Deep attention branch networks for skin lesion classification

Saisai Ding; Zhongyi Wu; Yanyan Zheng; Zhaobang Liu; Xiaodong Yang; Xiaokai Yang; Gang Yuan; Jing Xie

doi:10.1016/j.cmpb.2021.106447

Deep attention branch networks for skin lesion classification

Comput Methods Programs Biomed. 2021 Nov:212:106447. doi: 10.1016/j.cmpb.2021.106447. Epub 2021 Oct 2.

Authors

Saisai Ding¹, Zhongyi Wu², Yanyan Zheng³, Zhaobang Liu², Xiaodong Yang², Xiaokai Yang³, Gang Yuan⁴, Jing Xie⁵

Affiliations

¹ School of Communication and Information Engineering, Shanghai University, Shanghai, 200444, China.
² School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230026, China; Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China.
³ The Wenzhou Third Clinical Institute Affiliated To Wenzhou Medical University, Wenzhou, 325000, China; Wenzhou People's Hospital, Wenzhou, 325000, China.
⁴ School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, 230026, China; Department of Medical Imaging, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China. Electronic address: yuangang@sibet.ac.cn.
⁵ The Wenzhou Third Clinical Institute Affiliated To Wenzhou Medical University, Wenzhou, 325000, China; Wenzhou People's Hospital, Wenzhou, 325000, China. Electronic address: christian_xj@163.com.

PMID: 34678529
DOI: 10.1016/j.cmpb.2021.106447

Abstract

Background and objective: The skin lesion usually covers a small region of the dermoscopy image, and the lesions of different categories might own high similarities. Therefore, it is essential to design an elaborate network for accurate skin lesion classification, which can focus on semantically meaningful lesion parts. Although the Class Activation Mapping (CAM) shows good localization capability of highlighting the discriminative parts, it cannot be obtained in the forward propagation process.

Methods: We propose a Deep Attention Branch Network (DABN) model, which introduces the attention branches to expand the conventional Deep Convolutional Neural Networks (DCNN). The attention branch is designed to obtain the CAM in the training stage, which is then utilized as an attention map to make the network focus on discriminative parts of skin lesions. DABN is applicable to multiple DCNN structures and can be trained in an end-to-end manner. Moreover, a novel Entropy-guided Loss Weighting (ELW) strategy is designed to counter class imbalance influence in the skin lesion datasets.

Results: The proposed method achieves an Average Precision (AP) of 0.719 on the ISIC-2016 dataset and an average area under the ROC curve (AUC) of 0.922 on the ISIC-2017 dataset. Compared with other state-of-the-art methods, our method obtains better performance without external data and ensemble learning. Moreover, extensive experiments demonstrate that it can be applied to multi-class classification tasks and improves mean sensitivity by more than 2.6% in different DCNN structures.

Conclusions: The proposed method can adaptively focus on the discriminative regions of dermoscopy images and allows for effective training when facing class imbalance, leading to the performance improvement of skin lesion classification, which could also be applied to other clinical applications.

Keywords: Attention branch; Class activation mapping; Class imbalance; Dermoscopy image; Loss weighting; Skin lesion classification.

MeSH terms

Dermoscopy
Humans
Neural Networks, Computer
Research
Skin Diseases* / diagnostic imaging
Skin Neoplasms*