Pranav Kulkarni

prof_pic.jpg

6116 Executive Blvd, Suite 200
North Bethesda, MD 20852
pranavk [at] umd.edu

Hi! I am an incoming CS Ph.D. student at the University of Maryland, advised by Heng Huang. Currently, I am a bioinformatics software engineer at the University of Maryland Institute for Health Computing (UM-IHC), where I build user-friendly tools for visualizing and analyzing biomedical data.

My research is primarily focused on the intersection of machine learning, computer vision, and medical imaging, with the goal of enabling opportunistic screening for early-stage, low-cost disease detection. I am currently interested in 1️⃣ Multi-modal foundation models that integrate imaging, clinical, and multi-omics data; 2️⃣ Federated learning methods to leverage distributed, heterogeneous data while preserving privacy; and 3️⃣ Trustworthy and explainable AI systems that adapt to distribution shifts over time, align with nuanced human feedback, and mitigate algorithmic bias.

In my free time, I enjoy hiking, gardening, and reading about history, biogeography, and urban planning!

Recent News

May 2025 A review article that I co-authored has been published in Radiology.
Apr 2025 Received UM-IHC Travel Award to support my travel for MIDL’25.
Mar 2025 Two papers accepted at MIDL’25 in Salt Lake City.
Mar 2025 A book chapter that I co-authored for the MICCAI Society’s Book on Federated learning for Medical Imaging has been published.
Mar 2025 One tiny paper accepted at ICLR’25 Workshop on Bidirectional Human-AI Alignment in Singapore.
Feb 2025 One paper published in the American Journal of Roentgenology.
Nov 2024 One paper accepted at ML4H’24 in Vancouver.
Oct 2024 Three papers published in the Journal of Imaging Informatics in Medicine.
Jul 2024 One paper accepted for oral presentation at IEEE QCE’24 in Montreal.
Jul 2024 My first-authored paper was acknowledged as the second Most Reproducible Paper at MIDL’24.

Selected Publications

  1. Review Article
    Pitfalls and Best Practices in Evaluation of Algorithmic Biases in Radiology
    Paul H. Yi, Preetham Bachina, Beepul Bharti, Sean P. Garin, Adway Kanhere, Pranav Kulkarni, David Li, Vishwa S. Parekh, Samantha M. Santomartino, Linda Moy, and Jeremias Sulam
    Radiology, 315(2), e241674. May 2025
    HTML PDF
  2. From Isolation to Collaboration: Federated Class-Heterogeneous Learning for Chest X-Ray Classification
    Pranav Kulkarni, Adway Kanhere, Paul H. Yi, and Vishwa S. Parekh
    In Machine Learning for Health Symposium (ML4H), 623–635. Dec 2024
    HTML PDF Code arXiv
  3. Oral
    Hidden in Plain Sight: Undetectable Adversarial Bias Attacks on Vulnerable Patient Populations
    Pranav Kulkarni, Andrew Chan, Nithya Navarathna, Skylar Chan, Paul H. Yi, and Vishwa S. Parekh
    In Medical Imaging with Deep Learning (MIDL), 793–821. Jul 2024
    HTML PDF Code arXiv
  4. Best Poster Award
    Privacy-Preserving Collaboration for Multi-Organ Segmentation via Federated Learning from Sites with Partial Labels
    Adway Kanhere, Pranav Kulkarni, Paul H. Yi, and Vishwa S. Parekh
    In CVPR Workshop on Data Curation and Augmentation in Medical Imaging (CVPR DCA-in-MI), 2380–2387. Jun 2024
    HTML PDF Code arXiv