空间门控扩散用于局部化胸部X光片反事实编辑
Spatially Gated Diffusion for Localized Counterfactual Chest Radiograph Editing
浏览论文内容
中文总结 AI 辅助
本研究提出一种空间门控潜在扩散方法，通过门控混合源与编辑轨迹并应用图像空间掩码，在胸部X光片反事实编辑中实现高目标完成率（97.4%）和联合有效性（93.5%），同时有效保留无关内容。
中文摘要 AI 辅助
编辑胸部X光片需要在完成所需更改的同时保留无关内容。我们研究了一种潜在扩散编辑器，其具有与指令无关的源轨迹和指令条件化的编辑轨迹。一个学习得到的门控在每个执行步骤中混合它们采样后的候选结果，并且一个独立的图像空间掩码将解码后的提议与源图像合成。在2,400个源自MIMIC的请求中，2,244个输出满足了联合目标、保留、质量和覆盖度标准（93.5%），目标完成率为97.4%。联合有效性超过了匹配的仅合成对照组1.7个百分点（配对患者簇95%区间，0.6--2.8）。在固定学习掩码下，学习门控提议将联合有效性提高了1.6个百分点（0.8--2.4）；在固定学习提议下，学习掩码将其提高了2.6个百分点（1.7--3.5）。在三个训练种子下，平均联合有效性为93.5%，样本标准差为0.3个百分点。一项盲法240请求评估得出，完整编辑器的裁定联合有效性为93.3%，而仅合成为91.7%。受保护区域的平均绝对误差从原始提议中的0.0190降至合成后的0.0075。这些发现区分了在评估队列中，循环门控对提议的影响与通过最终合成实现的保留效果。
英文摘要
Editing a chest radiograph requires completing the requested change while preserving unrelated content. We study a latent diffusion editor with an instruction-independent source trajectory and an instruction-conditioned editing trajectory. A learned gate mixes their post-sampler candidates at each executed step, and a separate image-space mask composites the decoded proposal with the source. On 2,400 MIMIC-derived requests, 2,244 outputs met the joint target, preservation, quality, and coverage rubric (93.5%), and target completion was 97.4%. Joint validity exceeded a matched composition-only control by 1.7 percentage points (paired patient-cluster 95% interval, 0.6--2.8). At a fixed learned mask, the learned-gate proposal improved joint validity by 1.6 points (0.8--2.4); at a fixed learned proposal, the learned mask improved it by 2.6 points (1.7--3.5). Across three training seeds, mean joint validity was 93.5% with a 0.3-point sample standard deviation. A blinded 240-request assessment yielded adjudicated joint validity of 93.3% for the full editor and 91.7% for composition only. Protected-region mean absolute error decreased from 0.0190 in the raw proposal to 0.0075 after composition. These findings distinguish recurrent-gating effects on the proposal from preservation through final composition in the assessed cohort.
发表机构
- COMSATS University Islamabad（伊斯兰堡COMSATS大学）
机构由 AI 辅助整理，请以论文原文为准。
