Stacked Autoencoder for classification of glioma grade III and grade IV. (September 2018)

• Record Type: Journal Article
• Authors: Patil, Supriya; Naik, Gourish; Pai, Radhakrishna; Gad, Rajendra
• Is Part Of: Biomedical signal processing and control. Volume 46(2018)
• Page Start: 67
• Page End: 75
• Publication Date: 2018-09
• Subjects: Resilient Back Propagation algorithm -- Conjugate Gradient Back Propagation with Fletcher–Reeves Update algorithm -- Conjugate Gradient Back Propagation with Polak–Ribire Update -- Conjugate Gradient Back Propagation with Powell–Beale Restarts algorithm -- Levenberg Marquardt algorithm -- Stacked Autoencoder algorithm; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2018.07.002
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Highlights: Fusion of Thresholding and Ratio method selects the subset of genes with less ratio within the chosen threshold range. Thresholding gives the alternate subset of genes to confirmation of result of classification. Stacked Autoencoder algorithm gives best possible compromise between number of genes and accuracy. 100% classification accuracy obtained using five common genes across four glioma datasets (GDS1975, GDS1976, GDS1815 and GDS1816). Abstract: Invention of the microarray technology has rendered it possible to inspect the whole genome at once in cancer classification. However, in order to curtail the computational complexity and augment the accuracy of cancer classification, it is essential to sift the vast microarray data for the informative genes. In this paper, Thresholding and Ratio methods are presented, individually as well as conjointly (hybrid method) to choose optimal gene subset from the microarray data. Moreover, Discrete Wavelet Transform (DWT) is deployed to pare the size of microarray data still further. The classification is accomplished by using various neural network algorithms and Stacked Autoencoder algorithm. The results of classification are compared for number of thresholds, ratios, wavelets and classification algorithms. It is observed that the Stacked Autoencoder network trained by Back Propagation algorithm delivers the best results in terms of classification accuracy and number of genes.