Zhang Huiying, Li Yongmeng, He Lei, Zhang Wenbo, Shen Yuchen, Xing Lumin
Department of Thoracic Surgery, Qilu Hospital of Shandong University, Jinan, Shandong, China.
The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, Shandong, China.
PLoS One. 2025 Jul 23;20(7):e0323676. doi: 10.1371/journal.pone.0323676. eCollection 2025.
Multi-source domain adaptation leverages complementary knowledge from multiple source domains to enhance transfer effectiveness, making it more suitable for complex medical scenarios compared to single-source domain adaptation. However, most existing studies operate under the assumption that the source and target domains share identical class distributions, leaving the challenge of addressing class shift in multi-source domain adaptation largely unexplored. To address this gap, this study proposes a Class-Aware Multi-Source Domain Adaptation algorithm based on a Reweighted Matrix Matching strategy (CAMSDA-RMM). This algorithm employs a class-aware strategy to strengthen positive transfer effects between similar classes. Additionally, first-order and second-order moment matching strategies are applied to effectively align the source and target domains, while an adaptive weighting mechanism is utilized to optimize the contributions of different source domains to the target domain. These approaches collectively improve classification accuracy and domain adaptability. Experimental results on four publicly available chest X-ray datasets demonstrate that the superiority of the proposed method.
多源域适应利用来自多个源域的互补知识来提高迁移效果，与单源域适应相比，它更适合复杂的医学场景。然而，大多数现有研究是在源域和目标域共享相同类分布的假设下进行的，多源域适应中解决类转移的挑战在很大程度上尚未得到探索。为了弥补这一差距，本研究提出了一种基于重加权矩阵匹配策略的类感知多源域适应算法（CAMSDA-RMM）。该算法采用类感知策略来加强相似类之间的正向迁移效果。此外，应用一阶和二阶矩匹配策略来有效地对齐源域和目标域，同时利用自适应加权机制来优化不同源域对目标域的贡献。这些方法共同提高了分类准确率和域适应性。在四个公开可用的胸部X光数据集上进行实验，结果验证了所提方法的优越性。
