HTC-Net: A hybrid CNN-transformer framework for medical image segmentation

Hui Tang, Yuanbin Chen, Tao Wang, Yuanbo Zhou, Longxuan Zhao, Qinquan Gao, Min Du, Tao Tan, Xinlin Zhang, Tong Tong

Abstract: Highlights•Proposed an encoder–decoder architecture that integrates DCNNs and Transformer.•Proposed a TMF block that dynamically fuses semantic information in high-level features.•Proposed a UA block that combines spatial attention and channel attention.