I am an Associate Professor of Radiology and Electrical and Computer Engineering at Duke University. I am also a faculty in the Duke Medical Physics Program and a member of Duke Cancer Institute.

My main research focus is on applications of machine learning including deep learning and statistical modeling as well as computer vision algorithms to medicine. The particular focus in terms of applications is medical imaging in the context of cancer treatment as well as understanding image interpretation process and error-making in radiology.

One of the main research directions in my lab is imaging-based cancer biomarkers and radiogenomics. Specifically, our focus is on predicting patient outcomes in breast and brain cancers (lower and high grade gliomas) as well as finding associations of imaging features with molecular subtypes and other genomic markers for these cancers.


Another important research direction in my lab is development of human observer models that capture error-making patterns of the radiology trainees when they analyze medical images. The ultimate goal of this research is to reach a better understanding of decision and error making in radiologists and to construct an adaptive computer-aided education system for radiology.

The general goal we work toward in my lab is to combine rigorous algorithm development with the highest significance of the solved problems. Toward this goal, the lab members represent both, scientific and medical tracks and have included postdoctoral associates, medical residents and fellows, medical students, graduate students, visiting scholars, and undergraduate students.

My work has been funded by the National Institutes of Health, The US Deparment of Defense, Radiological Society of North America, industry, and Duke internal competitive grants.


Maciej A. Mazurowski, Ph.D.
Department of Radiology
Duke University

Tel: +1 (919) 684 1466
Fax: +1 (919) 684 1491
maciej(.dot)mazurowski(.at)duke(.dot)edu Twitter: @MAMazurowski