Rethinking automatic segmentation of gross target volume from a decoupling perspective

Jun Shi, Zhaohui Wang, Shulan Ruan, Minfan Zhao, Ziqi Zhu, Hongyu Kan, Hong An, Xudong Xue, Bing Yan

Abstract: Highlights•The decoupled two-stage segmentation framework can efficiently reduce false positives.•Spatial alignment module can compensate for the information loss caused by downsampling.•A novel combined regularization loss is proposed to alleviate the pixel imbalance problem.