Computer-Aided Diagnosis Psoriasis Lesion Using Skin Color and Texture Features

Abstract

Psoriasis form out to be one of the weakening and persisting incendiary skin lesions. Frequently confused as a casual skin thickness, it is evaluated that around 125 million individuals overall endures because of this disease. The case is exacerbated when there is no known cure in the status norm. The common classification of psoriasis has been considered as unexpectedly separated scaly and erythematous plaque at patient's skin. This lesion could follow anyplace on the human body. Objectives: Diagnosis of psoriasis requires an experienced specialist in the field of dermatology which lead to majority cases of an error in diagnosis, incorrect disease identification is highly possible and there is no consensus on the current subjective assessment methods due to the unavoidable inter and intra- observer variances. The purpose of this study is to establish a diagnosis system of psoriasis lesion to ease the role of the physician in diagnosis by providing better and more reliable results, to support the expert's decision to diagnose the lesion, especially doctors with little experience. Methods: In this paper, the researcher is interested in the diagnosis psoriasis lesion by using color and texture features by finding the new sign (color and texture features) implementation to support the expert decision. Aggregate 200 image samples of psoriasis patients are used in our database. Machine learning using Artificial Neural Network classifier ANN to obtain optimized performance. Result: CADP system shows optimal performance of 100% accuracy, 100% sensitivity and 100% specificity for color-texture feature with RGB-Local Binary Pattern method and performance of 100% accuracy, 100% sensitivity and 100% specificity with the RGB Color Co-occurrence Matrix method. Conclusions: CAD system became a tool for physicians and therefore it is important to have accurate and reliable CAD system. The LBP and CCM texture features are powerful in psoriasis disease classification for RGB color images.