Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914465522384896 |
|---|---|
| author | Atad, Matan Marka, Alexander W. Steinhelfer, Lisa Curto-Vilalta, Anna Leonhardt, Yannik Foreman, Sarah C. Dietrich, Anna-Sophia Walburga Graf, Robert Gersing, Alexandra S. Menze, Bjoern Rueckert, Daniel Kirschke, Jan S. Möller, Hendrik |
| author_facet | Atad, Matan Marka, Alexander W. Steinhelfer, Lisa Curto-Vilalta, Anna Leonhardt, Yannik Foreman, Sarah C. Dietrich, Anna-Sophia Walburga Graf, Robert Gersing, Alexandra S. Menze, Bjoern Rueckert, Daniel Kirschke, Jan S. Möller, Hendrik |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06849 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT Atad, Matan Marka, Alexander W. Steinhelfer, Lisa Curto-Vilalta, Anna Leonhardt, Yannik Foreman, Sarah C. Dietrich, Anna-Sophia Walburga Graf, Robert Gersing, Alexandra S. Menze, Bjoern Rueckert, Daniel Kirschke, Jan S. Möller, Hendrik Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Hide-and-Seek Attribution: Weakly Supervised Segmentation of Vertebral Metastases in CT |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2512.06849 |