← Back to Our Team
Arianna Bunnell

Arianna Bunnell

PhD Student

I’m a PhD student in the Computer Science (ICS) department at the University of Hawai’i. I have Bachelors degrees in Statistics and Computer Science, and am passionate about the application of data science to healthcare. I currently work as a Research Assistant in the UH Machine Learning Lab, working in applied ML. My work with the Shepherd Research Lab focuses on applying deep learning to breast ultrasound imaging.

Publications (13)

  • Deep Learning Enables Large-Scale Shape and Appearance Modeling in Total-Body DXA Imaging
    Bunnell A, Cataldi D, Glaser Y, Wolfgruber T, Heymsfield SB, Zonderman AB, Kelly TL, Sadowski P, Shepherd J
    Lecture notes in computer science, 2025· doi:10.1007/978-3-032-06774-6_20
  • Artificial intelligence-enhanced handheld breast ultrasound for screening: A systematic review of diagnostic test accuracy
    Bunnell A, Valdez D, Strand F, Glaser Y, Sadowski P, Shepherd J
    PLOS Digital Health, 2025· doi:10.1371/journal.pdig.0001019
  • Prediction of mammographic breast density based on clinical breast ultrasound images using deep learning: a retrospective analysis
    Bunnell A, Valdez D, Wolfgruber T, Quon BK, Hung K, Hernandez BY, Seto TB, Killeen J, Miyoshi M, Sadowski P, Shepherd J
    The Lancet Regional Health - Americas, 2025· doi:10.1016/j.lana.2025.101096
  • BUSClean: Open-source software for breast ultrasound image pre-processing and knowledge extraction for medical AI
    Bunnell A, Hung K, Shepherd JA, Sadowski P
    PLOS ONE, 2024· doi:10.1371/journal.pone.0315434
  • Artificial Intelligence-Informed Handheld Breast Ultrasound for Screening: A Systematic Review of Diagnostic Test Accuracy
    Bunnell A, Valdez D, Strand F, Glaser Y, Sadowski P, Shepherd J
    arXiv (Cornell University), 2024· doi:10.48550/arxiv.2411.07322
  • Deep Learning Predicts Mammographic Breast Density in Clinical Breast Ultrasound Images
    Bunnell A, Valdez D, Wolfgruber T, Quon BK, Hung K, Hernandez BY, Seto TB, Killeen J, Marshall M, Sadowski P, Shepherd J
    arXiv (Cornell University), 2024· doi:10.48550/arxiv.2411.00891
  • Abstract PO5-08-12: Ethnic Admixture Affects Breast Cancer Incidence in Native Hawaiians: The Multiethnic Cohort
    Valdez D, Bunnell A, Bogumil D, Maskarinec G, Shepherd J
    Cancer Research, 2024· doi:10.1158/1538-7445.sabcs23-po5-08-12
  • Abstract 3449: Is AI-enhanced breast ultrasound ready for breast cancer screening in low-resource environments? A systematic review
    Bunnell A, Valdez D, Strand F, Glaser Y, Sadowski P, Shepherd J
    Cancer Research, 2024· doi:10.1158/1538-7445.am2024-3449
  • Performance of Progressive Generations of GPT on an Exam Designed for Certifying Physicians as Certified Clinical Densitometrists
    Valdez D, Bunnell A, Lim SY, Sadowski P, Shepherd J
    Journal of Clinical Densitometry, 2024· doi:10.1016/j.jocd.2024.101480
  • Learning a Clinically-Relevant Concept Bottleneck for Lesion Detection in Breast Ultrasound
    Bunnell A, Glaser Y, Valdez D, Wolfgruber T, Altamirano A, González CZ, Hernandez BY, Sadowski P, Shepherd J
    Lecture notes in computer science, 2024· doi:10.1007/978-3-031-72384-1_61
  • Performance of progressive generations of GPT on an exam designed for certifying physicians as Certified Clinical Densitometrists (Preprint)
    Valdez D, Bunnell A, Lim SY, Sadowski P, Shepherd J
    , 2023· doi:10.2196/preprints.49529
  • Abstract P3-03-02: Can artificial intelligence derived ultrasound breast density provide comparable breast cancer risk estimates to density derived from mammograms
    Valdez D, Bunnell A, Wolfgruber T, Altamirano A, Quon BK, Maskarinec G, Sadowski P, Shepherd J
    Cancer Research, 2023· doi:10.1158/1538-7445.sabcs22-p3-03-02
  • Abstract P3-04-05: Artificial Intelligence Detects, Classifies, and Describes Lesions in Clinical Breast Ultrasound Images
    Bunnell A, Valdez D, Wolfgruber T, Altamirano A, Hernandez BY, Sadowski P, Shepherd J
    Cancer Research, 2023· doi:10.1158/1538-7445.sabcs22-p3-04-05

Stay in the loop

New publications, study announcements, and research updates — occasional, no spam.