Home > Published Issues > 2021 > Volume 12, No. 2, May 2021 >

Squeeze-and-Excitation Convolutional Neural Network for Classification of Malignant and Benign Lung Nodules

Ying Chen 1, Weiwei Du 2, Xiaojie Duan 1, Yanhe Ma 3, and Hong Zhang 3
1. School of Electronics and Information Engineering, Tiangong University, Tianjin, China
2. Department of Information and Human Science, Kyoto Institute of Technology, Kyoto, Japan
3. Tianjin Chest Hospita, Tianjin, China

Abstract—Lung cancer is the world’s highest morbidity and mortality cancer, which seriously threatens the life and health of the public. Early detection and diagnosis of lung nodules is an important prerequisite for lung cancer prevention and diagnosis. This paper designs a new structure which is a Squeeze-and-Excitation Convolutional Neural Network. Experimental results show that SE-CNN can recognize the benign and malignant lung nodules. SE-CNN is more effective than CNN for classification of benign and malignant lung nodules.
Index Terms—squeeze-and-excitation convolutional network, classify, lung nodules, the LIDC-IDRI database

Cite: Ying Chen, Weiwei Du, Xiaojie Duan, Yanhe Ma, and Hong Zhang, "Squeeze-and-Excitation Convolutional Neural Network for Classification of Malignant and Benign Lung Nodules," Journal of Advances in Information Technology, Vol. 12, No. 2, pp. 153-158, May 2021. doi: 10.12720/jait.12.2.153-158

Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.