AI 中文总结
研究针对医学成像中验证XAI方法缺少真实数据的问题，提出LLIFT框架，用GAN和扩散两种范式实现，能生成含真实病变的半合成脑磁共振图像，为评估XAI方法提供了可控真实数据，且评估效果良好。
AI 中文摘要
在医学成像中验证可解释人工智能（XAI）方法需要具有信息特征已知位置的真实数据。当前方法依赖易出错的专家注释或缺乏临床真实性的人工扰动。我们提出局部标签信息特征转移（LLIFT）框架，用于生成具有放置在用户控制区域的真实病变的半合成脑磁共振图像，训练时无需像素级病变注释。我们用两种生成范式实现LLIFT：LLIFT-GAN，一种仅从二元类标签学习病理特征的定制GAN；LLIFT-DM，一种基于扩散的通过ControlNet以边界框掩码为条件的图像修复管道。两种方法在源自人类连接组项目的脑磁共振成像数据上进行评估，都取得了与给定数据集中健康与病理图像的类间参考相当的Fréchet Inception Distance分数，定性检查也证实了病变结构的真实性。所得基准数据集为评估医学成像中的XAI方法提供了空间可控的真实数据。
英文摘要
Validating Explainable Artificial Intelligence (XAI) methods in medical imaging requires ground-truth data with known locations of informative features. However, current approaches rely on expert annotations, which are prone to labeling errors, or on hand-crafted artificial perturbations superimposed onto healthy images to mimic lesions or malignant features, which lack clinical realism. We present Local Label-Informed Feature Transfer (LLIFT), a framework for generating semi-synthetic brain magnetic resonance images with realistic lesions placed in user-controlled regions, which does not require pixel-level lesion annotations during training. We implement LLIFT with two generative paradigms: LLIFT-GAN, a custom GAN that learns pathological features from binary class labels alone, and LLIFT-DM, a diffusion-based inpainting pipeline conditioned on bounding-box masks via ControlNet. Both approaches are evaluated on brain magnetic resonance imaging data derived from the Human Connectome Project. In evaluations, both achieve Fréchet Inception Distance scores, with respect to the real pathological distribution, that are comparable to the inter-class reference between healthy and pathological images in the given dataset. Furthermore, qualitative inspection confirms the realism of lesion structures. The resulting benchmark datasets provide spatially controlled ground truth data for evaluating XAI methods in medical imaging.
Comments6 pages, submitted to IEEE MetroXRAINE 2026
