Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages.

Journal: Scientific reports
PMID: 34021170

Abstract

Cerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5-40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

Authors

  • Christian Crouzet
    Beckman Laser Institute and Medical Clinic, University of California-Irvine, Irvine, CA, USA.
  • Gwangjin Jeong
    Department of Biomedical Engineering, Beckman Laser Institute Korea, Dankook University, Cheonan, 31116, Republic of Korea.
  • Rachel H Chae
    Massachusetts Institute of Technology, Cambridge, MA, USA.
  • Krystal T LoPresti
    Beckman Laser Institute and Medical Clinic, University of California-Irvine, Irvine, CA, USA.
  • Cody E Dunn
    Beckman Laser Institute and Medical Clinic, University of California-Irvine, Irvine, CA, USA.
  • Danny F Xie
    Beckman Laser Institute and Medical Clinic, University of California-Irvine, Irvine, CA, USA.
  • Chiagoziem Agu
    Albany State University, Albany, GA, USA.
  • Chuo Fang
    Neurology and Pathology and Laboratory Medicine, University of California-Irvine, Irvine, CA, USA.
  • Ane C F Nunes
    Department of Medicine, Division of Nephrology, University of California-Irvine, Irvine, CA, USA.
  • Wei Ling Lau
    Division of Nephrology, Department of Medicine, University of California Irvine, Orange, California.
  • Sehwan Kim
    Department of Biomedical Engineering, Beckman Laser Institute Korea, Dankook University, Cheonan, 31116, Republic of Korea.
  • David H Cribbs
    Institute for Memory Impairments and Neurological Disorders, University of California-Irvine, Irvine, CA, USA.
  • Mark Fisher
    School of Computing Sciences, University of East Anglia, Norwich Research Park, Norwich, NR4 7TJ, UK. Electronic address: mark.fisher@uea.ac.uk.
  • Bernard Choi
    Beckman Laser Institute and Medical Clinic, University of California-Irvine, Irvine, CA, USA. choib@uci.edu.

Keywords

External Resources

Popular Topics
Recent Journals