Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT

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.

---

Paper

The paper's preprint is available on arXiv:
Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT

If you use this repository, please cite:

@article{atad2025hideandseek,
  title={Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT},
  author={Atad, Matan and Marka, Alexander W. and Steinhelfer, Lisa and Curto-Vilalta, Anna and Leonhardt, Yannik and Foreman, Sarah C. and Dietrich, Anna-Sophia Walburga and Graf, Robert and Gersing, Alexandra S. and Menze, Bjoern and Rueckert, Daniel and Kirschke, Jan S. and M{\"o}ller, Hendrik},
  journal={arXiv preprint arXiv:2512.06849},
  year={2025},
  doi={10.48550/arXiv.2512.06849}
}

---

Code Availability

The full implementation will be added shortly. Stay tuned!