Maciej A Mazurowski

Associate Professor in Radiology

Appointments and Affiliations

  • Associate Professor in Radiology
  • Associate Professor in the Department of Electrical and Computer Engineering
  • Associate Professor in Biostatistics and Bioinformatics
  • Associate Professor of Computer Science
  • Member of the Duke Cancer Institute

Contact Information

  • Office Location: Dept of Radiology, Durham, NC 27710
  • Office Phone: (919) 684-1440
  • Email Address: maciej.mazurowski@duke.edu

Education

  • Ph.D. University of Louisville, 2008

Courses Taught

  • COMPSCI 393: Research Independent Study
  • ECE 899: Special Readings in Electrical Engineering

In the News

Representative Publications

  • Zhang, Y., and M. A. Mazurowski. “Convolutional neural networks rarely learn shape for semantic segmentation.” Pattern Recognition 146 (February 1, 2024). https://doi.org/10.1016/j.patcog.2023.110018.
  • Prabhu, Neel K., Megan K. Wong, Jacob A. Klapper, John C. Haney, Maciej A. Mazurowski, Joseph G. Mammarappallil, and Matthew G. Hartwig. “Computed Tomography Volumetrics for Size Matching in Lung Transplantation for Restrictive Disease.” Ann Thorac Surg 117, no. 2 (February 2024): 413–21. https://doi.org/10.1016/j.athoracsur.2023.03.033.
  • Zhang, Jikai, Carlos Santos, Christine Park, Maciej A. Mazurowski, and Roy Colglazier. “Improving Image Classification of Knee Radiographs: An Automated Image Labeling Approach.” J Digit Imaging 36, no. 6 (December 2023): 2402–10. https://doi.org/10.1007/s10278-023-00894-x.
  • Dong, Haoyu, Yifan Zhang, Hanxue Gu, Nicholas Konz, Yixin Zhang, and Maciej A. Mazurowski. “SWSSL: Sliding Window-Based Self-Supervised Learning for Anomaly Detection in High-Resolution Images.” IEEE Trans Med Imaging 42, no. 12 (December 2023): 3860–70. https://doi.org/10.1109/TMI.2023.3314318.
  • Mazurowski, Maciej A., Haoyu Dong, Hanxue Gu, Jichen Yang, Nicholas Konz, and Yixin Zhang. “Segment anything model for medical image analysis: An experimental study.” Med Image Anal 89 (October 2023): 102918. https://doi.org/10.1016/j.media.2023.102918.