Kyle Jon Lafata

Thaddeus V. Samulski Assistant Professor of Radiation Oncology

Kyle Lafata is the Thaddeus V. Samulski Assistant Professor at Duke University in the Departments of Radiation Oncology, Radiology, Medical Physics, and Electrical & Computer Engineering. After earning his PhD in Medical Physics in 2018, he completed postdoctoral training at the U.S. Department of Veterans Affairs in the Big Data Scientist Training Enhancement Program. Prof. Lafata has broad expertise in imaging science, digital pathology, computer vision, biophysics, and applied mathematics. His dissertation work focused on the applied analysis of stochastic differential equations and high-dimensional radiomic phenotyping, where he developed physics-based computational methods and soft-computing paradigms to interrogate images. These included stochastic modeling, self-organization, and quantum machine learning (i.e., an emerging branch of research that explores the methodological and structural similarities between quantum systems and learning systems). 

Prof. Lafata has worked in various areas of computational medicine and biology, resulting in 39 peer-reviewed journal publications, 15 invited talks, and more than 50 national conference presentations. At Duke, the Lafata Lab focuses on the theory, development, and application of multiscale computational biomarkers. Using computational and mathematical methods, they study the appearance and behavior of disease across different physical length-scales (i.e., radiomics ~10−3 m, pathomics ~10−6 m, and genomics ~10−9 m) and time-scales (e.g., the natural history of disease, response to treatment). The overarching goal of the lab is to develop and apply new technology that transforms imaging into basic science findings and computational biomarker discovery.

Appointments and Affiliations

  • Thaddeus V. Samulski Assistant Professor of Radiation Oncology
  • Associate Professor of Radiation Oncology
  • Assistant Professor in Radiology
  • Assistant Professor in the Department of Electrical and Computer Engineering
  • Assistant Professor of Pathology
  • Member of the Duke Cancer Institute

Contact Information

  • Office Location: Radiation Physics, Box 3295 DUMC, Durham, NC 27710
  • Office Phone: (978) 491-8730
  • Email Address: kyle.lafata@duke.edu
  • Websites:

Education

  • Ph.D. Duke University, 2018
  • C. Duke University, 2018
  • Duke University School of Medicine, 2020

Research Interests

Biomedical imaging, image processing, computer vision, computational pathology, applied analysis of stochastic differential equations, high dimensional data analysis, feature engineering, adaptive imaging, multi-scale data fusion, Uncertainty Quantification

Courses Taught

  • ECE 392: Projects in Electrical and Computer Engineering
  • ECE 493: Projects in Electrical and Computer Engineering
  • ECE 494: Projects in Electrical and Computer Engineering
  • ECE 891: Internship
  • MEDPHY 507: Radiation Biology
  • MEDPHY 791: Independent Study in Medical Physics

Representative Publications

  • Kreiss, L., S. Jiang, X. Li, S. Xu, K. C. Zhou, K. C. Lee, A. Mühlberg, et al. “Digital staining in optical microscopy using deep learning - a review (Accepted).” PhotoniX 4, no. 1 (December 1, 2023). https://doi.org/10.1186/s43074-023-00113-4.
  • Yang, Zhenyu, Kyle Lafata, Eugene Vaios, Zongsheng Hu, Trey Mullikin, Fang- Fang Yin, and Chunhao Wang. “Quantifying U-Net uncertainty in multi-parametric MRI-based glioma segmentation by spherical image projection.” Med Phys, September 11, 2023. https://doi.org/10.1002/mp.16695.
  • Yang, Zhenyu, Zongsheng Hu, Hangjie Ji, Kyle Lafata, Eugene Vaios, Scott Floyd, Fang-Fang Yin, and Chunhao Wang. “A neural ordinary differential equation model for visualizing deep neural network behaviors in multi-parametric MRI-based glioma segmentation.” In Med Phys, 50:4825–38, 2023. https://doi.org/10.1002/mp.16286.
  • Kelleher, Colm B., Jacob Macdonald, Tracy A. Jaffe, Brian C. Allen, Kevin R. Kalisz, Travis H. Kauffman, Jordan D. Smith, et al. “A Faster Prostate MRI: Comparing a Novel Denoised, Single-Average T2 Sequence to the Conventional Multiaverage T2 Sequence Regarding Lesion Detection and PI-RADS Score Assessment.” J Magn Reson Imaging 58, no. 2 (August 2023): 620–29. https://doi.org/10.1002/jmri.28577.
  • Rigiroli, Francesca, Jocelyn Hoye, Reginald Lerebours, Peijie Lyu, Kyle J. Lafata, Anru R. Zhang, Alaattin Erkanli, et al. “Exploratory analysis of mesenteric-portal axis CT radiomic features for survival prediction of patients with pancreatic ductal adenocarcinoma.” Eur Radiol 33, no. 8 (August 2023): 5779–91. https://doi.org/10.1007/s00330-023-09532-0.