Leveraging domain knowledge for synthetic ultrasound image generation: a novel approach to rare disease AI detection.

Journal: International journal of computer assisted radiology and surgery
PMID: 39739290

Abstract

PURPOSE: This study explores the use of deep generative models to create synthetic ultrasound images for the detection of hemarthrosis in hemophilia patients. Addressing the challenge of sparse datasets in rare disease diagnostics, the study aims to enhance AI model robustness and accuracy through the integration of domain knowledge into the synthetic image generation process.

Authors

  • M Mendez
    Institute of Medical Science, University of Toronto, Toronto, ON, Canada.
  • F Castillo
    Department of Medical Imaging, University of Toronto, Toronto, ONM5T 1W7, Canada.
  • L Probyn
    Department of Medical Imaging, University of Toronto, Toronto, ONM5T 1W7, Canada.
  • S Kras
    Mohawk College & McMaster Medical Radiation Sciences Program, McMaster University Mohawk College, Hamilton, ON, Canada.
  • P N Tyrrell
    Institute of Medical Science, University of Toronto, Toronto, ON, Canada. pascal.tyrrell@utoronto.ca.

Keywords

External Resources

Popular Topics
Recent Journals