SAFE-Diff: Scale-Aware Attention and Feature-Dispersive Diffusion with Uncertainty Estimation for Contrast-Enhanced Breast MRI Synthesis

2026-05-25Computer Vision and Pattern Recognition

Computer Vision and Pattern Recognition
AI summary

The authors explain that creating detailed and accurate contrast-enhanced MRI images is important for improving breast cancer screening, making it safer and faster. However, this is difficult because the images show complicated textures and varied patterns of how lesions absorb contrast. Their work focuses on addressing these challenges to improve the quality of MRI synthesis.

MRIcontrast enhancementbreast cancer screeninglesion textureheterogeneous enhancementmedical imagingimage synthesisradiology
Authors
Tianyu Zhang, Xinglong Liang, Jarek van Dijk, Luyi Han, Chunyao Lu, Antonio Portaluri, Xinghe Xie, Yaofei Duan, Nika Rasoolzadeh, Xin Wang, Yuan Gao, Muzhen He, Yue Sun, Jonas Teuwen, Tao Tan, Ritse Mann
Abstract
Synthesizing high fidelity contrast enhanced MRI is clinically valuable for safer and more efficient breast cancer screening, yet remains challenging due to complex lesion textures and heterogeneous enhancement patterns.