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

arXiv: https://arxiv.org/abs/2512.06849 · HTML: https://mlsanity.com/paper/2512.06849/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 41 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN](https://mlsanity.com/paper/2207.07553/) (2022)
- [Weakly-Supervised Segmentation for Disease Localization in Chest X-Ray Images](https://mlsanity.com/paper/2007.00748/) (2020)
- [Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder](https://mlsanity.com/paper/2408.01571/) (2024)
- [CF-Seg: Counterfactuals meet Segmentation](https://mlsanity.com/paper/2506.16213/) (2025)
- [Weakly-Supervised Detection of Bone Lesions in CT](https://mlsanity.com/paper/2402.00175/) (2024)
- [COIN: Counterfactual inpainting for weakly supervised semantic segmentation for medical images](https://mlsanity.com/paper/2404.12832/) (2024)
- [Registration of Longitudinal Spine CTs for Monitoring Lesion Growth](https://mlsanity.com/paper/2402.09341/) (2024)

## Abstract (arXiv)

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 2D 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 suspect candidate lesions. 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.