See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912753601478656 |
|---|---|
| author | Liu, Junqi Wu, Zejun Bassi, Pedro R. A. S. Zhou, Xinze Li, Wenxuan Hamamci, Ibrahim E. Er, Sezgin Lin, Tianyu Luo, Yi Płotka, Szymon Menze, Bjoern Xu, Daguang Ding, Kai Wang, Kang Yang, Yang Tang, Yucheng Yuille, Alan L. Zhou, Zongwei |
| author_facet | Liu, Junqi Wu, Zejun Bassi, Pedro R. A. S. Zhou, Xinze Li, Wenxuan Hamamci, Ibrahim E. Er, Sezgin Lin, Tianyu Luo, Yi Płotka, Szymon Menze, Bjoern Xu, Daguang Ding, Kai Wang, Kang Yang, Yang Tang, Yucheng Yuille, Alan L. Zhou, Zongwei |
| contents | Image enhancement improves visual quality and helps reveal details that are hard to see in the original image. In medical imaging, it can support clinical decision-making, but current models often over-edit. This can distort organs, create false findings, and miss small tumors because these models do not understand anatomy or contrast dynamics. We propose SMILE, an anatomy-aware diffusion model that learns how organs are shaped and how they take up contrast. It enhances only clinically relevant regions while leaving all other areas unchanged. SMILE introduces three key ideas: (1) structure-aware supervision that follows true organ boundaries and contrast patterns; (2) registration-free learning that works directly with unaligned multi-phase CT scans; (3) unified inference that provides fast and consistent enhancement across all contrast phases. Across six external datasets, SMILE outperforms existing methods in image quality (14.2% higher SSIM, 20.6% higher PSNR, 50% better FID) and in clinical usefulness by producing anatomically accurate and diagnostically meaningful images. SMILE also improves cancer detection from non-contrast CT, raising the F1 score by up to 10 percent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07251 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement Liu, Junqi Wu, Zejun Bassi, Pedro R. A. S. Zhou, Xinze Li, Wenxuan Hamamci, Ibrahim E. Er, Sezgin Lin, Tianyu Luo, Yi Płotka, Szymon Menze, Bjoern Xu, Daguang Ding, Kai Wang, Kang Yang, Yang Tang, Yucheng Yuille, Alan L. Zhou, Zongwei Computer Vision and Pattern Recognition Image enhancement improves visual quality and helps reveal details that are hard to see in the original image. In medical imaging, it can support clinical decision-making, but current models often over-edit. This can distort organs, create false findings, and miss small tumors because these models do not understand anatomy or contrast dynamics. We propose SMILE, an anatomy-aware diffusion model that learns how organs are shaped and how they take up contrast. It enhances only clinically relevant regions while leaving all other areas unchanged. SMILE introduces three key ideas: (1) structure-aware supervision that follows true organ boundaries and contrast patterns; (2) registration-free learning that works directly with unaligned multi-phase CT scans; (3) unified inference that provides fast and consistent enhancement across all contrast phases. Across six external datasets, SMILE outperforms existing methods in image quality (14.2% higher SSIM, 20.6% higher PSNR, 50% better FID) and in clinical usefulness by producing anatomically accurate and diagnostically meaningful images. SMILE also improves cancer detection from non-contrast CT, raising the F1 score by up to 10 percent. |
| title | See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.07251 |