通过器官掩码调控注意力，实现胸部X光片病灶的精准可控生成。
Mask-Guided Attention Regulation for Anatomically Consistent Counterfactual CXR Synthesis
- 用器官掩码限制注意力范围，防止解剖结构错乱。
- 早期去噪阶段强化病灶区域注意力，提升病变定位精度。
- 适合医学影像生成、病灶模拟与数据增强任务使用。
胸部X光片的反事实生成旨在模拟合理的病理变化，同时保留患者特异性解剖结构。然而，基于扩散模型的编辑方法常出现结构漂移问题：稳定的解剖语义通过注意力机制全局传播，导致非目标区域失真；且病灶表达不稳定，因细微局部病灶产生的条件信号微弱而嘈杂。本文提出一种推理时注意力调控框架，用于可靠反事实胸部X光生成。一个解剖感知注意力正则化模块，利用器官掩码对自注意力及解剖标记物与跨注意力进行门控，将结构交互限制在解剖感兴趣区域，减少意外失真。一个病灶引导模块在早期去噪阶段增强目标肺区内的病灶标记物跨注意力，并基于注意力集中能量执行轻量级潜在空间修正，实现可控制的病灶定位与范围。在多个胸部X光数据集上的广泛评估表明，相比标准扩散编辑，本方法显著提升了解剖一致性与病灶编辑的精确性与可控性，支持局部反事实分析与下游任务的数据增强。
原文摘要 · Abstract (English)
Counterfactual generation for chest X-rays (CXR) aims to simulate plausible pathological changes while preserving patient-specific anatomy. However, diffusion-based editing methods often suffer from structural drift, where stable anatomical semantics propagate globally through attention and distort non-target regions, and unstable pathology expression, since subtle and localized lesions induce weak and noisy conditioning signals. We present an inference-time attention regulation framework for reliable counterfactual CXR synthesis. An anatomy-aware attention regularization module gates self-attention and anatomy-token cross-attention with organ masks, confining structural interactions to anatomical ROIs and reducing unintended distortions. A pathology-guided module enhances pathology-token cross-attention within target lung regions during early denoising and performs lightweight latent corrections driven by an attention-concentration energy, enabling controllable lesion localization and extent. Extensive evaluations on CXR datasets show improved anatomical consistency and more precise, controllable pathological edits compared with standard diffusion editing, supporting localized counterfactual analysis and data augmentation for downstream tasks.
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。