High-throughput label-free cell detection and counting from diffraction patterns with deep fully convolutional neural networks.

Journal: Journal of biomedical optics
Published Date:

Abstract

SIGNIFICANCE: Digital holographic microscopy (DHM) is a promising technique for the study of semitransparent biological specimen such as red blood cells (RBCs). It is important and meaningful to detect and count biological cells at the single cell level in biomedical images for biomarker discovery and disease diagnostics. However, the biological cell analysis based on phase information of images is inefficient due to the complexity of numerical phase reconstruction algorithm applied to raw hologram images. New cell study methods based on diffraction pattern directly are desirable.

Authors

  • Faliu Yi
    Quantitative Biomedical Research Center, Department of Clinical Sciences, University of Texas Southwestern Medical Center, 5325 Harry Hines Blvd, Dallas, TX, 75390, USA.
  • Seonghwan Park
    Daegu Gyeongbuk Institute of Science and Technology, Department of Robotics Engineering, Dalseong-gu, Republic of Korea.
  • Inkyu Moon
    Daegu Gyeongbuk Institute of Science and Technology, Department of Robotics Engineering, Dalseong-gu, Republic of Korea.