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

作者：

Highlights：

• Proposed a unified multiple kernel framework to classify potential nodule objects.

• Regularized multiple kernel with l2,1 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.

摘要

Highlights•Proposed a unified multiple kernel framework to classify potential nodule objects.•Regularized multiple kernel with l2,1 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.

论文关键词：Lung nodule detection,False positive reduction,Classification,Imbalanced data learning,Multi-kernel learning,Feature selection

论文评审过程：Received 27 June 2016, Revised 13 October 2016, Accepted 5 November 2016, Available online 14 November 2016, Version of Record 4 December 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.11.007