Label-free histological analysis of retrieved thrombi in acute ischemic stroke using optical diffraction tomography and deep learning.

Autor: Chung Y; Department of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea.; Department of Physics, KAIST, Daejeon, Republic of Korea., Kim G; Department of Physics, KAIST, Daejeon, Republic of Korea.; KAIST Institute for Health Science and Technology, KAIST, Daejeon, Republic of Korea., Moon AR; Department of Pathology, Soonchunhyang University Bucheon Hospital, Bucheon, Republic of Korea., Ryu D; Department of Physics, KAIST, Daejeon, Republic of Korea., Hugonnet H; Department of Physics, KAIST, Daejeon, Republic of Korea.; KAIST Institute for Health Science and Technology, KAIST, Daejeon, Republic of Korea., Lee MJ; Graduate School of Medical Science and Engineering, KAIST, Daejeon, Republic of Korea., Shin D; Department of Neurosurgery, Soonchunhyang University Bucheon Hospital, Bucheon, Republic of Korea., Lee SJ; Department of Neurology, Soonchunhyang University Bucheon Hospital, Bucheon, Republic of Korea., Lee ES; Department of Neurology, Soonchunhyang University Bucheon Hospital, Bucheon, Republic of Korea., Park Y; Department of Physics, KAIST, Daejeon, Republic of Korea.; Tomocube Inc., Daejeon, Republic of Korea.
Jazyk: angličtina
Zdroj: Journal of biophotonics [J Biophotonics] 2023 Aug; Vol. 16 (8), pp. e202300067. Date of Electronic Publication: 2023 Jun 05.
DOI: 10.1002/jbio.202300067
Abstrakt: 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.
(© 2023 Wiley-VCH GmbH.)
Databáze: MEDLINE
Externí odkaz: