Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2601.15884 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914541482278912 |
|---|---|
| author | Chen, Yifan Yin, Fei Chen, Hao Wu, Jia Li, Chao |
| author_facet | Chen, Yifan Yin, Fei Chen, Hao Wu, Jia Li, Chao |
| contents | Contrast-enhanced imaging is central to oncologic diagnosis, but contrast agents can be contraindicated for many of the patients who need them most. Synthesizing contrast scans from non-contrast inputs is the natural response. Two obstacles stand in the way: no benchmark provides paired contrast data with lesion-level evaluation, and no single model handles the arbitrary missing patterns seen in practice. We introduce Contrast-X, a benchmark of paired contrast-enhanced and non-contrast imaging spanning 10 organs in CT (1{,}526 patients) and multi-phase breast DCE-MRI (1116 patients). Every case carries radiologist-verified phase labels and tumor masks. We further propose FlowMI, a single model that handles arbitrary subsets of available modalities through a unified multi-modal latent space and flow matching. We benchmark a range of missing-modality configurations, reporting standard image-quality metrics, radiologist reader studies, and downstream lesion analysis on the synthesized scans. We further evaluate cross-organ generalization to test whether the model has learned a transferable contrast-enhancement operation. Dataset, code, and leaderboard will be released. Our code are available at https://github.com/YifanChen02/Contrast-X. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_15884 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching Chen, Yifan Yin, Fei Chen, Hao Wu, Jia Li, Chao Computer Vision and Pattern Recognition Contrast-enhanced imaging is central to oncologic diagnosis, but contrast agents can be contraindicated for many of the patients who need them most. Synthesizing contrast scans from non-contrast inputs is the natural response. Two obstacles stand in the way: no benchmark provides paired contrast data with lesion-level evaluation, and no single model handles the arbitrary missing patterns seen in practice. We introduce Contrast-X, a benchmark of paired contrast-enhanced and non-contrast imaging spanning 10 organs in CT (1{,}526 patients) and multi-phase breast DCE-MRI (1116 patients). Every case carries radiologist-verified phase labels and tumor masks. We further propose FlowMI, a single model that handles arbitrary subsets of available modalities through a unified multi-modal latent space and flow matching. We benchmark a range of missing-modality configurations, reporting standard image-quality metrics, radiologist reader studies, and downstream lesion analysis on the synthesized scans. We further evaluate cross-organ generalization to test whether the model has learned a transferable contrast-enhancement operation. Dataset, code, and leaderboard will be released. Our code are available at https://github.com/YifanChen02/Contrast-X. |
| title | Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.15884 |