Abstract：
OBJECTIVE: Flow cytometry is a widely used technique for identifying cell populations in patient-derived fluids, such as peripheral blood (PB) or cerebrospinal fluid (CSF). Despite its ubiquity in research and clinical practice, the process of gating, i.e., manually identifying cell types, is labor-intensive and error-prone. The objective of this study is to address this challenge by introducing GateNet, a neural network architecture designed for fully end-to-end automated gating without the need for correcting batch effects.
METHODS: For this study a unique dataset is used which comprises over 8,000,000 events from N = 127 PB and CSF samples which were manually labeled independently by four experts. Applying cross-validation, the classification performance of GateNet is compared to the human experts performance. Additionally, GateNet is applied to a publicly available dataset to evaluate generalization. The classification performance is measured using the F1 score.
RESULTS: GateNet achieves F1 scores ranging from 0.910 to 0.997 demonstrating human-level performance on samples unseen during training. In the publicly available dataset, GateNet confirms its generalization capabilities with an F1 score of 0.936. Importantly, we also show that GateNet only requires ≈10 samples to reach human-level performance. Finally, gating with GateNet only takes 15 microseconds per event utilizing graphics processing units (GPU).
CONCLUSIONS: GateNet enables fully end-to-end automated gating in flow cytometry, overcoming the labor-intensive and error-prone nature of manual adjustments. The neural network achieves human-level performance on unseen samples and generalizes well to diverse datasets. Notably, its data efficiency, requiring only ∼10 samples to reach human-level performance, positions GateNet as a widely applicable tool across various domains of flow cytometry.
METHODS: For this study a unique dataset is used which comprises over 8,000,000 events from N = 127 PB and CSF samples which were manually labeled independently by four experts. Applying cross-validation, the classification performance of GateNet is compared to the human experts performance. Additionally, GateNet is applied to a publicly available dataset to evaluate generalization. The classification performance is measured using the F1 score.
RESULTS: GateNet achieves F1 scores ranging from 0.910 to 0.997 demonstrating human-level performance on samples unseen during training. In the publicly available dataset, GateNet confirms its generalization capabilities with an F1 score of 0.936. Importantly, we also show that GateNet only requires ≈10 samples to reach human-level performance. Finally, gating with GateNet only takes 15 microseconds per event utilizing graphics processing units (GPU).
CONCLUSIONS: GateNet enables fully end-to-end automated gating in flow cytometry, overcoming the labor-intensive and error-prone nature of manual adjustments. The neural network achieves human-level performance on unseen samples and generalizes well to diverse datasets. Notably, its data efficiency, requiring only ∼10 samples to reach human-level performance, positions GateNet as a widely applicable tool across various domains of flow cytometry.
摘要：
目的：流式细胞术是一种广泛使用的技术，用于识别患者来源的液体中的细胞群，如外周血(PB)或脑脊液(CSF)。尽管它在研究和临床实践中无处不在，门控的过程，即，手动识别细胞类型，是劳动密集型和容易出错的。本研究的目的是通过引入GateNet来解决这一挑战，一种神经网络架构，专为完全端到端自动门控而设计，无需校正批次效应。
方法:对于本研究,使用独特的数据集,其包括来自N=127PB和CSF样品的超过8,000,000个事件,其由四位专家独立地手动标记。应用交叉验证，将GateNet的分类性能与人类专家的性能进行比较。此外,GateNet应用于公开可用的数据集以评估泛化。使用F1分数测量分类性能。
结果：GateNet取得了从0.910到0.997的F1分数，证明了在训练过程中看不见的样本上的人类水平表现。在公开可用的数据集中，GateNet以0.936的F1评分证实了其泛化能力。重要的是,我们还表明，GateNet只需要≈10个样本就可以达到人类水平的性能。最后,使用GateNet门控使用图形处理单元(GPU)每个事件只需要15微秒。
结论：GateNet能够在流式细胞术中实现完全端到端自动门控，克服了人工调整的劳动密集型和容易出错的特点。神经网络在看不见的样本上实现了人类水平的性能，并很好地推广到不同的数据集。值得注意的是,它的数据效率，只需要10个样本就能达到人类水平的性能，将GateNet定位为广泛适用于流式细胞术各个领域的工具。
方法:对于本研究,使用独特的数据集,其包括来自N=127PB和CSF样品的超过8,000,000个事件,其由四位专家独立地手动标记。应用交叉验证，将GateNet的分类性能与人类专家的性能进行比较。此外,GateNet应用于公开可用的数据集以评估泛化。使用F1分数测量分类性能。
结果：GateNet取得了从0.910到0.997的F1分数，证明了在训练过程中看不见的样本上的人类水平表现。在公开可用的数据集中，GateNet以0.936的F1评分证实了其泛化能力。重要的是,我们还表明，GateNet只需要≈10个样本就可以达到人类水平的性能。最后,使用GateNet门控使用图形处理单元(GPU)每个事件只需要15微秒。
结论：GateNet能够在流式细胞术中实现完全端到端自动门控，克服了人工调整的劳动密集型和容易出错的特点。神经网络在看不见的样本上实现了人类水平的性能，并很好地推广到不同的数据集。值得注意的是,它的数据效率，只需要10个样本就能达到人类水平的性能，将GateNet定位为广泛适用于流式细胞术各个领域的工具。
