arXiv:2512.16685cs.CVcs.AI2025-12

用少量影像识别医学影像中同一患者,防止数据泄露。

Few-Shot Fingerprinting Subject Re-Identification in 3D-MRI and 2D-X-Ray

  • 通过嵌入空间指纹映射,实现跨数据集的患者身份匹配。
  • 在20类1样本下准确率达99.1%,100类3样本下仍超98%。
  • 适合医疗数据共享与隐私保护场景,尤其关注小样本应用。

将多个开源数据集合并使用可能因同一受试者出现在多个数据集中导致数据泄露,从而虚高模型性能。为解决此问题,本文探索基于受试者指纹的方法,将同一受试者的全部影像映射至潜在空间中的唯一区域,通过相似性匹配实现受试者重识别。采用以三元组损失训练的ResNet-50模型,在标准(20类1样本)和挑战性(1000类1样本)场景下评估了3D MRI与2D X-ray数据上的少样本指纹识别效果。结果显示:在ChestXray-14数据集上,20类1样本时平均召回率@K达99.10%,500类5样本时达90.06%;在BraTS-2021数据集上,20类1样本时为99.20%,100类3样本时为98.86%。

原文摘要 · Abstract (English)

Combining open-source datasets can introduce data leakage if the same subject appears in multiple sets, leading to inflated model performance. To address this, we explore subject fingerprinting, mapping all images of a subject to a distinct region in latent space, to enable subject re-identification via similarity matching. Using a ResNet-50 trained with triplet margin loss, we evaluate few-shot fingerprinting on 3D MRI and 2D X-ray data in both standard (20-way 1-shot) and challenging (1000-way 1-shot) scenarios. The model achieves high Mean- Recall-@-K scores: 99.10% (20-way 1-shot) and 90.06% (500-way 5-shot) on ChestXray-14; 99.20% (20-way 1-shot) and 98.86% (100-way 3-shot) on BraTS- 2021.

医学影像少样本学习数据隐私

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。