Zhang Yijie, Huang Luzhe, Pillar Nir, Li Yuzhu, Chen Hanlong, Ozcan Aydogan
Electrical and Computer Engineering Department, University of California, Los Angeles, CA, 90095, USA.
Bioengineering Department, University of California, Los Angeles, CA, 90095, USA.
Nat Commun. 2025 May 30;16(1):5016. doi: 10.1038/s41467-025-60387-z.
Virtual staining of tissue offers a powerful tool for transforming label-free microscopy images of unstained tissue into equivalents of histochemically stained samples. This study presents a diffusion model-based pixel super-resolution virtual staining approach utilizing a Brownian bridge process to enhance both the spatial resolution and fidelity of label-free virtual tissue staining, addressing the limitations of traditional deep learning-based methods. Our approach integrates sampling techniques into a diffusion model-based image inference process to significantly reduce the variance in the generated virtually stained images, resulting in more stable and accurate outputs. Blindly applied to lower-resolution auto-fluorescence images of label-free human lung tissue samples, the diffusion-based pixel super-resolution virtual staining model consistently outperforms conventional approaches in resolution, structural similarity and perceptual accuracy, successfully achieving a pixel super-resolution factor of 4-5×, increasing the output space-bandwidth product by 16-25-fold compared to the input label-free microscopy images. Diffusion-based pixel super-resolved virtual tissue staining not only improves resolution and image quality but also enhances the reliability of virtual staining without traditional chemical staining, offering significant potential for clinical diagnostics.
组织的虚拟染色提供了一种强大的工具，可将未染色组织的无标记显微镜图像转化为等同于组织化学染色样本的图像。本研究提出了一种基于扩散模型的像素超分辨率虚拟染色方法，该方法利用布朗桥过程来提高无标记虚拟组织染色的空间分辨率和保真度，解决了传统深度学习方法的局限性。我们的方法将采样技术集成到基于扩散模型的图像推理过程中，以显著降低生成的虚拟染色图像中的方差，从而产生更稳定、准确的输出。将基于扩散的像素超分辨率虚拟染色模型盲目应用于无标记人肺组织样本的低分辨率自发荧光图像时，在分辨率、结构相似性和感知准确性方面始终优于传统方法，成功实现了4-5倍的像素超分辨率因子，与输入的无标记显微镜图像相比，输出空间带宽积增加了16-25倍。基于扩散的像素超分辨虚拟组织染色不仅提高了分辨率和图像质量，还增强了无需传统化学染色的虚拟染色的可靠性，为临床诊断提供了巨大潜力。
