Significance: Our study introduces an application of deep learning to virtually generate fluorescence images to reduce the burdens of cost and time from considerable effort in sample preparation related to chemical fixation and staining. Aim: The objective of our work was to determine how successfully deep learning methods perform on fluorescence prediction that depends on structural and/or a functional relationship between input labels and output labels. Approach: We present a virtual-fluorescence-staining method based on deep neural networks (VirFluoNet) to transform co-registered images of cells into subcellular compartment-specific molecular fluorescence labels in the same field-of-view. An algorithm based on conditional generative adversarial networks was developed and trained on microscopy datasets from breast-cancer and bone-osteosarcoma cell lines: MDA-MB-231 and U2OS, respectively. Several established performance metrics—the mean absolute error (MAE), peak-signal-to-noise ratio (PSNR), and structural-similarity-index (SSIM)—as well as a novel performance metric, the tolerance level, were measured and compared for the same algorithm and input data. Results: For the MDA-MB-231 cells, F-actin signal performed the fluorescent antibody staining of vinculin prediction better than phase-contrast as an input. For the U2OS cells, satisfactory metrics of performance were archieved in comparison with ground truth. MAE is <0.005, 0.017, 0.012; PSNR is >40 / 34 / 33 dB; and SSIM is >0.925 / 0.926 / 0.925 for 4′,6-diamidino-2-phenylindole/hoechst, endoplasmic reticulum, and mitochondria prediction, respectively, from channels of nucleoli and cytoplasmic RNA, Golgi plasma membrane, and F-actin. Conclusions: These findings contribute to the understanding of the utility and limitations of deep learning image-regression to predict fluorescence microscopy datasets of biological cells. We infer that predicted image labels must have either a structural and/or a functional relationship to input labels. Furthermore, the approach introduced here holds promise for modeling the internal spatial relationships between organelles and biomolecules within living cells, leading to detection and quantification of alterations from a standard training dataset.

中文翻译：

---

通过对抗学习进行荧光成像的虚拟细胞器自编码

意义：我们的研究引入了深度学习的应用，以虚拟生成荧光图像，以减少与化学固定和染色相关的样品制备的大量工作所带来的成本和时间负担。目标：我们工作的目标是确定深度学习方法在荧光预测上的成功程度，这取决于输入标签和输出标签之间的结构和/或功能关系。方法：我们提出了一种基于深度神经网络 (VirFluoNet) 的虚拟荧光染色方法，可将共同注册的细胞图像转换为相同视场中的亚细胞区室特定分子荧光标记。开发了一种基于条件生成对抗网络的算法，并在来自乳腺癌和骨骨肉瘤细胞系的显微镜数据集上进行了训练：MDA-MB-231 和 U2OS，分别。测量了几个既定的性能指标——平均绝对误差 (MAE)、峰值信噪比 (PSNR) 和结构相似性指数 (SSIM)——以及一种新的性能指标——容差水平比较相同的算法和输入数据。结果：对于 MDA-MB-231 细胞，F-肌动蛋白信号对纽蛋白预测的荧光抗体染色比作为输入的相差更好。对于 U2OS 单元，与地面实况相比，获得了令人满意的性能指标。MAE 为 <0.005、0.017、0.012；PSNR > 40 / 34 / 33 dB；对于 4'，SSIM > 0.925 / 0.926 / 0.925，分别来自核仁和细胞质 RNA、高尔基体质膜和 F-肌动蛋白通道的 6-二脒基-2-苯基吲哚/hoechst、内质网和线粒体预测。结论：这些发现有助于理解深度学习图像回归预测生物细胞荧光显微镜数据集的效用和局限性。我们推断预测图像标签必须与输入标签具有结构和/或功能关系。此外，这里介绍的方法有望对活细胞内细胞器和生物分子之间的内部空间关系进行建模，从而检测和量化标准训练数据集的变化。来自核仁和细胞质 RNA、高尔基体膜和 F-肌动蛋白的通道。结论：这些发现有助于理解深度学习图像回归预测生物细胞荧光显微镜数据集的效用和局限性。我们推断预测图像标签必须与输入标签具有结构和/或功能关系。此外，这里介绍的方法有望对活细胞内细胞器和生物分子之间的内部空间关系进行建模，从而检测和量化标准训练数据集的变化。来自核仁和细胞质 RNA、高尔基体膜和 F-肌动蛋白的通道。结论：这些发现有助于理解深度学习图像回归预测生物细胞荧光显微镜数据集的效用和局限性。我们推断预测图像标签必须与输入标签具有结构和/或功能关系。此外，这里介绍的方法有望对活细胞内细胞器和生物分子之间的内部空间关系进行建模，从而检测和量化标准训练数据集的变化。这些发现有助于理解深度学习图像回归预测生物细胞荧光显微镜数据集的效用和局限性。我们推断预测图像标签必须与输入标签具有结构和/或功能关系。此外，这里介绍的方法有望对活细胞内细胞器和生物分子之间的内部空间关系进行建模，从而检测和量化标准训练数据集的变化。这些发现有助于理解深度学习图像回归预测生物细胞荧光显微镜数据集的效用和局限性。我们推断预测图像标签必须与输入标签具有结构和/或功能关系。此外，这里介绍的方法有望对活细胞内细胞器和生物分子之间的内部空间关系进行建模，从而检测和量化标准训练数据集的变化。