A multi-kernel based framework for heterogeneous feature selection and over-sampling for computer-aided detection of pulmonary nodules

详细信息    查看全文

• 作者：Peng Cao^a ; ^b ; ^{caopeng@cse.neu.edu.cn}Author Vitae ; Xiaoli Liu^a ; ^bAuthor Vitae ; Jinzhu Yang^aAuthor Vitae ; Dazhe Zhao^a ; ^bAuthor Vitae ; Wei Li^bAuthor Vitae ; Min Huang^c ; ^dAuthor Vitae ; Osmar Zaiane^eAuthor Vitae
• 关键词：Lung nodule detection ; False positive reduction ; Classification ; Imbalanced data learning ; Multi-kernel learning ; Feature selection
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：April 2017
• 年：2017
• 卷：64
• 期：Complete
• 页码：327-346
• 全文大小：2570 K
• 卷排序：64

文摘

Proposed a unified multiple kernel framework to classify potential nodule objects. Regularized multiple kernel with l2,1l2,1 norm to fuse the heterogeneous feature subsets. Two different feature selection from heterogeneous feature subsets. Over-sampling positive instances in kernel space for imbalanced data.