urgent findings from radiology text report, and prediction of healthcare cost from chest radiographs.

The team seeks interested students, scientists, engineers, and post-doctoral scholars. Please reach out with a CV and any areas or projects of interest.