| Autor: |
Hsu CH; Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA., Agaronyan A; Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA., Katherine R; Department of Critical Care Medicine, Children's National Hospital, Washington, DC, USA., Kadden M; Department of Critical Care Medicine, Children's National Hospital, Washington, DC, USA., Ton HT; Department of Critical Care Medicine, Children's National Hospital, Washington, DC, USA., Wu F; Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA., Lin YS; Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA., Lee YJ; School of Medicine, Fu-Jen Catholic University, New Taipei City, Taiwan., Wang PC; Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA.; Department of Physics, Fu-Jen Catholic University, New Taipei City, Taiwan., Shoykhet M; Department of Critical Care Medicine, Children's National Hospital, Washington, DC, USA., Tu TW; Molecular Imaging Laboratory, Department of Radiology, Howard University, Washington, DC, USA. |
| Abstrakt: |
Microglia are the resident macrophages in the central nervous system. Brain injuries, such as traumatic brain injury, hypoxia, and stroke, can induce inflammatory responses accompanying microglial activation. The morphology of microglia is notably diverse and is one of the prominent manifestations during activation. In this study, we proposed to detect the activated microglia in immunohistochemistry images by convolutional neural networks (CNN). 2D Iba1 images (40 μ m) were acquired from a control and a cardiac arrest treated Sprague-Dawley rat brain by a scanning microscope using a 20X objective. The training data were a collection of 54,333 single-cell images obtained from the cortex and midbrain areas, and curated by experienced neuroscientists. Results were compared between CNNs with different architectures, including Resnet18, Resnet50, Resnet101, and support vector machine (SVM) classifiers. The highest model performance was found by Resnet18, trained after 120 epochs with a classification accuracy of 95.5%. The findings indicate a potential application for using CNN in quantitative analysis of microglial morphology over regional difference in a large brain section. |
