Abstract
Accurate segmentation of vertebral metastasis in CT is clinically important yet difficult to scale, as voxel-level annotations are scarce and both lytic and blastic lesions often resemble benign degenerative changes. We introduce a weakly supervised method trained solely on vertebra-level healthy/malignant labels, without any lesion masks. The method combines a Diffusion Autoencoder (DAE) that produces a classifier-guided healthy edit of each vertebra with pixel-wise difference maps that propose candidate lesion regions. To determine which regions truly reflect malignancy, we introduce Hide-and-Seek Attribution: each candidate is revealed in turn while all others are hidden, the edited image is projected back to the data manifold by the DAE, and a latent-space classifier quantifies the isolated malignant contribution of that component. High-scoring regions form the final lytic or blastic segmentation. On held-out radiologist annotations, we achieve strong blastic/lytic performance despite no mask supervision (F1: 0.91/0.85; Dice: 0.87/0.78), exceeding baselines (F1: 0.79/0.67; Dice: 0.74/0.55). These results show that vertebra-level labels can be transformed into reliable lesion masks, demonstrating that generative editing combined with selective occlusion supports accurate weakly supervised segmentation in CT.
Abstract (translated)
在CT图像中对椎体转移瘤进行精确分割具有重要的临床意义，但这一过程难以规模化实施，因为像素级标注稀缺，并且溶骨性和成骨性病变往往与良性退行性改变相似。我们引入了一种仅基于椎体级别健康/恶性标签训练的弱监督方法，无需任何病灶掩码。该方法结合了扩散自动编码器（DAE），它根据分类器指导对每个椎体进行健康编辑，并生成像素级差异图来提出候选病变区域。为了确定哪些区域真正反映了恶性肿瘤特征，我们引入了“Hide-and-Seek Attribution”：逐个揭示每个候选区，同时隐藏所有其他区域，在用DAE将修改后的图像投影回数据流形后，通过潜在空间分类器量化被孤立的恶性成分贡献。得分较高的区域形成最终的溶骨性或成骨性分割结果。 在独立于放射科医生注释的数据集上，尽管没有病灶掩码监督，我们实现了出色的成骨/溶骨性能（F1: 0.91/0.85；Dice: 0.87/0.78），超过了基准方法（F1: 0.79/0.67；Dice: 0.74/0.55）。这些结果表明，椎体级别标签可以转换为可靠的病变掩码。结合生成编辑与选择性遮挡支持在CT图像中进行准确的弱监督分割。
URL
https://arxiv.org/abs/2512.06849
