loading page

Label-free histological analysis of retrieved thrombi in acute ischemic stroke using optical diffraction tomography and deep learning
  • +7
  • Yoonjae Chung,
  • Geon Kim,
  • Ah-Rim Moon,
  • DongHun Ryu,
  • Herve Hugonnet,
  • Mahn Jae Lee,
  • DongSeong Shin,
  • Seung-Jae Lee,
  • Eek-Sung Lee,
  • Yongkeun Park
Yoonjae Chung
Korea Advanced Institute of Science and Technology
Author Profile
Geon Kim
Korea Advanced Institute of Science and Technology
Author Profile
Ah-Rim Moon
Soonchunhyang University Hospital Bucheon
Author Profile
DongHun Ryu
Korea Advanced Institute of Science and Technology
Author Profile
Herve Hugonnet
Korea Advanced Institute of Science and Technology
Author Profile
Mahn Jae Lee
Korea Advanced Institute of Science and Technology
Author Profile
DongSeong Shin
Soonchunhyang University Hospital Bucheon
Author Profile
Seung-Jae Lee
Soonchunhyang University Hospital Bucheon
Author Profile
Eek-Sung Lee
Soonchunhyang University Hospital Bucheon
Author Profile
Yongkeun Park
Korea Advanced Institute of Science and Technology

Corresponding Author:yk.park@kaist.ac.kr

Author Profile

Abstract

For patients with acute ischemic stroke, histological quantification of thrombus composition provides evidence for determining appropriate treatment. However, the traditional manual segmentation of stained thrombi is laborious and inconsistent. In this study, we propose a label-free method that combines optical diffraction tomography (ODT) and deep learning (DL) to automate the histological quantification process. The DL model classifies ODT image patches with 95% accuracy, and the collective prediction generates a whole-slide map of red blood cells and fibrin. The resulting whole-slide composition displays an average error of 1.1% and does not experience staining variability, facilitating faster analysis with reduced labor. The present approach will enable rapid and quantitative evaluation of blood clot composition, expediting the preclinical research and diagnosis of cardiovascular diseases.
27 Feb 2023Submitted to Journal of Biophotonics
28 Feb 2023Submission Checks Completed
28 Feb 2023Assigned to Editor
28 Feb 2023Review(s) Completed, Editorial Evaluation Pending
28 Feb 2023Reviewer(s) Assigned
03 May 2023Editorial Decision: Accept