SkinNet: A Deep Learning Framework for Skin Lesion Segmentation
This work addresses the need for accurate automatic segmentation of skin lesions to improve early diagnosis and treatment for patients with skin cancer, but it is incremental as it builds on the existing U-Net architecture.
The paper tackled the problem of skin lesion segmentation for early cancer detection by proposing SkinNet, a modified U-Net CNN, which outperformed state-of-the-art methods on the ISBI 2017 dataset with average Dice coefficient, Jaccard index, and sensitivity scores of 85.10, 76.67, and 93.0%, respectively.
There has been a steady increase in the incidence of skin cancer worldwide, with a high rate of mortality. Early detection and segmentation of skin lesions are crucial for timely diagnosis and treatment, necessary to improve the survival rate of patients. However, skin lesion segmentation is a challenging task due to the low contrast of lesions and their high similarity in terms of appearance, to healthy tissue. This underlines the need for an accurate and automatic approach for skin lesion segmentation. To tackle this issue, we propose a convolutional neural network (CNN) called SkinNet. The proposed CNN is a modified version of U-Net. We compared the performance of our approach with other state-of-the-art techniques, using the ISBI 2017 challenge dataset. Our approach outperformed the others in terms of the Dice coefficient, Jaccard index and sensitivity, evaluated on the held-out challenge test data set, across 5-fold cross validation experiments. SkinNet achieved an average value of 85.10, 76.67 and 93.0%, for the DC, JI, and SE, respectively.