Exploring the color feature power for psoriasis risk stratification and classification: A data mining paradigm

• Published in: Computers in biology and medicine Vol. 65; pp. 54 - 68
• Main Authors: Shrivastava, Vimal K, Londhe, Narendra D, Sonawane, Rajendra S, Suri, Jasjit S
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01-10-2015; Elsevier Limited
• Subjects: Accuracy; Classification; Color; Color space; Data mining; Data Mining - methods; Databases, Factual; Dermatology; Disease; Feature power; Female; Humans; Image Processing, Computer-Assisted - methods; Internal Medicine; Male; Melanoma; Other; PCA; Power; Psoriasis; Psoriasis - classification; Psoriasis - pathology; Reliability; Researchers; Skin diseases; Skin Pigmentation; Standard deviation; Studies; Psoriasis; Reliability; Color space; Classification; PCA; Feature power
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2015.07.021

Abstract A large percentage of dermatologist׳s decision in psoriasis disease assessment is based on color. The current computer-aided diagnosis systems for psoriasis risk stratification and classification lack the vigor of color paradigm. The paper presents an automated psoriasis computer-aided diagnosis (pCAD) system for classification of psoriasis skin images into psoriatic lesion and healthy skin, which solves the two major challenges: (i) fulfills the color feature requirements and (ii) selects the powerful dominant color features while retaining high classification accuracy. Fourteen color spaces are discovered for psoriasis disease analysis leading to 86 color features. The pCAD system is implemented in a support vector-based machine learning framework where the offline image data set is used for computing machine learning offline color machine learning parameters. These are then used for transformation of the online color features to predict the class labels for healthy vs. diseased cases. The above paradigm uses principal component analysis for color feature selection of dominant features, keeping the original color feature unaltered. Using the cross-validation protocol, the above machine learning protocol is compared against the standalone grayscale features with 60 features and against the combined grayscale and color feature set of 146. Using a fixed data size of 540 images with equal number of healthy and diseased, 10 fold cross-validation protocol, and SVM of polynomial kernel of type two, pCAD system shows an accuracy of 99.94% with sensitivity and specificity of 99.93% and 99.96%. Using a varying data size protocol, the mean classification accuracies for color, grayscale, and combined scenarios are: 92.85%, 93.83% and 93.99%, respectively. The reliability of the system in these three scenarios are: 94.42%, 97.39% and 96.00%, respectively. We conclude that pCAD system using color space alone is compatible to grayscale space or combined color and grayscale spaces. We validated our pCAD system against facial color databases and the results are consistent in accuracy and reliability.