Complementary Network with Adaptive Receptive Fields for Melanoma Segmentation

Automatic melanoma segmentation in dermoscopic images is essential in computer-aided diagnosis of skin cancer. Existing methods may suffer from the hole and shrink problems with limited segmentation performance. To tackle these issues, we propose a novel complementary network with adaptive receptive filed learning. Instead of regarding the segmenta- tion task independently, we introduce a foreground network to detect melanoma lesions and a background network to mask non-melanoma regions. Moreover, we propose adap- tive atrous convolution (AAC) and knowledge aggregation module (KAM) to fill holes and alleviate the shrink prob- lems. AAC explicitly controls the receptive field at multiple scales and KAM convolves shallow feature maps by dilated convolutions with adaptive receptive fields, which are ad- justed according to deep feature maps. In addition, a novel mutual loss is proposed to utilize the dependency between the foreground and background networks, thereby enabling the reciprocally influence within these two networks. Con- sequently, this mutual training strategy enables the semi- supervised learning and improve the boundary-sensitivity. Training with Skin Imaging Collaboration (ISIC) 2018 skin lesion segmentation dataset, our method achieves a dice co- efficient of 86.4% and shows better performance compared with state-of-the-art melanoma segmentation methods.