[论文解读] Automatic Cell Counting in Flourescent Microscopy Using Deep Learning

R. Morelli, L. Clissa+4 more|arXiv (Cornell University)|Feb 24, 2021

Cell Image Analysis Techniques参考文献 11被引用 7

一句话总结

本文提出一种基于深度学习的荧光显微镜图像自动细胞计数方法，采用改进的ResUNet架构并结合加权损失图，以提升密集区域的检测性能。该模型F₁分数达到0.87，表现出人类水平的性能，其错误主要处于操作员解释的可接受范围内，显著减少了生物图像分析中的手动工作量。

ABSTRACT

Counting cells in fluorescent microscopy is a tedious, time-consuming task that researchers have to accomplish to assess the effects of different experimental conditions on biological structures of interest. Although such objects are generally easy to identify, the process of manually annotating cells is sometimes subject to arbitrariness due to the operator's interpretation of the borderline cases. We propose a Machine Learning approach that exploits a fully-convolutional network in a binary segmentation fashion to localize the objects of interest. Counts are then retrieved as the number of detected items. Specifically, we adopt a UNet-like architecture leveraging residual units and an extended bottleneck for enlarging the field-of-view. In addition, we make use of weighted maps that penalize the errors on cells boundaries increasingly with overcrowding. These changes provide more context and force the model to focus on relevant features during pixel-wise classification. As a result, the model performance is enhanced, especially in presence of clumping cells, artifacts and confounding biological structures. Posterior assessment of the results with domain experts confirms that the model detects cells of interest correctly. The model demonstrates a human-level ability inasmuch even erroneous predictions seem to fall within the limits of operator interpretation. This qualitative assessment is also corroborated by quantitative metrics as an ${F_1}$ score of 0.87. Despite some difficulties in interpretation, results are also satisfactory with respect to the counting task, as testified by mean and median absolute error of, respectively, 0.8 and 1.

研究动机与目标

• 自动化荧光显微镜图像中耗时且主观的手动细胞计数任务。
• 减少在识别边界细胞情况下的操作员疲劳和观察者间差异。
• 开发一种既能提供计数结果又能生成可视化分割图以解释结果的模型。
• 在细胞聚集、伪影和低对比度区域等挑战性条件下提升性能。
• 在模糊或不确定的情况下，实现与人类相当的细胞检测与计数可靠性。

提出的方法

• 采用基于UNet结构并引入残差单元与扩展瓶颈的全卷积神经网络，用于细胞的二值分割。
• 应用加权损失图，对过度拥挤区域的边界错误施加更重惩罚，从而提升密集细胞簇中的定位精度。
• 模型训练目标为预测像素级分割掩码，进而通过检测到的实例数量获得细胞计数结果。
• 网络架构设计旨在扩展感受野，同时显著控制参数量，增强上下文理解能力。
• 探索使用空洞卷积以扩大感受野，但因伪影生成问题而未带来显著性能提升。
• 全卷积设计支持对不同尺寸图像进行推理，实现灵活部署。

实验结果

研究问题

• RQ1 深度学习模型能否在荧光显微镜图像的细胞计数中达到人类水平的准确性？
• RQ2 加权损失图的使用在细胞密集或重叠区域的性能表现有何影响？
• RQ3 模型错误在多大程度上与人类操作员解释中的固有不确定性一致？
• RQ4 该模型是否能在无需微调的情况下，泛化于不同形状、强度和图像质量的细胞？
• RQ5 网络架构中扩展的感受野在多大程度上提升了分割与计数的准确性？

主要发现

• 模型F₁分数达到0.87，表明在细胞检测与分割方面表现优异。
• 细胞计数的平均绝对误差为0.8，中位数绝对误差为1，与真实值高度一致。
• 误报与漏报常可解释为边界情况，证实了与人类操作员不确定性的对齐。
• 加权损失图显著提升了对接触或聚集细胞的检测能力，通过强化密集区域的边界精度。
• 领域专家确认，即使预测错误，其结果也在人类解释的合理范围内，表明具备人类水平的可靠性。
• 模型在低质量及挑战性图像上泛化良好，未出现系统性失败，表现出强鲁棒性。