scSEETV-Net: Spatial and Channel Squeeze-Excitation and Edge Attention Guidance V-Shaped Network for Skin Lesion Segmentation

Abstract

Early detection of skin cancer ensures the survival of many cases. There are still challenges in segmenting dermoscopic skin lesion images. Artifacts in the lesion images, such as various dirt, hairs, low contrast, and unclear boundaries, are challenges that affect segmentation accuracy. Convolutional neural networks have brought success in skin lesion segmentation. U-shaped and V-shaped deep learning-based segmentation architectures learn boundary information in the first layers. However, this information becomes weaker in the following layers. Herein, the Edge-aTtention module is added to the V-Net architecture to move edge information to the last layer, and the spatial and channel squeeze-excitation module is added to emphasize high-level features by recalibrating the channel information to learn lesion boundaries better. The scSEETV-Net is supported by fusing the binary cross-entropy, which calculates the loss on a pixel-based, and the focal Twersky loss function, which has significant success in class imbalances. The proposed architecture achieves 0.9212 Jaccard and 0.9552 Dice in the ISIC2016 dataset, 0.8273 Jaccard and 0.8949 Dice in the ISIC2017 dataset, and 0.8070 Jaccard and 0.8831 Dice in the ISIC2018 dataset. Comparative analyses show that the proposed methodology outperforms the state-of-the-art techniques in the literature.