Classification of Activated Microglia by Convolutional Neural Networks
Classification of Activated Microglia by Convolutional Neural Networks
复制标题
卷积神经网络对激活的小胶质细胞进行分类
DOI：
10.1109/biocas54905.2022.9948635
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Shoykhet, Michael
中科院分区：
文献类型：
--
作者：
Hsu, Chao-Hsiung;Agaronyan, Artur;Katherine, Raffensperger;Kadden, Micah;Ton, Hoai T.;Wu, Frank;Lin, Yu-Shun;Lee, Yih-Jing;Wang, Paul C.;Shoykhet, Michael
小胶质细胞是驻留在中枢神经系统的巨噬细胞。脑损伤，如创伤性脑损伤、缺氧和中风，可诱发炎症反应，同时伴有小胶质细胞的激活。小胶质细胞形态多样，是活化的显著表现。在这项研究中，我们建议使用卷积神经网络(CNN)对激活的小胶质细胞进行分类。IBA1图像来自对照和心脏骤停Long-Evans大鼠脑组织，用明视场显微镜观察。54,333张单细胞图像的训练数据是从大脑皮层和中脑区收集的，并由经验丰富的神经科学家进行整理。比较了具有不同结构的CNN之间的结果，包括Resnet18、Resnet50、Resnet101和支持向量机分类器。Resnet18的模型性能最好，经过120个历元训练，分类准确率为95.5-98.8%。这一发现表明，在一个大的大脑切片上，使用CNN来定量分析小胶质细胞形态的区域差异是一个潜在的应用。
Microglia are the macrophages resident 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 a prominent manifestation of activation. In this study, we propose to classify activated microglia using a convolutional neural network (CNN). Iba1 images were acquired from a control and cardiac arrest Long-Evans rat brain with a bright-field microscopy. The training data of 54,333 single-cell images were collected 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 classifiers. The highest model performance was found by Resnet18, trained after 120 epochs with a classification accuracy of 95.5-98.8 percent. The findings indicate a potential application for using CNN in the quantitative analysis of microglial morphology over regional differences in a large brain section.
登录
查看更多内容
影响因子：
5.3
作者：
Fernández-Arjona MDM;Grondona JM;Granados-Durán P;Fernández-Llebrez P;López-Ávalos MD
通讯作者：
López-Ávalos MD
影响因子：
3
作者：
Lu, Yanbin;Carin, Lawrence;Roysam, Badrinath
通讯作者：
Roysam, Badrinath
影响因子：
9.3
作者：
Verdonk F;Roux P;Flamant P;Fiette L;Bozza FA;Simard S;Lemaire M;Plaud B;Shorte SL;Sharshar T;Chrétien F;Danckaert A
通讯作者：
Danckaert A
影响因子：
6.2
作者：
Salamanca, Luis;Mechawar, Naguib;Skupin, Alexander
通讯作者：
Skupin, Alexander
影响因子：
5.3
作者：
Heindl S;Gesierich B;Benakis C;Llovera G;Duering M;Liesz A
通讯作者：
Liesz A