Metasample-Based Sparse Representation for Tumor Classification

Authors:
Chun-Hou Zheng;Lei Zhang;To-Yee Ng;Chi Keung Shiu;De-Shuang Huang
Affiliations:
Qufu Normal University, Rizhao and The Hong Kong Polytechnic University, Hong Kong;The Hong Kong Polytechnic University, Hong Kong;The Hong Kong Polytechnic University, Hong Kong;The Hong Kong Polytechnic University, Hong Kong;Tongi University, Shanghai
Venue:
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Year:
2011

Citing 0
Cited 5

Classification approach based on non-negative least squares

Neurocomputing
A novel ensemble algorithm for tumor classification

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part II
Low-resolution image restoration using the combination method of sparse representation and PDE model

ICIC'13 Proceedings of the 9th international conference on Intelligent Computing Theories
Eigenface-based sparse representation for face recognition

ICIC'13 Proceedings of the 9th international conference on Intelligent Computing Theories and Technology
Unsupervised images segmentation via incremental dictionary learning based sparse representation

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

A reliable and accurate identification of the type of tumors is crucial to the proper treatment of cancers. In recent years, it has been shown that sparse representation (SR) by l_1-norm minimization is robust to noise, outliers and even incomplete measurements, and SR has been successfully used for classification. This paper presents a new SR-based method for tumor classification using gene expression data. A set of metasamples are extracted from the training samples, and then an input testing sample is represented as the linear combination of these metasamples by l_1-regularized least square method. Classification is achieved by using a discriminating function defined on the representation coefficients. Since l_1-norm minimization leads to a sparse solution, the proposed method is called metasample-based SR classification (MSRC). Extensive experiments on publicly available gene expression data sets show that MSRC is efficient for tumor classification, achieving higher accuracy than many existing representative schemes.