Article: A computerised framework for prediction of fatty and dense breast tissue using principal component analysis and multi-resolution texture descriptors Journal: International Journal of Computational Systems Engineering (IJCSYSE) 2018 Vol.4 No.2/3 pp.73 - 85 Abstract: The present work proposes a computerised framework for prediction of fatty and dense breast tissue using principal component analysis and multi-resolution texture descriptors. For this study, 480 MLO view digitised screen film mammograms have been taken from the DDSM dataset. A fixed ROIs size of 128 × 128 pixels are cropped from the centre location of each mammographic image. Three texture features are computed in multi-resolution transform domain, where each ROI is decomposed up to 2nd level using ten different compact support wavelet filters resulting 16 sub-band feature images. Two step feature optimisation approach (feature pruning followed by feature space dimensionality reduction using PCA) is applied. In feature pruning stage, the TFV corresponding to best basis feature is selected; result of feature pruning stage is PTFV. This PTFV is subjected to PCA for feature space dimensionality reductions. After the application, PCA accuracy increases from 92.1% to 97.9%. Inderscience Publishers - linking academia, business and industry through research

Title: A computerised framework for prediction of fatty and dense breast tissue using principal component analysis and multi-resolution texture descriptors

Authors: Indrajeet Kumar; H.S. Bhadauria; Jitendra Virmani

Addresses: Department of Computer Science and Engineering, GB Pant Engineering College, Pauri Garhwal, Uttarakhand, 246194, India ' Department of Computer Science and Engineering, GB Pant Engineering College, Pauri Garhwal, Uttarakhand, 246194, India ' Council of Scientific and Industrial Research, Central Scientific Instruments Organization (CSIR-CSIO), Ministry of Science and Technology, Govt of India, Sector 30-C, Chandigarh-160030, India

Abstract: The present work proposes a computerised framework for prediction of fatty and dense breast tissue using principal component analysis and multi-resolution texture descriptors. For this study, 480 MLO view digitised screen film mammograms have been taken from the DDSM dataset. A fixed ROIs size of 128 × 128 pixels are cropped from the centre location of each mammographic image. Three texture features are computed in multi-resolution transform domain, where each ROI is decomposed up to 2nd level using ten different compact support wavelet filters resulting 16 sub-band feature images. Two step feature optimisation approach (feature pruning followed by feature space dimensionality reduction using PCA) is applied. In feature pruning stage, the TFV corresponding to best basis feature is selected; result of feature pruning stage is PTFV. This PTFV is subjected to PCA for feature space dimensionality reductions. After the application, PCA accuracy increases from 92.1% to 97.9%.

Keywords: mammography; breast density classification; multi-resolution texture descriptors; principal component analysis; PCA; support vector machine classifier; SVM.

DOI: 10.1504/IJCSYSE.2018.091386

International Journal of Computational Systems Engineering, 2018 Vol.4 No.2/3, pp.73 - 85

Received: 12 Oct 2016
Accepted: 29 Mar 2017
Published online: 30 Apr 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A computerised framework for prediction of fatty and dense breast tissue using principal component analysis and multi-resolution texture descriptors

Keep up-to-date