Annotation burden reduction in deep learning for lensless imaging flow cytometry with a self-supervised pretext task Conferences uri icon

  •  
  • Overview
  •  
  • Research
  •  
  • Identity
  •  
  • Additional Document Info
  •  
  • View All
  •  

abstract

  • A self-supervised pretext task is developed based on flow profile and motion extraction for cell detection in a lensless imaging flow cytometer. It reduces the annotation burden, automatically selects usable frames, and improves detection performance.

publication date

  • 2023