SimGen: A Diffusion-Based Framework for Simultaneous Surgical Image and Segmentation Mask 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_ | 1866913652003569664 |
|---|---|
| author | Bhat, Aditya Bose, Rupak Nwoye, Chinedu Innocent Padoy, Nicolas |
| author_facet | Bhat, Aditya Bose, Rupak Nwoye, Chinedu Innocent Padoy, Nicolas |
| contents | Acquiring and annotating surgical data is often resource-intensive, ethical constraining, and requiring significant expert involvement. While generative AI models like text-to-image can alleviate data scarcity, incorporating spatial annotations, such as segmentation masks, is crucial for precision-driven surgical applications, simulation, and education. This study introduces both a novel task and method, SimGen, for Simultaneous Image and Mask Generation. SimGen is a diffusion model based on the DDPM framework and Residual U-Net, designed to jointly generate high-fidelity surgical images and their corresponding segmentation masks. The model leverages cross-correlation priors to capture dependencies between continuous image and discrete mask distributions. Additionally, a Canonical Fibonacci Lattice (CFL) is employed to enhance class separability and uniformity in the RGB space of the masks. SimGen delivers high-fidelity images and accurate segmentation masks, outperforming baselines across six public datasets assessed on image and semantic inception distance metrics. Ablation study shows that the CFL improves mask quality and spatial separation. Downstream experiments suggest generated image-mask pairs are usable if regulations limit human data release for research. This work offers a cost-effective solution for generating paired surgical images and complex labels, advancing surgical AI development by reducing the need for expensive manual annotations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09008 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SimGen: A Diffusion-Based Framework for Simultaneous Surgical Image and Segmentation Mask Generation Bhat, Aditya Bose, Rupak Nwoye, Chinedu Innocent Padoy, Nicolas Computer Vision and Pattern Recognition Acquiring and annotating surgical data is often resource-intensive, ethical constraining, and requiring significant expert involvement. While generative AI models like text-to-image can alleviate data scarcity, incorporating spatial annotations, such as segmentation masks, is crucial for precision-driven surgical applications, simulation, and education. This study introduces both a novel task and method, SimGen, for Simultaneous Image and Mask Generation. SimGen is a diffusion model based on the DDPM framework and Residual U-Net, designed to jointly generate high-fidelity surgical images and their corresponding segmentation masks. The model leverages cross-correlation priors to capture dependencies between continuous image and discrete mask distributions. Additionally, a Canonical Fibonacci Lattice (CFL) is employed to enhance class separability and uniformity in the RGB space of the masks. SimGen delivers high-fidelity images and accurate segmentation masks, outperforming baselines across six public datasets assessed on image and semantic inception distance metrics. Ablation study shows that the CFL improves mask quality and spatial separation. Downstream experiments suggest generated image-mask pairs are usable if regulations limit human data release for research. This work offers a cost-effective solution for generating paired surgical images and complex labels, advancing surgical AI development by reducing the need for expensive manual annotations. |
| title | SimGen: A Diffusion-Based Framework for Simultaneous Surgical Image and Segmentation Mask Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.09008 |