An integrated inverse space sparse representation framework for tumor classification

作者：

Highlights：

• An integrated inverse space sparse representation model is proposed for gene-based tumor classification.

• A gene selection method is proposed to improve the model's representation ability to small sample problem.

• A feature representation learning method is proposed to enhance the model's representation ability and stability.

• The model is optimized and the convergence is analyzed.

• Extensive experiments are conducted on six microarray gene expression datasets, which contain early diagnosis, tumor type recognition and postoperative metastasis.

摘要

•An integrated inverse space sparse representation model is proposed for gene-based tumor classification.•A gene selection method is proposed to improve the model's representation ability to small sample problem.•A feature representation learning method is proposed to enhance the model's representation ability and stability.•The model is optimized and the convergence is analyzed.•Extensive experiments are conducted on six microarray gene expression datasets, which contain early diagnosis, tumor type recognition and postoperative metastasis.

论文关键词：Tumor classification,Microarray gene expression data,Decision information genes,Layer-wise pre-training sparse NMF,Inverse space sparse representation

论文评审过程：Received 18 May 2018, Revised 2 March 2019, Accepted 13 April 2019, Available online 15 April 2019, Version of Record 3 May 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.04.013