EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A machine learning approach to automate microinfarct and microhemorrhage screening in hematoxylin and eosin-stained human brain tissues

Luca Cerny Oliveira iD, Joohi Chauhan, Ajinkya Chaudhari, Sen-Ching S Cheung, Viharkumar Patel, Amparo C Villablanca, Lee-Way Jin, Charles DeCarli, Chen-Nee Chuah iD, Brittany N Dugger iD

Journal of Neuropathology & Experimental Neurology · 01.02.2025 · 84 (2) · 114-125

DOI: 10.1093/jnen/nlae120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neuropathology & Experimental Neurology, online erschienen am 26.12.2024. Verfasst von Luca Cerny Oliveira und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of California Davis, Davis, CA, United States. Hauptthemen laut MEDLINE: Machine Learning, Brain, Cerebral Hemorrhage, Brain Infarction. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: April Krueger v. Wyeth, Inc., Case, Frances Lazda Endowed Chair in Women's Cardiovascular Medicine, NIA NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Microinfarcts and microhemorrhages are characteristic lesions of cerebrovascular disease. Although multiple studies have been published, there is no one universal standard criteria for the neuropathological assessment of cerebrovascular disease. In this study, we propose a novel application of machine learning in the automated screening of microinfarcts and microhemorrhages. Utilizing whole slide images (WSIs) from postmortem human brain samples, we adapted a patch-based pipeline with convolutional neural networks. Our cohort consisted of 22 cases from the University of California Davis Alzheimer’s Disease Research Center brain bank with hematoxylin and eosin-stained formalin-fixed, paraffin-embedded sections across 3 anatomical areas: frontal, parietal, and occipital lobes (40 WSIs with microinfarcts and/or microhemorrhages, 26 without). We propose a multiple field-of-view prediction step to mitigate false positives. We report screening performance (ie, the ability to distinguish microinfarct/microhemorrhage-positive from microinfarct/microhemorrhage-negative WSIs), and detection performance (ie, the ability to localize the affected regions within a WSI). Our proposed approach improved detection precision and screening accuracy by reducing false positives thereby achieving 100% screening accuracy. Although this sample size is small, this pipeline provides a proof-of-concept for high efficacy in screening for characteristic brain changes of cerebrovascular disease to aid in screening of microinfarcts/microhemorrhages at the WSI level.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningBrainCerebral HemorrhageBrain InfarctionHumansMaleAgedFemaleAged, 80 and overHematoxylinEosine Yellowish-(YS)Middle AgedStaining and Labeling

Stichwörter der Autor:innen

deep learningdigital pathologyhistologyinfarctsvascular dementia

Substanzen

HematoxylinEosine Yellowish-(YS)

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, University of California Davis, Davis, CA, United States.
  • Department of Pathology and Laboratory Medicine, University of California Davis, Sacramento, CA, United States.
  • Department of Electrical and Computer Engineering, University of Kentucky, Lexington, KY, United States.
  • Department of Internal Medicine, University of California Davis, Davis, CA, United States.

ORCID-Profile: Luca Cerny Oliveira, Chen-Nee Chuah, Brittany N Dugger

Förderung

  • April Krueger v. Wyeth, Inc., Case
  • Frances Lazda Endowed Chair in Women's Cardiovascular Medicine
  • NIA NIH HHS
  • NIH HHS
  • National Institute on Aging of the National Institutes of Health
  • US District Court
  • BrEast and BrAin Heath Equity Research
  • National Institute on Aging

Zitieren

APA

Cerny Oliveira, L., Chauhan, J., Chaudhari, A., Cheung, S. S., Patel, V., Villablanca, A. C., Jin, L. W., DeCarli, C., Chuah, C. N., & Dugger, B. N. (2025). A machine learning approach to automate microinfarct and microhemorrhage screening in hematoxylin and eosin-stained human brain tissues. Journal of Neuropathology & Experimental Neurology, 84(2), 114-125. https://doi.org/10.1093/jnen/nlae120

Vancouver

Cerny Oliveira L, Chauhan J, Chaudhari A, Cheung SS, Patel V, Villablanca AC, et al. A machine learning approach to automate microinfarct and microhemorrhage screening in hematoxylin and eosin-stained human brain tissues. Journal of Neuropathology & Experimental Neurology. 2025;84(2):114-125. doi:10.1093/jnen/nlae120

BibTeX
@article{CernyOliveira2025,
  author = {Cerny Oliveira, Luca and Chauhan, Joohi and Chaudhari, Ajinkya and Cheung, Sen-Ching S and Patel, Viharkumar and Villablanca, Amparo C and Jin, Lee-Way and DeCarli, Charles and Chuah, Chen-Nee and Dugger, Brittany N},
  title = {A machine learning approach to automate microinfarct and microhemorrhage screening in hematoxylin and eosin-stained human brain tissues},
  journal = {Journal of Neuropathology & Experimental Neurology},
  year = {2025},
  volume = {84},
  number = {2},
  pages = {114--125},
  doi = {10.1093/jnen/nlae120}
}
Kostenlos starten →