GLF-Segformer: An improved Segformer model integrating local and global information for skin cancer image segmentation

Abstract:

More accurate segmentation of skin cancers in dermoscopy images is crucial for clinical treatment. However, the prevalence of interfering noise in dermoscopy images poses a challenge to its accurate segmentation. For this reason, this paper proposes an improved GLF-Segformer to improve segmentation. The model adds PSA and R-CAFM modules to the Segformer's encoder to enhance the ability to capture local information and facilitate the effective fusion of local and global information. The decoder employs an innovative two-stage hybrid up-sampling to effectively reduce information loss. In addition, a new hybrid loss function is designed to further improve the segmentation accuracy of the model at complex boundaries. The experimental results show that GLF-Segformer achieves 89.9% and 89.48% mIoU on two standard datasets, ISIC2017 and ISIC2018, respectively, and exhibits better segmentation performance compared to other comparison algorithms.

Key words:Skin cancer image segmentation, Segformer, attention mechanism, deconvolution