SwinHR: Hemodynamic-powered hierarchical vision transformer for breast tumor segmentation

Zhihe Zhao, Siyao Du, Zeyan Xu, Zhi Yin, Xiaomei Huang, Xin Huang, Chinting Wong, Yanting Liang, Jing Shen, Jianlin Wu, Jinrong Qu, Lina Zhang, Yanfen Cui, Ying Wang, Leonard Wee, Andre Dekker, Chu Han, Zaiyi Liu, Zhenwei Shi, Changhong Liang

Abstract: Highlights•Accurate, automated dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) breast tumor segmentation is crucial.•A novel scheme named SwinHR for breast tumor segmentation, integrating hemodynamic-powered knowledge of DCE-MRI.•The current study includes 2246 patients from multiple medical centers.