Ученые USC создали автоматизированную систему для анализа МРТ мозга животных в многоцентровых исследованиях инсультов

Researchers from the Mark and Mary Stevens Neuroimaging and Informatics Institute (Stevens INI) at the Keck School of Medicine of USC have developed an automated system that uses MRI to measure brain tissue changes in animal models for large, multicenter studies of experimental stroke treatments. By reducing variability among thousands of preclinical research scans from different sources, the automated system has the potential to improve the early-stage evaluation of new therapies. The open-source image analysis pipeline, described in a new study published in Imaging Neuroscience, was tested on scans from more than 2,000 mice and rats at six academic research centers. Its measurements closely matched those made by human experts and helped reduce variability associated with differences in MRI scanners and acquisition environments. The system was created for the National Institutes of Health-sponsored Stroke Preclinical Assessment Network (SPAN), which tests potential treatments for acute ischemic stroke in coordinated animal studies before the most promising therapies advance toward clinical trials. The Stevens INI serves as the informatics and data core for SPAN. Before a potential treatment can be tested in people, researchers need confidence that its effects have been measured rigorously and consistently. This pipeline gives us an objective and scalable way to assess brain injury across a large research network." Kirsten M. Lynch, PhD, assistant professor of research neurology and co-first author of the study Why promising stroke treatments fall short An ischemic stroke occurs when a blocked blood vessel cuts off blood and oxygen to part of the brain. Although many treatments have shown promise in laboratory studies, few have proved effective in patients. Differences in how early-stage studies are conducted and analyzed can make results difficult to reproduce or compare across research centers. Scientists have traditionally measured damage after an experimental stroke by removing the brain, staining tissue sections, and manually outlining injured areas. That process can distort tissue, depends partly on individual judgment, and captures only one point in time. MRI allows researchers to scan the same animal more than once, tracking early injury and swelling as well as tissue loss that develops later. But analyzing thousands of scans collected on different equipment creates another challenge. "The scale of SPAN made automation essential," said Ryan Cabeen, PhD, a computational scientist at the Stevens INI who led development of the imaging biomarker platform and who was co-first author of the study. "We needed a method that could process thousands of scans while applying the same rules to every image, regardless of where the data were collected." AI that researchers can understand The pipeline checks image quality, adjusts for scanner differences, identifies the brain, and measures injured tissue, swelling, displacement, and longer-term tissue loss. It uses a deep-learning model to separate the brain from surrounding bone, muscle, and other tissue. The system then applies transparent, rule-based methods to identify stroke damage rather than relying entirely on artificial intelligence. "We wanted researchers to understand how the results were produced," Lynch said. "A method can be highly automated without becoming a black box. The combination of deep learning and transparent image-processing rules gave us both robustness and interpretability." Measurements that match human experts The study included 2,442 mice and rats. More than 2,200 were scanned two days after an experimentally induced stroke, and 1,750 received another scan about one month later. When researchers compared the automated results with injuries manually outlined by imaging experts, the measurements showed extremely close agreement. The pipeline performed about as consistently with a human reviewer as two human reviewers did with each other. The system also reduced variation linked to different scanners and imaging environments, allowing the same analysis approach to work across all six research centers. The software successfully processed the vast majority of scans despite differences in species, equipment, magnetic field strength, and image quality. An open tool for collaborative research The researchers have made the software and MRI data publicly available so other groups can reproduce the findings and adapt the pipeline for future studies. The tool was designed for standardized animal models and is not intended to analyze the more varied stroke injuries seen in patients. However, its framework could be expanded to include additional imaging methods and measures of brain tissue outcomes. "Large, collaborative studies require tools that produce reliable results across institutions," said Arthur W. Toga, PhD, director of the Stevens INI and a co-author of the study. "By combining advanced imaging, artificial intelligence, data harmonization, and high-performance computing, this work provides a reproducible foundation for evaluating which experimental stroke treatments have the greatest potential to move toward clinical testing." Source: Journal reference: Lynch, K. M., et al. (2026) A robust and reproducible automated MRI pipeline for quantifying tissue outcomes after experimental stroke in multi-center preclinical networks. Imaging Neuroscience. DOI: 10.1162/IMAG.a.1328. https://direct.mit.edu/imag/article/doi/10.1162/IMAG.a.1328/137726/A-robust-and-reproducible-automated-MRI-pipeline