Accurate morphological classification of white blood cells (WBCs) is an important step in the diagnosis of leukemia, a disease in which nonfunctional blast cells accumulate in the bone marrow. Recently, deep convolutional neural networks (CNNs) have been successfully used to classify leukocytes by training them on single-cell images from a specific domain. Most CNN models assume that the distributions of the training and test data are similar, i.e., that the data are independently and identically distributed. Therefore, they are not robust to different staining protocols, magnifications, resolutions, scanners, or imaging protocols, as well as variations in clinical centers or patient cohorts. In addition, domain-specific data imbalances affect the generalization performance of classifiers. Here, we train a robust CNN for WBC classification by addressing cross-domain data imbalance and domain shifts. To this end, we use two loss functions and demonstrate the effectiveness on out-of-distribution (OOD) generalization. Our approach achieves the best F1 macro score compared to other existing methods, and is able to consider rare cell types. This is the first demonstration of imbalanced domain generalization in hematological cytomorphology and paves the way for robust single cell classification methods for the application in laboratories and clinics.

翻译：白细胞（WBCs）的准确形态学分类是白血病诊断的关键步骤，该疾病以功能丧失的原始细胞在骨髓中积聚为特征。近年来，深度卷积神经网络（CNNs）已被成功应用于白细胞分类，其通过在特定域的单细胞图像上训练模型实现。多数CNN模型假设训练数据与测试数据分布相似，即数据独立同分布。因此，这些模型对不同染色方案、放大倍数、分辨率、扫描仪或成像协议缺乏稳健性，也难以应对临床中心或患者队列的变异。此外，域特定数据不平衡会进一步影响分类器的泛化性能。本文通过解决跨域数据不平衡与域迁移问题，训练了一个稳健的CNN用于白细胞分类。为此，我们采用两种损失函数，并验证其对于域外（OOD）泛化的有效性。与现有方法相比，本方法实现了最优的F1宏平均得分，并能有效识别稀有细胞类型。这是首次在血液细胞形态学中验证非平衡域泛化，为实验室和临床中稳健单细胞分类方法的应用奠定了基础。