Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland.
Institute of Biomedicine, University of Eastern Finland, Kuopio, Finland.
BMC Bioinformatics. 2019 Feb 15;20(1):80. doi: 10.1186/s12859-019-2605-z.
Cell counting from cell cultures is required in multiple biological and biomedical research applications. Especially, accurate brightfield-based cell counting methods are needed for cell growth analysis. With deep learning, cells can be detected with high accuracy, but manually annotated training data is required. We propose a method for cell detection that requires annotated training data for one cell line only, and generalizes to other, unseen cell lines.
Training a deep learning model with one cell line only can provide accurate detections for similar unseen cell lines (domains). However, if the new domain is very dissimilar from training domain, high precision but lower recall is achieved. Generalization capabilities of the model can be improved with training data transformations, but only to a certain degree. To further improve the detection accuracy of unseen domains, we propose iterative unsupervised domain adaptation method. Predictions of unseen cell lines with high precision enable automatic generation of training data, which is used to train the model together with parts of the previously used annotated training data. We used U-Net-based model, and three consecutive focal planes from brightfield image z-stacks. We trained the model initially with PC-3 cell line, and used LNCaP, BT-474 and 22Rv1 cell lines as target domains for domain adaptation. Highest improvement in accuracy was achieved for 22Rv1 cells. F-score after supervised training was only 0.65, but after unsupervised domain adaptation we achieved a score of 0.84. Mean accuracy for target domains was 0.87, with mean improvement of 16 percent.
With our method for generalized cell detection, we can train a model that accurately detects different cell lines from brightfield images. A new cell line can be introduced to the model without a single manual annotation, and after iterative domain adaptation the model is ready to detect these cells with high accuracy.
细胞培养物的细胞计数在多个生物学和生物医学研究应用中是必需的。特别是，需要准确的基于明场的细胞计数方法来进行细胞生长分析。通过深度学习，可以高精度地检测细胞，但需要手动注释训练数据。我们提出了一种仅需要一个细胞系的注释训练数据的细胞检测方法，并将其推广到其他未见过的细胞系。
仅用一个细胞系训练深度学习模型可以对相似的未见过的细胞系（领域）进行准确检测。然而，如果新领域与训练领域非常不同，则会达到高精度但较低的召回率。通过训练数据变换可以提高模型的泛化能力，但仅在一定程度上。为了进一步提高未见过的领域的检测精度，我们提出了迭代的无监督领域自适应方法。具有高精度的未见过细胞系的预测能够自动生成训练数据，这些数据与之前使用的部分注释训练数据一起用于训练模型。我们使用了基于 U-Net 的模型，以及明场图像 z 堆叠的三个连续焦平面。我们最初用 PC-3 细胞系训练模型，并使用 LNCaP、BT-474 和 22Rv1 细胞系作为域自适应的目标域。22Rv1 细胞的准确性提高最大。经过监督训练后的 F 分数仅为 0.65，但经过无监督域自适应后，我们达到了 0.84。目标域的平均准确率为 0.87，平均提高了 16%。
通过我们的通用细胞检测方法，我们可以训练一个能够从明场图像中准确检测不同细胞系的模型。可以在没有单个手动注释的情况下向模型中引入新的细胞系，并且在迭代的域自适应之后，模型可以准备好以高精度检测这些细胞。
