Machine Learning–Enabled Quantification of Hepatocellular Necrosis in the Liver After Lethal Marburg and Ebola Virus Exposures
The Journal of Infectious Diseases · 2026
DOI: 10.1093/infdis/jiag040 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Infectious Diseases, 2026. Verfasst von Yanling Liu und 12 weiteren Autor:innen. Beteiligte Einrichtung: Integrated Data Sciences Section, Research Technologies Branch, Division of Intramural Research, National Institute of Allergy and Infectious Disease…. Hauptthemen laut MEDLINE: Liver, Hemorrhagic Fever, Ebola, Marburg Virus Disease, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, NCI NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
The liver is a key target of pathogenic Marburg and Ebola viruses (MARV and EBOV, respectively), with injury common in severe filovirid disease, yet high-resolution histopathologic quantification is lacking. We addressed this by deploying deep learning (DL) models for pixel-level quantitative analysis of digitized liver pathology slides in lethal rhesus monkey (RM) models of MARV and 2 EBOV variants, Makona and Kikwit. Our DL model segmented arteries, veins, bile ducts, and hepatic necrosis, achieving interobserver variability in necrosis segmentation comparable to that of 3 pathologists. DL-quantified liver necrosis correlated with exposure virus (f = 6.61, P = .006) and was highest in MARV-exposed RMs (11.0%). While filovirid-exposed RMs showed elevations in aspartate aminotransferase, alanine aminotransferase (ALT), gamma-glutamyl transferase, and alkaline phosphatase, only ALT levels correlated with necrosis severity. Necrosis localization differed—portal tract proximate after MARV exposure and central vein proximate after EBOV exposure. This proof-of-concept work enables future large-scale retrospective “meta-pathologic” analyses.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Integrated Data Sciences Section, Research Technologies Branch, Division of Intramural Research, National Institute of Allergy and Infectious Diseases, National Institutes of Health,Rockville, Maryland, USA.
- Integrated Research Facility at Fort Detrick, Division of Clinical Research, National Institute of Allergy and Infectious Diseases, National Institutes of Health,Frederick, Maryland, USA.
- Clinical Monitoring Research Program Directorate, Frederick National Laboratory for Cancer Research, Frederick, Maryland, USA.
ORCID-Profile: Winston T Chu, Daniel B Woodburn, Donna L Perry, Ian Crozier, C Paul Morris
Förderung
- NIH HHS
- NCI NIH HHS
- National Institutes of Health
- National Cancer Institute
Zitieren
APA
Liu, Y., Chu, W. T., Gilani, S. Q., Woodburn, D. B., Liu, D. X., Vinithakumari, A. A., Isic, N., Boshinski, A., Perry, D. L., Hischak, A., Solomon, J., Crozier, I., & Morris, C. P. (2026). Machine Learning–Enabled Quantification of Hepatocellular Necrosis in the Liver After Lethal Marburg and Ebola Virus Exposures. The Journal of Infectious Diseases. https://doi.org/10.1093/infdis/jiag040
Vancouver
Liu Y, Chu WT, Gilani SQ, Woodburn DB, Liu DX, Vinithakumari AA, et al. Machine Learning–Enabled Quantification of Hepatocellular Necrosis in the Liver After Lethal Marburg and Ebola Virus Exposures. The Journal of Infectious Diseases. 2026. doi:10.1093/infdis/jiag040
BibTeX
@article{Liu2026,
author = {Liu, Yanling and Chu, Winston T and Gilani, Syed Qasim and Woodburn, Daniel B and Liu, David X and Vinithakumari, Akhil A and Isic, Nejra and Boshinski, Amber and Perry, Donna L and Hischak, Amanda and Solomon, Jeffrey and Crozier, Ian and Morris, C Paul},
title = {Machine Learning–Enabled Quantification of Hepatocellular Necrosis in the Liver After Lethal Marburg and Ebola Virus Exposures},
journal = {The Journal of Infectious Diseases},
year = {2026},
doi = {10.1093/infdis/jiag040}
}
EUVIMED