A hierarchical structure based on Stacking approach for skin lesion classification
作者：
Highlights：
• The complete implementation process of an automatic system to diagnose melanoma is presented.
• Complex networks are used for the first time to analyze the lesion boundary.
• A new approach based on Stacking is presented to categorize skin lesions.
• Wrapper and filter based methods are used to remove redundant features.
• The proposed method provides better results compared to other methods proposed in other articles.
摘要
•The complete implementation process of an automatic system to diagnose melanoma is presented.•Complex networks are used for the first time to analyze the lesion boundary.•A new approach based on Stacking is presented to categorize skin lesions.•Wrapper and filter based methods are used to remove redundant features.•The proposed method provides better results compared to other methods proposed in other articles.
论文关键词：Skin cancer,Melanoma,Ensemble classifiers,Meta learning,Stacking
论文评审过程：Received 2 June 2019, Revised 4 November 2019, Accepted 8 December 2019, Available online 10 December 2019, Version of Record 17 December 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.113127
