Abstract
Skin lesion segmentation plays a pivotal role in the diagnosis and treatment of skin diseases. By using deep neural networks to segment lesion areas, doctors can more accurately assess the severity of health-related conditions of patients and promptly implement appropriate treatment measures, thereby enhancing treatment outcomes and improving the quality of life (QoL) of patients. However, existing segmentation networks still face challenges in balancing segmentation performance and efficiency. To address this issue, a novel network, named AFCF-Net, is proposed in this paper for skin lesion segmentation tasks. Firstly, the proposed network employs a newly designed spatial channel feature calibration convolution (SCFCConv) to enhance its ability to perceive spatial and channel features. Secondly, AFCF-Net utilizes newly designed feature symmetric fusion convolution (FSFConv) in skip connections to selectively fuse features from different levels, thereby enhancing its sensitivity to texture, edges, and other detailed features. In addition, a feature attention recombination module (FARM) is added to the bottleneck of the proposed network to comprehensively acquire and utilize contextual information at different scales, thus improving the network's generalization ability. Finally, a newly designed multi-level feature aggregation branch is introduced as an additional decoder for AFCF-Net to supplement key features lost during the original decoding process. Experiments, conducted on four skin image datasets, demonstrate that the proposed AFCF-Net network achieves better segmentation performance with fewer parameters and computational resources, compared to state-of-the-art segmentation networks. Additionally, AFCF-Net exhibits stronger generalization ability.