{"slug": "anatomy-aware-synthesis-of-post-contrast-breast-mri-from-pre-contrast-images", "title": "Anatomy-Aware Synthesis of Post-Contrast Breast MRI from Pre-Contrast Images", "summary": "An anatomy-aware deep learning framework synthesized post-contrast breast MRI from pre-contrast images across 649 patients and 6,251 paired images, outperforming Pix2Pix, Pix2PixHD, diffusion-based synthesis, and mask-supervised baselines in whole-image and regional evaluations, according to an arXiv paper (2609.27015v1). The framework integrates breast mask consistency, lesion-region supervision, and background parenchymal enhancement (BPE) region supervision into an image-to-image translation model, and a reader study with two breast radiologists plus downstream Ki-67 classification found no statistically significant performance differences between real- and synthetic-image training and testing, though the authors state this does not establish equivalence. The authors conclude anatomy-aware supervision improves synthesis fidelity and support further investigation of synthetic post-contrast MRI for contrast-free imaging workflows.", "body_md": "arXiv:2609.27015v1 Announce Type: new \nAbstract: We developed an anatomy-aware deep learning framework to synthesize post-contrast breast MRI from pre-contrast images, emphasizing tumor and background parenchymal enhancement (BPE) regions. This retrospective study included 649 patients with 6,251 paired pre-contrast and post-contrast images. The framework integrates breast mask consistency, lesion-region supervision, and BPE-region supervision into an image-to-image translation model. Evaluation included quantitative image quality metrics, a reader study with two breast radiologists, and downstream Ki-67 classification. The proposed method outperformed Pix2Pix, Pix2PixHD, diffusion-based synthesis, and mask-supervised baselines in whole-image and regional evaluations. Ki-67 classification showed no statistically significant performance differences across real- and synthetic-image training and testing settings, although this does not establish equivalence. These findings suggest that anatomy-aware supervision improves synthesis fidelity and support further investigation of synthetic post-contrast MRI for contrast-free imaging workflows.", "url": "https://wpnews.pro/news/anatomy-aware-synthesis-of-post-contrast-breast-mri-from-pre-contrast-images", "canonical_source": "https://arxiv.org/abs/2609.27015", "published_at": "2026-09-24 04:00:00+00:00", "updated_at": "2026-09-24 04:01:37.418505+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision", "ai-research"], "entities": ["arXiv", "Pix2Pix", "Pix2PixHD", "Ki-67"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/anatomy-aware-synthesis-of-post-contrast-breast-mri-from-pre-contrast-images", "markdown": "https://wpnews.pro/news/anatomy-aware-synthesis-of-post-contrast-breast-mri-from-pre-contrast-images.md", "text": "https://wpnews.pro/news/anatomy-aware-synthesis-of-post-contrast-breast-mri-from-pre-contrast-images.txt", "jsonld": "https://wpnews.pro/news/anatomy-aware-synthesis-of-post-contrast-breast-mri-from-pre-contrast-images.jsonld"}}