Attentive boundary aware network for multi-scale skin lesion segmentation with adversarial training

Because of the large variation in appearance, the existence of artifacts, the low contrast, skin lesion segmentation remains a challenging task. In this paper, we propose a novel Scale Attention based Atrous Spatial Pyramid Pooling (Scale-Att-ASPP) module for skin lesion segmentation with attentive boundary aware. Our network is based on the Generative Adversarial Network (GAN), which includes the segmentation network and the critic network. In the segmentation network, we design the Scale-Att-ASPP module to automatically select the optimal scale of the skin lesion feature of the intermediate convolution layer (Inter-CL) in the encoding path, meanwhile, the irrelevant artifacts features are automatically diminished without using complex pre-processing. After introducing the output of the Scale-Att-ASPP module to the same level layer in the decoding path through skip connection in pixel-wise addition way, the more meaningful semantic segmentation is gained. The Jaccard distance loss is employed to solve the problem of label imbalance in skin lesion segmentation. Our network is adversarially trained on ISBI 2017 dataset by the multi-scale L₁ loss introduced by the critic network, which guides the Scale-Att-ASPP module learning to focus on the optimal scale of the skin lesion feature. Finally, our network significantly improves the segmentation performance compared with other state-of-the-art methods, especially for the JAC and SEN scores. Besides, our proposed network works efficiently and shows robustness for different datasets.