Medical data often exhibits distribution shifts, which cause test-time performance degradation for deep learning models trained using standard supervised learning pipelines. This challenge is addressed in the field of Domain Generalization (DG) with the sub-field of Single Domain Generalization (SDG) being specifically interesting due to the privacy- or logistics-related issues often associated with medical data. Existing disentanglement-based SDG methods heavily rely on structural information embedded in segmentation masks, however classification labels do not provide such dense information. This work introduces a novel SDG method aimed at medical image classification that leverages channel-wise contrastive disentanglement. It is further enhanced with reconstruction-based style regularization to ensure extraction of distinct style and structure feature representations. We evaluate our method on the complex task of multicenter histopathology image classification, comparing it against state-of-the-art (SOTA) SDG baselines. Results demonstrate that our method surpasses the SOTA by a margin of 1% in average accuracy while also showing more stable performance. This study highlights the importance and challenges of exploring SDG frameworks in the context of the classification task. The code is publicly available at https://github.com/BioMedIA-MBZUAI/ConDiSR

翻译：医学数据常存在分布偏移，这会导致使用标准监督学习流程训练的深度学习模型在测试时性能下降。域泛化（Domain Generalization, DG）领域致力于解决这一挑战，其中单域泛化（Single Domain Generalization, SDG）子领域因医学数据常涉及的隐私或物流相关问题而尤为引人关注。现有基于解缠的SDG方法严重依赖分割掩模中嵌入的结构信息，但分类标签无法提供此类密集信息。本文提出一种面向医学图像分类的新型SDG方法，该方法利用通道级对比解缠技术，并通过基于重建的风格正则化进一步增强，以确保提取到独特的风格与结构特征表示。我们在多中心组织病理学图像分类这一复杂任务上评估了该方法，并与当前最优（SOTA）的SDG基线进行了比较。结果表明，我们的方法在平均准确率上以1%的幅度超越SOTA，同时展现出更稳定的性能。本研究凸显了在分类任务背景下探索SDG框架的重要性与挑战性。代码已开源于https://github.com/BioMedIA-MBZUAI/ConDiSR