Nick Konz

nick_kyoto_lowres.jpg

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

Bluesky 🦋: @nickkonz.bsky.social

I’m a Ph.D. candidate studying machine learning at Duke University under Maciej Mazurowski. My current research is in deep learning for medical image analysis, in topics like domain adaptation, image-to-image translation, and image generation. Broadly, I’m interested in how foundational machine learning concepts, such as generalization, intrinsic geometric dataset properties, and image distribution distance metrics behave differently or should be adapted in the context of medical image analysis (or other secondary computer vision domains).

Additionally, I’m 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. My undergrad was at UNC in physics and math, with research in statistical techniques for astronomy.

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

On my free time I like to practice jiu-jitsu and yoga, cook, listen to and play music, and read.

Selected Papers

  1. rad.png
    RaD: A Metric for Medical Image Distribution Comparison in Out-of-Domain Detection and Other Applications
    Nicholas Konz, Yuwen Chen, Hanxue Gu, and 3 more authors
    arXiv preprint, 2024
  2. samfailure.png
    Quantifying the Limits of Segment Anything Model: Analyzing Challenges in Segmenting Tree-Like and Low-Contrast Structures
    Yixin Zhang*, Nicholas Konz*, Kevin Kramer, and 1 more author
    arXiv preprint, 2024
  3. sciforDL24.png
    Pre-processing and Compression: Understanding Hidden Representation Refinement Across Imaging Domains via Intrinsic Dimension
    Nicholas Konz, and Maciej A. Mazurowski
    SciForDL @ NeurIPS, 2024
  4. segdiff.png
    Anatomically-Controllable Medical Image Generation with Segmentation-Guided Diffusion Models
    Nicholas Konz, Yuwen Chen, Haoyu Dong, and 1 more author
    MICCAI, 2024
  5. iclr24.png
    The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images
    Nicholas Konz, and Maciej A. Mazurowski
    ICLR, 2024
  6. intent.png
    Medical Image Segmentation with InTEnt: Integrated Entropy Weighting for Single Image Test-Time Adaptation
    Haoyu Dong, Nicholas Konz, Hanxue Gu, and 1 more author
    DEF-AI-MIA @ CVPR (Oral), 2024
  7. midl24.png
    Rethinking Perceptual Metrics for Medical Image Translation
    Nicholas Konz, Yuwen Chen, Hanxue Gu, and 2 more authors
    MIDL, 2024
  8. picard.png
    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
  9. attrib.png
    Attributing Learned Concepts in Neural Networks to Training Data
    Nicholas Konz, Charles Godfrey, Madelyn Shapiro, and 3 more authors
    ATTRIB @ NeurIPS (Oral), 2023
  10. emnlp23.png
    Understanding the Inner-workings of Language Models Through Representation Dissimilarity
    Davis Brown, Charles Godfrey, Nicholas Konz, and 2 more authors
    EMNLP, 2023
  11. sam23.png
    Segment anything model for medical image analysis: an experimental study
    Maciej A. Mazurowski, Haoyu Dong, Hanxue Gu, and 3 more authors
    Medical Image Analysis, 2023
  12. midl23.png
    Reverse engineering breast mris: Predicting acquisition parameters directly from images
    Nicholas Konz, and Maciej A. Mazurowski
    MIDL, 2023
  13. dbtex.png
    A competition, benchmark, code, and data for using artificial intelligence to detect lesions in digital breast tomosynthesis
    Nicholas Konz, Mateusz Buda, Hanxue Gu, and 8 more authors
    JAMA Network Open, 2023
  14. swssl.png
    SWSSL: Sliding window-based self-supervised learning for anomaly detection in high-resolution images
    Haoyu Dong, Yifan Zhang, Hanxue Gu, and 3 more authors
    IEEE Transactions on Medical Imaging, 2023
  15. miccai22.png
    The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning
    Nicholas Konz, Hanxue Gu, Haoyu Dong, and 1 more author
    MICCAI, 2022
  16. rcr.png
    Robust chauvenet outlier rejection
    MP Maples, DE Reichart, Nicholas Konz, and 7 more authors
    The Astrophysical Journal Supplement Series, 2018