Stain normalization algorithms aim to transform the color and intensity characteristics of a source multi-gigapixel histology image to match those of a target image, mitigating inconsistencies in the appearance of stains used to highlight cellular components in the images. We propose a new approach, StainFuser, which treats this problem as a style transfer task using a novel Conditional Latent Diffusion architecture, eliminating the need for handcrafted color components. With this method, we curate SPI-2M the largest stain normalization dataset to date of over 2 million histology images with neural style transfer for high-quality transformations. Trained on this data, StainFuser outperforms current state-of-the-art GAN and handcrafted methods in terms of the quality of normalized images. Additionally, compared to existing approaches, it improves the performance of nuclei instance segmentation and classification models when used as a test time augmentation method on the challenging CoNIC dataset. Finally, we apply StainFuser on multi-gigapixel Whole Slide Images (WSIs) and demonstrate improved performance in terms of computational efficiency, image quality and consistency across tiles over current methods.

通过采用基于条件潜在扩散的新型架构，以样式转移任务的方式处理了镜像污染问题，并建立了迄今为止最大的超过200万组织学图像数据集SPI-2M，并使用神经样式转移进行高质量转换，从而在归一化图像的质量方面胜过了现有的GAN和手工方法。此外，作为考验时间增强方法应用于具有挑战性的CoNIC数据集的核实例分割和分类模型，与现有方法相比，它改进了性能。最后，在多千兆像素全尺寸图像（Whole Slide Images，WSIs）上应用了StainFuser，并展示了相对于现有方法，它在计算效率、图像质量和图块之间的一致性方面的改进。

StainFuser：在多亿像素组织学图像中控制扩散以加速神经风格转移