Sengupta Sourya, Xu Jianquan, Nguyen Phuong, Brooks Frank J, Liu Yang, Anastasio Mark A
Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA.
Center for Label-free Imaging and Multiscale Biophotonics, University of Illinois Urbana-Champaign, Urbana, IL, USA.
bioRxiv. 2025 Aug 6:2025.08.04.668552. doi: 10.1101/2025.08.04.668552.
Virtual staining, or in-silico-labeling, has been proposed to computationally generate synthetic fluorescence images from label-free images by use of deep learning-based image-to-image translation networks. In most reported studies, virtually stained images have been assessed only using traditional image quality measures such as structural similarity or signal-to-noise ratio. However, in biomedical imaging, images are typically acquired to facilitate an image-based inference, which we refer to as a downstream biological or clinical task. This study systematically investigates the utility of virtual staining for facilitating clinically relevant downstream tasks (like segmentation or classification) with consideration of the capacity of the deep neural networks employed to perform the tasks. Comprehensive empirical evaluations were conducted using biological datasets, assessing task performance by use of label-free, virtually stained, and ground truth fluorescence images. The results demonstrated that the utility of virtual staining is largely dependent on the ability of the segmentation or classification task network to extract meaningful task-relevant information, which is related to the concept of network capacity. Examples are provided in which virtual staining does not improve, or even degrades, segmentation or classification performance when the capacity of the associated task network is sufficiently large. The results demonstrate that task network capacity should be considered when deciding whether to perform virtual staining.
虚拟染色，即计算机模拟标记，已被提出通过使用基于深度学习的图像到图像转换网络，从无标记图像中计算生成合成荧光图像。在大多数已报道的研究中，虚拟染色图像仅使用传统的图像质量指标进行评估，如结构相似性或信噪比。然而，在生物医学成像中，获取图像通常是为了便于基于图像的推理，我们将其称为下游生物学或临床任务。本研究系统地探讨了虚拟染色在促进临床相关下游任务（如分割或分类）方面的效用，并考虑了用于执行这些任务的深度神经网络的能力。使用生物数据集进行了全面的实证评估，通过使用无标记、虚拟染色和真实荧光图像来评估任务性能。结果表明，虚拟染色的效用在很大程度上取决于分割或分类任务网络提取有意义的任务相关信息的能力，这与网络容量的概念相关。文中给出了一些示例，当相关任务网络的容量足够大时，虚拟染色不会提高甚至会降低分割或分类性能。结果表明，在决定是否进行虚拟染色时应考虑任务网络容量。
