EH-former: Regional easy-hard-aware transformer for breast lesion segmentation in ultrasound images

Xiaolei Qu, Jiale Zhou, Jue Jiang, Wenhan Wang, Haoran Wang, Shuai Wang, Wenzhong Tang, Xun Lin

Abstract: Highlights•A region-wise CL is proposed to learn regional features from easy to hard.•An uncertainty-based regularization method is proposed to separate easy and hard regional features.•A dynamic fusion method is proposed to dynamically modulates the fusion weights of easy and hard regional features.•Extensive experimental results verify the superior performance of the proposed EH-Former.