Multiclass primal Support Vector Machines for breast density classification. (3rd August 2009)

• Record Type: Journal Article
• Authors: Land Jr., Walker H.; Verheggen, Elizabeth A.
• Is Part Of: International journal of computational biology and drug design. Volume 2:Number 1(2009)
• Page Start: 21
• Page End: 57
• Publication Date: 2009-08-03
• Subjects: parenchyma -- breast density -- correlation pattern recognition -- primal SVM -- support vector machines -- OVA -- one-versus-all -- AVA -- all-versus-all -- lacunarity -- CADe -- computer-aided detection -- computer-aided diagnosis -- breast tissue -- fractal signatures -- texture modelling -- epidemiological risk models -- breast cancer; Computational biology -- Periodicals; Drugs -- Design -- Periodicals; 570.285
• Languages: English
• ISSNs: 1756-0756

Abstract

Parenchymal patterns defining the density of breast tissue are detected by advanced correlation pattern recognition in an integrated Computer-Aided Detection (CAD) and diagnosis system. Fractal signatures of density are modelled according to four clinical categories. A Support Vector Machine (SVM) in the primal formulation solves the multiclass problem using 'One-Versus-All' (OVA) and 'All-Versus-All' (AVA) decompositions, achieving 85% and 94% accuracy, respectively. Fully automated classification of breast density via a texture model derived from fractal dimension, dispersion, and lacunarity moves current qualitative methods forward to objective quantitative measures, amenable with the overarching vision of substantiating the role of density in epidemiological risk models of breast cancer.