iMSCGnet: Iterative Multi-Scale Context-Guided Segmentation of Skin Lesion in Dermoscopic Images

Despite much effort has been devoted to skin lesion segmentation, the performance of existing methods is still not satisfactory enough for practical applications. The challenges may include fuzzy lesion boundary, uneven and low contrast, and variation of colors across space, which often lead to fragmentary segmentation and inaccurate boundary. To alleviate this problem, we propose a multi-scale context-guided network named as MSCGnet to segment the skin lesions accurately. In MSCGnet, the context information is utilized to guide the feature encoding procedure. Moreover, because of the information loss in spatial down-sampling, a context-based attention structure (CAs) is designed to select effective context features in the decoding path. Furthermore, we boost the performance of MSCGnet with iterations and term this upgraded version as iterative MSCGnet, denoted as iMSCGnet. To supervise the training of iMSCGnet in an end-to-end fashion, a novel objective function of deep supervision, which consists of the terms of each encoding layers and the terms from each MSCGnet output of iMSCGnet, is employed. Our method is evaluated extensively on the four publicly available datasets, including ISBI2016 [1], ISBI2017 [2], ISIC2018 [3] and PH2 [4] datasets. The experimental results prove the effectiveness of proposed components and show that our method generally outperforms the state-of-the-art methods.