A novel approach to multiclass psoriasis disease risk stratification: Machine learning paradigm. (July 2016)

• Record Type: Journal Article
• Authors: Shrivastava, Vimal K.; Londhe, Narendra D.; Sonawane, Rajendra S.; Suri, Jasjit S.
• Is Part Of: Biomedical signal processing and control. Volume 28(2016)
• Page Start: 27
• Page End: 40
• Publication Date: 2016-07
• Subjects: Dermatology -- Psoriasis skin disease -- Color features -- Texture features -- Machine learning -- Multiclass; 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.2016.04.001
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Multiclass risk assessment and stratification system for psoriasis disease. Comparison of four kinds of systems: SVM-PCA, SVM-FDR, DT-PCA and DT-FDR. Comprehensive feature space of 859 features. Performance evaluation using feature retaining power and aggregate feature effect. Classification accuracy of 99.92% and system reliability of 99.73%. Abstract: The stage and grade of psoriasis severity is clinically relevant and important for dermatologists as it aids them lead to a reliable and an accurate decision making process for better therapy. This paper proposes a novel psoriasis risk assessment system (pRAS) for stratification of psoriasis severity from colored psoriasis skin images having Asian Indian ethnicity. Machine learning paradigm is adapted for risk stratification of psoriasis disease grades utilizing offline training and online testing images. We design four kinds of pRAS systems. It uses two kinds of classifiers (support vector machines (SVM) and decision tree (DT)) during training and testing phases and two kinds of feature selection criteria (Principal Component Analysis (PCA) and Fisher Discriminant Ratio (FDR)), thus, leading to an exhaustive comparison between these four systems. Our database consisted of 848 psoriasis images with five severity grades: healthy, mild, moderate, severe and very severe, consisting of 383, 47, 245, 145, and 28 images respectively. The pRAS system computes 859 colored and grayscale image features. Using cross-validation protocol with K -fold procedure, the pRAS system utilizing the SVM with FDR combination with combined color and grayscale feature set gives an accuracy of 99.92%. Several performance evaluation parameters such as: feature retaining power, aggregated feature effect and system reliability is computed meeting our assumptions and hypothesis. Our results demonstrate promising results and pRAS system is able to stratify the psoriasis disease.