摘要: 血白细胞分类计数嗜碱性粒细胞、嗜酸性粒细胞、中性粒细胞、淋巴细胞、及单核细胞是临床诊断的重要依据。作者在细胞图像分割、白细胞特征提取、白细胞特征选择后，提出了用Sugeno型模糊神经网络的方法实现外周血白细胞的自动形态学分类。用构建的网络分别进行白细胞的3分类和5分类试验，结果表明，用模糊神经网络分类器对血白细胞形态学分类可行。

    关键词: 模糊神经网络;Sugeno;血白细胞;彩色图像;分类

    Peripheral White Blood Cell Classification Based on Sugeno-model Fuzzy Neural Network

    GAO Hong，BAO Xu-dong，ZHANG Jian-fu

    (Department of Biological Science and Medical Engineering，Southeast University，Nanjing Jiangsu210096，China;Department of Computer Science and Engineering，Southeast University，Jiangsu Nanjing210096;The First Affiliated Hospital of Nanjing Medical University，Jiangsu Nanjing210029)

    Abstract:Identification and classification of major white blood cell types named monocytes，lymphocytes，neutrophils，eosinophils，and basophils is important for clinical diagnosis.After cell segmentation，leukocytes′feature acquirement and selection，a classification method based on Sugeno-model fuzzy neural network was presented.The3-types classification and5-types classification experiment results show that the fuzzy neural network algorithm is feasible for white blood cell classification. ......