Skin lesion segmentation from dermoscopic images by using Mask R-CNN, Retina-Deeplab, and graph-based methods

Abstract

Background and objectiveTimely diagnosis of skin cancer which is one of the most common cancers can greatly prevent death. Automatic skin lesion segmentation is an important part of an automatic skin cancer diagnosis system. Due to the wide variety in color, location, size, shape, and boundary contrast of lesions, the lesion segmentation is still a challenging problem. MethodsIn this study, we present a two-stage automatic skin lesion segmentation method. In the first stage, a detection-based segmentation structure, Retina-Deeplab, is proposed to be combined with the Mask R-CNN, which inherently detects and segments objects simultaneously. To combine the results of these two segmentation methods, two geodesic-based and graph-based combination approaches are proposed. ResultsThe proposed method is evaluated using three well-known skin image datasets (ISBI 2017, DermQuest, and PH2). Through the proposed two-step graph-based combination strategy, the Jaccard value of the overall lesion segmentation method reached 80.04%, which is 3.54% higher than the winner of the ISBI 2017 lesion segmentation challenge. ConclusionsThe proposed Retina-Deeplab segmentation method reached about 1% of the Jaccard value higher than the Mask R-CNN. Our overall segmentation method considered both overall characteristics of lesions in all images (by using CNN-based methods in the first stage) and image-specific features of lesions (by using geodesic-based/graph-based combination approaches in the second stage). The proposed two-step geodesic-based and graph-based combination approaches performed better than earlier combination strategies. Experiments demonstrated that the overall proposed lesion segmentation methods outperformed other state-of-the-art methods on well-known datasets.