The processed data of bright-field images of hematopoietic tumor cell lines for machine learning

Morphological images of cells contain extensive information, which help biologists to infer the type and state of cells to some degree based on their morphology. Convolutional Neural Network (CNN), a neural network architecture, is a powerful tool used for image recognition. However, whether it can be used to classify cells on the basis of their morphology remains unclear.We have obtained bright-field images of 10 human hematopoietic tumor-derived cell lines (including acute myeloid leukemia, chronic myeloid leukemia, B-cell acute lymphoblastic leukemia, and myeloma) by imaging flow cytometer (90,000 images per group). These data have been processed for use in Keras. Thus, we believe that these data could be useful for research in the field of cell biology using machine learning.

细胞形态学图像蕴含丰富信息，生物学家可基于细胞的形态特征在一定程度上推断其类型与状态。卷积神经网络（Convolutional Neural Network，CNN）作为一类经典神经网络架构，是图像识别领域的高效工具。然而，能否利用该模型基于细胞形态对细胞进行分类，目前尚无定论。本研究通过成像流式细胞仪（imaging flow cytometer）获取了10株人造血肿瘤源性细胞系的明场图像，每组分含9万张图像，所覆盖的细胞系类型包括急性髓系白血病、慢性髓系白血病、B细胞急性淋巴细胞白血病以及骨髓瘤。上述数据已完成预处理，可直接用于Keras框架。因此，我们认为该数据集可用于依托机器学习开展的细胞生物学相关研究。