Graph Conditioned Diffusion for Controllable Histopathology Image Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909831476019200 |
|---|---|
| author | Cechnicka, Sarah Baugh, Matthew Zhang, Weitong Dombrowski, Mischa Li, Zhe Paetzold, Johannes C. Roufosse, Candice Kainz, Bernhard |
| author_facet | Cechnicka, Sarah Baugh, Matthew Zhang, Weitong Dombrowski, Mischa Li, Zhe Paetzold, Johannes C. Roufosse, Candice Kainz, Bernhard |
| contents | Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sensitive areas such as medical imaging. Medical images feature inherent structure such as consistent spatial arrangement, shape or texture, all of which are critical for diagnosis. However, existing DPMs operate in noisy latent spaces that lack semantic structure and strong priors, making it difficult to ensure meaningful control over generated content. To address this, we propose graph-based object-level representations for Graph-Conditioned-Diffusion. Our approach generates graph nodes corresponding to each major structure in the image, encapsulating their individual features and relationships. These graph representations are processed by a transformer module and integrated into a diffusion model via the text-conditioning mechanism, enabling fine-grained control over generation. We evaluate this approach using a real-world histopathology use case, demonstrating that our generated data can reliably substitute for annotated patient data in downstream segmentation tasks. The code is available here. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07129 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph Conditioned Diffusion for Controllable Histopathology Image Generation Cechnicka, Sarah Baugh, Matthew Zhang, Weitong Dombrowski, Mischa Li, Zhe Paetzold, Johannes C. Roufosse, Candice Kainz, Bernhard Computer Vision and Pattern Recognition Artificial Intelligence Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sensitive areas such as medical imaging. Medical images feature inherent structure such as consistent spatial arrangement, shape or texture, all of which are critical for diagnosis. However, existing DPMs operate in noisy latent spaces that lack semantic structure and strong priors, making it difficult to ensure meaningful control over generated content. To address this, we propose graph-based object-level representations for Graph-Conditioned-Diffusion. Our approach generates graph nodes corresponding to each major structure in the image, encapsulating their individual features and relationships. These graph representations are processed by a transformer module and integrated into a diffusion model via the text-conditioning mechanism, enabling fine-grained control over generation. We evaluate this approach using a real-world histopathology use case, demonstrating that our generated data can reliably substitute for annotated patient data in downstream segmentation tasks. The code is available here. |
| title | Graph Conditioned Diffusion for Controllable Histopathology Image Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.07129 |