Cell types of erythrocytes should be identified because they are closely related to their functionality and viability. Conventional methods for classifying erythrocytes are time consuming and labor intensive. Therefore, an automatic and accurate erythrocyte classification system is indispensable in healthcare and biomedical fields. In this study, we proposed a new label-free sensor for automatic identification of erythrocyte cell types using a digital in-line holographic microscopy (DIHM) combined with machine learning algorithms. A total of 12 features, including information on intensity distributions, morphological descriptors, and optical focusing characteristics, is quantitatively obtained from numerically reconstructed holographic images. All individual features for discocytes, echinocytes, and spherocytes are statistically different. To improve the performance of cell type identification, we adopted several machine learning algorithms, such as decision tree model, support vector machine, linear discriminant classification, and k-nearest neighbor classification. With the aid of these machine learning algorithms, the extracted features are effectively utilized to distinguish erythrocytes. Among the four tested algorithms, the decision tree model exhibits the best identification performance for the training sets (n = 440, 98.18%) and test sets (n = 190, 97.37%). This proposed methodology, which smartly combined DIHM and machine learning, would be helpful for sensing abnormal erythrocytes and computer-aided diagnosis of hematological diseases in clinic.

应该确定红细胞的细胞类型，因为它们与其功能和生存能力密切相关。用于对红细胞进行分类的常规方法既费时又费力。因此，在医疗保健和生物医学领域必不可少的是自动而准确的红细胞分类系统。在这项研究中，我们提出了一种新的无标记传感器，该传感器可使用数字在线全息显微镜（DIHM）与机器学习算法相结合来自动识别红细胞类型。从数字重建的全息图像中定量获得了总共12个特征，包括有关强度分布，形态描述符和光学聚焦特性的信息。盘状细胞，棘突细胞和球状细胞的所有单个特征在统计上都是不同的。k-最近邻居分类。借助这些机器学习算法，可以有效地利用提取的特征来区分红细胞。在这四种测试算法中，决策树模型对训练集（n = 440，98.18％）和测试集（n = 190，97.37％）表现出最佳的识别性能。该提议的方法将DIHM与机器学习巧妙地结合在一起，将有助于临床中感测红细胞异常和血液病的计算机辅助诊断。