SkinNet: A Deep Learning Framework for Skin Lesion Segmentation

TL;DR

SkinNet is a modified U-Net CNN that significantly improves automatic skin lesion segmentation accuracy, aiding early skin cancer detection through superior performance metrics on a standard dataset.

Contribution

The paper introduces SkinNet, a novel CNN architecture based on U-Net, tailored for skin lesion segmentation, demonstrating improved accuracy over existing methods.

Findings

Outperformed state-of-the-art techniques in Dice coefficient, Jaccard index, and sensitivity.

Achieved average values of 85.10% (DC), 76.67% (JI), and 93.0% (SE).

Validated effectiveness through 5-fold cross-validation on ISBI 2017 dataset.

Abstract

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.