GP-CNN-DTEL: Global-Part CNN Model With Data-Transformed Ensemble Learning for Skin Lesion Classification

• Published in: IEEE journal of biomedical and health informatics Vol. 24; no. 10; pp. 2870 - 2882
• Main Authors: Tang, Peng, Liang, Qiaokang, Yan, Xintong, Xiang, Shao, Zhang, Dan
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Classification; color constancy guided ensemble learning; Convolutional neural networks; Data mining; Datasets; Deep Learning; Dermoscopy - methods; dermoscopy images; Ensemble learning; global-part model; Humans; Image classification; Image color analysis; Image Interpretation, Computer-Assisted - methods; Image processing; Information processing; Lesions; Melanoma; Microscopy; Neural networks; Neural Networks, Computer; Skin; Skin diseases; Skin Diseases - diagnostic imaging; Skin lesion classification; Skin lesions; Training
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2020.2977013

Precise skin lesion classification is still challenging due to two problems, i.e., (1) inter-class similarity and intra-class variation of skin lesion images, and (2) the weak generalization ability of single Deep Convolutional Neural Network trained with limited data. Therefore, we propose a Global-Part Convolutional Neural Network (GP-CNN) model, which treats the fine-grained local information and global context information with equal importance. The Global-Part model consists of a Global Convolutional Neural Network (G-CNN) and a Part Convolutional Neural Network (P-CNN). Specifically, the G-CNN is trained with downscaled dermoscopy images, and is used to extract the global-scale information of dermoscopy images and produce the Classification Activation Map (CAM). While the P-CNN is trained with the CAM guided cropped image patches and is used to capture local-scale information of skin lesion regions. Additionally, we present a data-transformed ensemble learning strategy, which can further boost the classification performance by integrating the different discriminant information from GP-CNNs that are trained with original images, color constancy transformed images, and feature saliency transformed images, respectively. The proposed method is evaluated on the ISIC 2016 and ISIC 2017 Skin Lesion Challenge (SLC) classification datasets. Experimental results indicate that the proposed method can achieve the state-of-the-art skin lesion classification performance (i.e., an AP value of 0.718 on the ISIC 2016 SLC dataset and an Average Auc value of 0.926 on the ISIC 2017 SLC dataset) without any external data, compared with other current methods which need to use external data.