用解剖结构对齐差异，让医学图像识别更可解释、更准确。
Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identification
- 构建解剖图谱，通过节点对应计算同源部位差异。
- 在眼底和胸部影像上分别提升7.1%和3.1%的召回率。
- 结果基于可验证的解剖节点，适合临床可审计场景。
医学图像重识别（MedReID）可用于患者纵向关联，但易受捷径学习影响，且决策难以与具体解剖结构对齐。本文提出图-差异模型（GoD），将身份比对锚定在显式的解剖结构上。每张图像被表示为解剖图，节点对应命名解剖区域；给定图像对后，建立软节点对应关系，并在匹配解剖区域上计算差异。图级差异对齐目标将这些解剖匹配差异与全局骨干网络差异关联，确保检索信号基于同源结构而非任意空间特征。解释性基于命名图节点定义，并通过节点插入/删除测试量化验证，以可验证的结构级证据替代不稳定的像素热图。在内部基准上，GoD相较于强基线在眼底图像上提升Rank-1 7.1个百分点，在胸部X光上提升3.1个百分点；零样本外部迁移实验进一步证实解剖结构引导显著提升准确率与泛化能力。代码已开源：https://github.com/GenMI-Lab/GoD.git。
原文摘要 · Abstract (English)
Medical image re-identification (MedReID) enables longitudinal patient linkage but remains vulnerable to shortcut learning and often produces decisions that clinicians cannot audit against named anatomy. We propose Graph-of-Differences (GoD), which grounds identity comparisons in explicit anatomical structure. Each image is represented as an anatomy graph whose nodes correspond to named anatomical regions; given an image pair, soft node correspondence is established, and differences are computed over matched anatomy. A graph-level difference alignment objective ties these anatomy-matched differences to the global backbone difference, ensuring the retrieval signal is anchored in homologous structures rather than arbitrary spatial tokens. Explanations are defined over named graph nodes and quantitatively audited via node insertion/deletion tests, replacing unstable pixel heatmaps with verifiable structure-level evidence. On internal benchmarks, GoD improves Rank-1 by +7.1 pp on fundus and +3.1 pp on CXR over a strong frozen-backbone baseline, with further gains on zero-shot external transfers confirming that anatomy grounding improves both accuracy and generalization. Code is available at https://github.com/GenMI-Lab/GoD.git.
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。