Automated and accurate segmentation of skin lesions based on dermoscopic images is an important task in clinical practice. However, limited labeled images and noisy annotations make the skin lesion segmentation task challenging. In this work, we propose a superpixel inpainting based self-supervised pretraining method to enhance skin lesion segmentation, the effectiveness of which is identified both quantitatively and qualitatively on two public datasets. State-of-the-art performance on skin lesion segmentation is observed, with mean Jaccard indices of 76.5% and 84.3% being obtained respectively on the ISIC2017 and PH2 datasets.
Paper
Full text
Superpixel Inpainting For Self-Supervised Skin Lesion Segmentation from Dermoscopic Images
Semantic Scholar · Medicine · 2022
Abstract
Automated and accurate segmentation of skin lesions based on dermoscopic images is an important task in clinical practice. However, limited labeled images and noisy annotations make the skin lesion segmentation task challenging. In this work, we propose a superpixel inpainting based self-supervised pretraining method to enhance skin lesion segmentation, the effectiveness of which is identified both quantitatively and qualitatively on two public datasets. State-of-the-art performance on skin lesion segmentation is observed, with mean Jaccard indices of 76.5% and 84.3% being obtained respectively on the ISIC2017 and PH2 datasets.