GateNet: A novel neural network architecture for automated flow cytometry gating

• Published in: Computers in biology and medicine 2024-09, Vol.179, p.108820, Article 108820
• Main Authors: Fisch, Lukas, Heming, Michael, Schulte-Mecklenbeck, Andreas, Gross, Catharina C., Zumdick, Stefan, Barkhau, Carlotta, Emden, Daniel, Ernsting, Jan, Leenings, Ramona, Sarink, Kelvin, Winter, Nils R., Dannlowski, Udo, Wiendl, Heinz, Hörste, Gerd Meyer zu, Hahn, Tim
• Format: Article
• Language: English
• Subjects: Automation; Cerebrospinal fluid; Classification; Datasets; Error analysis; Error correction; Flow cytometry; Flow Cytometry - methods; Fluid flow; Gating; Graphics processing units; Human performance; Humans; Labor; Machine learning; Neural network; Neural networks; Neural Networks, Computer; Performance evaluation; Peripheral blood
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108820

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. 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. 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). 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. •GateNets neural architecture enables automated gating with batch effect correction.•Validation on dataset with >8,000,000 events labeled independently by four experts.•Human-level performance on unseen samples with F1 scores ranging from 0.910 to 0.997.•Reaches human-level performance with only ∼10 training samples — broad applicability.•Gating only takes 15 microseconds per event making GateNet a swift and practical tool.