Open AccessAn Attention-based Convolutional Neural Network for Melanoma Recognition
Author(s) -
Qi Chen,
Lidan Wang,
Xiuling Gan,
Shukai Duan
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1861/1/012071
Subject(s) - discriminative model , artificial intelligence , computer science , convolutional neural network , pattern recognition (psychology) , focus (optics) , uncorrelated , melanoma , deep learning , task (project management) , medicine , mathematics , statistics , physics , management , cancer research , optics , economics
Early automatic and accurate melanoma recognition is an important method to reduce melanoma deaths. Existing methods are less sensitive to the position of the lesion areas. Network training may be affected by the uncorrelated noisy parts. In light of this circumstance, an end-to-end attention-based network AF-CNN for accurate melanoma recognition is proposed in this paper, which is mainly composed of pre-trained VGG19, attention blocks and a classification layer. Instead of treating each part of the input dermoscopy images equally, our AF-CNN model has strong discriminative ability to focus on the lesion areas. The AF-CNN was evaluated on the ISIC2017 dataset and concluded the proposed single model achieves the state-of-the-art result in melanoma recognition task.