StainAI: quantitative mapping of stained microglia and insights into brain-wide neuroinflammation and therapeutic effects in cardiac arrest

Authors

Chao-Hsiung Hsu, Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA.
Yi-Yu Hsu, Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA.
Be-Ming Chang, Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA.
Katherine Raffensperger, Center for Neuroscience Research, Children's National Research Institute, Washington, DC, USA.
Micah Kadden, Center for Neuroscience Research, Children's National Research Institute, Washington, DC, USA.
Hoai T. Ton, Center for Neuroscience Research, Children's National Research Institute, Washington, DC, USA.
Essiet-Adidiong Ette, Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA.
Stephen Lin, Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA.
Janiya Brooks, Department of Physiology and Biophysics, Howard University, Washington, DC, USA.
Mark W. Burke, Department of Physiology and Biophysics, Howard University, Washington, DC, USA.
Yih-Jing Lee, School of Medicine, Fu-Jen Catholic University, New Taipei City, Taiwan.
Paul C. Wang, Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA.
Michael Shoykhet, Center for Neuroscience Research, Children's National Research Institute, Washington, DC, USA.
Tsang-Wei Tu, Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA. tsangwei.tu@howard.edu.

Document Type

Journal Article

Publication Date

3-20-2025

Journal

Communications biology

Volume

8

Issue

1

DOI

10.1038/s42003-025-07926-y

Abstract

Microglia, the brain's resident macrophages, participate in development and influence neuroinflammation, which is characteristic of multiple brain pathologies. Diverse insults cause microglia to alter their morphology from "resting" to "activated" shapes, which vary with stimulus type, brain location, and microenvironment. This morphologic diversity commonly restricts microglial analyses to specific regions and manual methods. We introduce StainAI, a deep learning tool that leverages 20x whole-slide immunohistochemistry images for rapid, high-throughput analysis of microglial morphology. StainAI maps microglia to a brain atlas, classifies their morphology, quantifies morphometric features, and computes an activation score for any region of interest. As a proof of principle, StainAI was applied to a rat model of pediatric asphyxial cardiac arrest, accurately classifying millions of microglia across multiple slices, surpassing current methods by orders of magnitude, and identifying both known and novel activation patterns. Extending its application to a non-human primate model of simian immunodeficiency virus infection further demonstrated its generalizability beyond rodent datasets, providing new insights into microglial responses across species. StainAI offers a scalable, high-throughput solution for microglial analysis from routine immunohistochemistry images, accelerating research in microglial biology and neuroinflammation.

Department

Pediatrics

Share

COinS