Li Rui, Winward Ashley, Lalonde Logan R, Hidalgo Daniel, Sardella John P, Hwang Yung, Swaminathan Aishwarya, Thackeray Sean, Hu Kai, Zhu Lihua Julie, Socolovsky Merav
Department of Molecular, Cell and Cancer Biology, UMass Chan Medical School, Worcester, Massachusetts.
Department of Molecular, Cell and Cancer Biology, UMass Chan Medical School, Worcester, Massachusetts.
Exp Hematol. 2025 Jul;147:104786. doi: 10.1016/j.exphem.2025.104786. Epub 2025 Apr 24.
Despite advances in flow cytometry and single-cell transcriptomics, colony-formation assays (CFAs) remain an essential component in the evaluation of erythroid and hematopoietic progenitors. These assays provide functional information on progenitor differentiation and proliferative potential, making them a mainstay of hematology research and clinical diagnosis. However, the utility of CFAs is limited by the time-consuming and error-prone manual counting of colonies, which is also prone to bias and inconsistency. Here we present "C-COUNT," a convolutional neural network-based tool that scores the standard colony-forming-unit-erythroid (CFU-e) assay by reliably identifying CFU-e colonies from images collected by automated microscopy and outputs both their number and size. We tested the performance of C-COUNT against three experienced scientists and find that it is equivalent or better in reliably identifying CFU-e colonies on plates that also contain myeloid colonies and other cell aggregates. We further evaluated its performance in the response of CFU-e progenitors to increasing erythropoietin concentrations and to a spectrum of genotoxic agents. We provide the C-COUNT code, a Docker image, a trained model, and training data set to facilitate its download, usage, and model refinement in other laboratories. The C-COUNT tool transforms the traditional CFU-e CFA into a rigorous and efficient assay with potential applications in high-throughput screens for novel erythropoietic factors and therapeutic agents.
尽管流式细胞术和单细胞转录组学取得了进展，但集落形成试验（CFA）仍然是评估红系和造血祖细胞的重要组成部分。这些试验提供了关于祖细胞分化和增殖潜力的功能信息，使其成为血液学研究和临床诊断的支柱。然而，CFA的效用受到集落人工计数耗时且容易出错的限制，这种计数还容易出现偏差和不一致。在此，我们展示了“C-COUNT”，这是一种基于卷积神经网络的工具，通过从自动显微镜收集的图像中可靠地识别集落形成单位红系（CFU-e）集落，并输出其数量和大小，对标准的CFU-e试验进行评分。我们将C-COUNT的性能与三位经验丰富的科学家进行了测试，发现在可靠识别同时含有髓系集落和其他细胞聚集体的平板上的CFU-e集落方面，它的表现相当或更优。我们进一步评估了其在CFU-e祖细胞对促红细胞生成素浓度增加以及一系列基因毒性剂的反应中的性能。我们提供了C-COUNT代码、一个Docker镜像、一个训练好的模型和训练数据集，以方便其他实验室下载、使用和改进模型。C-COUNT工具将传统的CFU-e CFA转变为一种严谨且高效的试验，在新型促红细胞生成因子和治疗剂的高通量筛选中具有潜在应用。
