ContriMix：数字病理中无需域标签的可扩展染色颜色增强域泛化方法
ContriMix: Scalable stain color augmentation for domain generalization without domain labels in digital pathology
AI总结：
针对数字病理图像染色差异导致深度学习模型泛化差、现有颜色增强方法依赖域标签难以规模化的问题，提出基于DRIT++的无域标签增强方法ContriMix，利用小批次样本染色变化与随机混合提取信息生成合成图像，在Camelyon17-WILDS数据集上性能优于同类方法，且鲁棒性强。
摘要：
染色和成像流程的差异会导致组织病理学图像出现显著的颜色变化，使得在部署从不同数据源训练的深度学习模型时泛化性能较差。目前已提出多种颜色增强方法，用于在训练期间生成合成图像，以提升模型的鲁棒性，从而无需在测试阶段进行染色归一化。许多颜色增强方法利用域标签生成合成图像，这种方法给模型的规模化应用带来三大挑战：首先，将新域的数据整合到基于现有域标签训练的深度学习模型中并非易事；其次，对域标签的依赖导致无法使用无域标签的病理图像来提升模型性能；最后，当单张图像关联多个域标签（如患者ID、医疗中心等）时，这类方法的实现会变得复杂。我们提出了ContriMix，这是一种基于风格迁移方法DRIT++的新型无域标签染色颜色增强方法。ContriMix利用训练小批次内样本的染色颜色变化和随机混合，从病理图像中提取内容和属性信息。训练好的ContriMix模型可利用这些信息生成合成图像，以提升现有分类器的性能。在Camelyon17-WILDS数据集上，ContriMix的性能优于同类竞争方法，其在测试集的不同切片上性能表现一致，同时对病理图像中罕见物质带来的颜色变化具有鲁棒性。我们公开了代码和训练好的ContriMix模型供研究使用，代码可在https://gitlab.com/huutan86/contrimix获取。
英文摘要：
Differences in staining and imaging procedures can cause significant color variations in histopathology images, leading to poor generalization when deploying deep-learning models trained from a different data source. Various color augmentation methods have been proposed to generate synthetic images during training to make models more robust, eliminating the need for stain normalization during test time. Many color augmentation methods leverage domain labels to generate synthetic images. This approach causes three significant challenges to scaling such a model. Firstly, incorporating data from a new domain into deep-learning models trained on existing domain labels is not straightforward. Secondly, dependency on domain labels prevents the use of pathology images without domain labels to improve model performance. Finally, implementation of these methods becomes complicated when multiple domain labels (e.g., patient identification, medical center, etc) are associated with a single image. We introduce ContriMix, a novel domain label free stain color augmentation method based on DRIT++, a style-transfer method. Contrimix leverages sample stain color variation within a training minibatch and random mixing to extract content and attribute information from pathology images. This information can be used by a trained ContriMix model to create synthetic images to improve the performance of existing classifiers. ContriMix outperforms competing methods on the Camelyon17-WILDS dataset. Its performance is consistent across different slides in the test set while being robust to the color variation from rare substances in pathology images. We make our code and trained ContriMix models available for research use. The code for ContriMix can be found at https://gitlab.com/huutan86/contrimix
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
