期刊
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
卷 27, 期 1, 页码 12-22出版社
WILEY
DOI: 10.1002/ima.22206
关键词
lung nodule classification; multiview convolutional neural networks; benign; primary malignant; metastatic malignant
资金
- National Science and Technology Major Project of China [2013ZX03006001]
- National High Technology Research and Development Program of China (863 Program) [2015AA01A709]
- National Natural Science Foundation of China [61471064, 61501056]
To find a better way to screen early lung cancer, motivated by the great success of deep learning, we empirically investigate the challenge of classifying lung nodules in computed tomography (CT) in an end-to-end manner. Multi-view convolutional neural networks (MV-CNN) are proposed in this article for lung nodule classification. Unlike the traditional CNNs, a MV-CNN takes multiple views of each entered nodule. We carry out a binary classification (benign and malignant) and a ternary classification (benign, primary malignant, and metastatic malignant) using the Lung Image Database Consortium and Image Database Resource Initiative database. The results show that, for binary or ternary classifications, the multiview strategy produces higher accuracy than the single view method, even for cases that are over-fitted. Our model achieves an error rate of 5.41 and 13.91% for binary and ternary classifications, respectively. Finally, the receiver operating characteristic curve and t-distributed stochastic neighbor embedding algorithm are used to analyze the models. The results reveal that the deep features learned by the model proposed in this article have a higher separability than features from the image space and the multiview strategies; therefore, researchers can get better representation. (C) 2017 Wiley Periodicals, Inc.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据