AdaptDiff：面向视网膜血管分割的基于弱条件语义扩散的跨模态域适应方法
AdaptDiff: Cross-Modality Domain Adaptation via Weak Conditional Semantic Diffusion for Retinal Vessel Segmentation
AI总结：
针对医学图像分割中跨模态域偏移且缺标注的问题，提出AdaptDiff无监督域适应方法，通过伪标签训练条件语义扩散模型生成目标域配对数据，微调分割网络以缩小域差距，在多模态公开数据集上实现性能显著提升。
摘要：
深度学习在医学图像分割领域已展现出优异性能，但在实际应用中仍面临诸多挑战：由于固有数据分布偏移，且缺乏人工标注引导域适应，模型难以有效迁移到未见过的域。为解决这一问题，我们提出一种名为AdaptDiff的无监督域适应（UDA）方法，可让在眼底照相（FP）上训练的视网膜血管分割网络，在无任何人工标注的情况下，在未见过的模态（如OCT-A）上取得令人满意的效果。对于所有目标域，我们首先采用在源域上训练的分割模型生成伪标签，再利用这些伪标签训练一个条件语义扩散概率模型，以表征目标域分布。实验表明，即便伪标签质量较低，该扩散模型仍能捕捉到条件语义信息。随后，我们使用来自源域的二值血管掩码在目标域上采样，得到配对数据，即以二值血管图为条件生成的目标域合成图像。最后，我们使用合成的配对数据微调预训练的分割网络，以缩小域间差距。我们在涵盖三种不同模态的七个公开数据集上评估了AdaptDiff的有效性，结果显示该方法在所有未见过的数据集上的分割性能均有显著提升。我们的代码已公开发布于https://github.com/DeweiHu/AdaptDiff。
英文摘要：
Deep learning has shown remarkable performance in medical image segmentation. However, despite its promise, deep learning has many challenges in practice due to its inability to effectively transition to unseen domains, caused by the inherent data distribution shift and the lack of manual annotations to guide domain adaptation. To tackle this problem, we present an unsupervised domain adaptation (UDA) method named AdaptDiff that enables a retinal vessel segmentation network trained on fundus photography (FP) to produce satisfactory results on unseen modalities (e.g., OCT-A) without any manual labels. For all our target domains, we first adopt a segmentation model trained on the source domain to create pseudo-labels. With these pseudo-labels, we train a conditional semantic diffusion probabilistic model to represent the target domain distribution. Experimentally, we show that even with low quality pseudo-labels, the diffusion model can still capture the conditional semantic information. Subsequently, we sample on the target domain with binary vessel masks from the source domain to get paired data, i.e., target domain synthetic images conditioned on the binary vessel map. Finally, we fine-tune the pre-trained segmentation network using the synthetic paired data to mitigate the domain gap. We assess the effectiveness of AdaptDiff on seven publicly available datasets across three distinct modalities. Our results demonstrate a significant improvement in segmentation performance across all unseen datasets. Our code is publicly available at https://github.com/DeweiHu/AdaptDiff.
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。
