Nick Konz

nick_kyoto_lowres.jpg

Email: nicholas (dot) konz (at) duke (dot) edu

I’m a Ph.D. candidate studying machine learning at Duke University under Prof. Maciej Mazurowski. My current research is in deep learning for medical image analysis; mainly domain adaptation, image translation and generation, and anomaly detection.

I’m also drawn to the intersection of ML and science: understanding deep learning from a scientific perspective, and the use of DL for scientific modeling & discovery and science-adjacent fields. I have also worked as a research intern in the Math, Stats, and Data Science Group at PNNL.

See my Google Scholar page for a full list of my publications, with a few recent papers highlighted in the section below.

My undergraduate degree was a double major in physics and mathematics at the University of North Carolina at Chapel Hill, where my research with Prof. Daniel Reichart was in statistical techniques for astronomy. I have been an educator in machine learning, physics, math and astronomy in the academic setting and beyond.

Selected Recent Papers

  1. Pre-processing and Compression: Understanding Hidden Representation Refinement Across Imaging Domains via Intrinsic Dimension
    Nicholas Konz, and Maciej A Mazurowski
    In NeurIPS (Advances in Neural Information Processing Systems): Workshop on Scientific Methods for Understanding Deep Learning, 2024
  2. The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images
    Nicholas Konz, and Maciej A Mazurowski
    In ICLR (The Twelfth International Conference on Learning Representations), 2024
  3. Anatomically-Controllable Medical Image Generation with Segmentation-Guided Diffusion Models
    Nicholas Konz, Yuwen Chen, Haoyu Dong, and 1 more author
    In MICCAI (International Conference on Medical Image Computing and Computer-Assisted Intervention), 2024
  4. Medical Image Segmentation with InTEnt: Integrated Entropy Weighting for Single Image Test-Time Adaptation
    Haoyu Dong, Nicholas Konz, Hanxue Gu, and 1 more author
    In CVPR (Conference on Computer Vision and Pattern Recognition): Workshop on Domain adaptation, Explainability, Fairness in AI for Medical Image Analysis (Oral), 2024
  5. Unsupervised anomaly localization in high-resolution breast scans using deep pluralistic image completion
    Nicholas Konz, Haoyu Dong, and Maciej A Mazurowski
    Medical Image Analysis, 2023