Conference
Annotation burden reduction in deep learning for lensless imaging flow cytometry with a self-supervised pretext task
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.
Authors
Hong T; Fang Q
Publisher
Optica Publishing Group
DOI
10.1364/boda.2023.jtu4b.12
Name of conference
Biophotonics Congress: Optics in the Life Sciences 2023 (OMA, NTM, BODA, OMP, BRAIN)