摘要：成像流式细胞术（IFC）可生成海量多光谱数据集，但对专家标注的刚性需求制约了监督深度学习模型的发展。尽管自监督学习（SSL）提供了一条解决路径，其在 IFC 中的应用仍较为零散且缺乏系统性基准评测。为此，我们提出了 IFC-SSL-Bench——一个用于评估 IFC 场景下 SSL 性能的模块化框架。我们在两个异构数据集上，系统测试了 6 种 SSL 方法在 4 种骨干网络上的表现。通过在训练集不同标注比例（1%-100%）下评估下游分类任务效果，我们量化了标注效率并确定了高维生物成像的最优配置。在形态学分类任务中，SSL 仅利用 5% 的标注数据即可媲美基于 100% 标注数据训练的全监督基线表现，并在低于 5% 的极少样本区间展现出显著优势。在两大数据集中，对比学习方法 MoCo-v2 与 ConvNeXt 骨干网络的搭配均展现出最佳性能，其中 ConvNeXtV1-T 最契合免疫突触分类，而 ConvNeXtV2-T 则在形态学分类中表现最优。我们还在迁移动态中发现了一个清晰模式：ImageNet 预训练初始化有助于形态学分类（这与其与自然图像的视觉相似性相符），而随机初始化则能更好地捕捉更具领域特异性的免疫突触分类特征。在仅有 1% 标注数据时，SSL 使结构复杂类别的特定类 F1 分数提升了 35 个百分点以上。我们整合这些洞见形成了一套在高通量 IFC 中部署自监督工作流的统一指导准则，并开源发布了该基准以供后续研究使用。

Abstract:Imaging Flow Cytometry (IFC) generates large multispectral datasets, yet the need for expert annotations bottlenecks the development of supervised deep learning models. While Self-Supervised Learning (SSL) offers a solution, its application to IFC remains fragmented and lacks systematic benchmarking. To address this, we present IFC-SSL-Bench, a modular framework for evaluating SSL in IFC. We benchmark six SSL approaches across four backbones on two heterogeneous datasets. By assessing downstream classification performance across annotation regimes of the training sets (1%-100%), we quantify annotation efficiency and identify optimal configurations for high-dimensional biological imaging. SSL matches the performance of fully supervised baselines trained on 100% of annotated data while using as little as 5% of annotations for morphological classification, with advantages in low-data regimes below 5%. Across both datasets, the contrastive approach MoCo-v2 paired with ConvNeXt backbones emerged as the top-performing configuration, with ConvNeXtV1-T best for immunological synapse classification and ConvNeXtV2-T for morphological classification. We identify a clear pattern in transfer dynamics: ImageNet initialization benefits morphological classification, consistent with its visual similarity to natural images, whereas random initialization better captures the more domain-specific immunological synapse classification. SSL elevates class-specific F1-scores by over 35 percentage points for structurally complex classes at 1% of annotated data. We synthesize these insights into a unified set of guidelines for deploying self-supervised workflows in high-throughput IFC, and release the benchmark as a resource for future work.