通过语义堆叠提升医学图像分割的鲁棒性，无需领域知识
S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging
- 引入无领域依赖的语义堆叠方法，融合多帧语义信息增强分割
- 在多种模态和数据集上显著提升分割精度，尤其在低数据场景下
- 适合缺乏标注数据或领域知识的医学图像分割任务
医学图像分割的鲁棒性和泛化能力常受训练数据稀缺与多样性不足的制约，而推理时却面临真实场景的高变异性。传统方法如领域特定增强、专用架构和定制训练虽有缓解作用，但依赖可靠领域知识。当知识缺失或错误时，性能反而下降。为此，我们提出一种全新的、无需领域知识的附加式数据驱动策略——语义堆叠。该方法受图像去噪中图像堆叠启发，训练时估计一个去噪后的语义表示，作为常规分割损失的补充。该方法不依赖领域假设，可广泛适用于不同图像模态、模型结构和增强方式。大量实验验证了其在多种条件下的优越性。代码已开源：https://github.com/ymp5078/Semantic-Stacking。
原文摘要 · Abstract (English)
Robustness and generalizability in medical image segmentation are often hindered by scarcity and limited diversity of training data, which stands in contrast to the variability encountered during inference. While conventional strategies -- such as domain-specific augmentation, specialized architectures, and tailored training procedures -- can alleviate these issues, they depend on the availability and reliability of domain knowledge. When such knowledge is unavailable, misleading, or improperly applied, performance may deteriorate. In response, we introduce a novel, domain-agnostic, add-on, and data-driven strategy inspired by image stacking in image denoising. Termed ``semantic stacking,'' our method estimates a denoised semantic representation that complements the conventional segmentation loss during training. This method does not depend on domain-specific assumptions, making it broadly applicable across diverse image modalities, model architectures, and augmentation techniques. Through extensive experiments, we validate the superiority of our approach in improving segmentation performance under diverse conditions. Code is available at https://github.com/ymp5078/Semantic-Stacking.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。