UConn Health, 263 Farmington Ave, Farmington, CT, USA.
Commun Biol. 2023 Mar 2;6(1):232. doi: 10.1038/s42003-023-04608-5.
Automated cell segmentation from optical microscopy images is usually the first step in the pipeline of single-cell analysis. Recently, deep-learning based algorithms have shown superior performances for the cell segmentation tasks. However, a disadvantage of deep-learning is the requirement for a large amount of fully annotated training data, which is costly to generate. Weakly-supervised and self-supervised learning is an active research area, but often the model accuracy is inversely correlated with the amount of annotation information provided. Here we focus on a specific subtype of weak annotations, which can be generated programmably from experimental data, thus allowing for more annotation information content without sacrificing the annotation speed. We designed a new model architecture for end-to-end training using such incomplete annotations. We have benchmarked our method on a variety of publicly available datasets, covering both fluorescence and bright-field imaging modality. We additionally tested our method on a microscopy dataset generated by us, using machine-generated annotations. The results demonstrated that our models trained under weak supervision can achieve segmentation accuracy competitive to, and in some cases, surpassing, state-of-the-art models trained under full supervision. Therefore, our method can be a practical alternative to the established full-supervision methods.
从光学显微镜图像中自动分割细胞通常是单细胞分析流水线的第一步。最近，基于深度学习的算法在细胞分割任务中表现出了优异的性能。然而，深度学习的一个缺点是需要大量的完全标注的训练数据，这在生成方面成本很高。弱监督和自监督学习是一个活跃的研究领域，但通常模型的准确性与提供的标注信息的数量成反比。在这里，我们专注于一种特定的弱标注类型，这种类型可以通过实验数据以编程方式生成，从而在不牺牲标注速度的情况下提供更多的标注信息内容。我们设计了一种新的模型架构，用于使用这种不完整的标注进行端到端训练。我们在各种公开可用的数据集上对我们的方法进行了基准测试，涵盖了荧光和明场成像模式。我们还使用机器生成的标注在我们生成的显微镜数据集上测试了我们的方法。结果表明，我们在弱监督下训练的模型可以达到与完全监督下训练的最先进模型相当的分割精度，在某些情况下甚至超过了最先进模型。因此，我们的方法可以作为一种实用的替代方案，替代现有的完全监督方法。
