Area assessment of psoriasis lesions for PASI scoring

Abstract

Psoriasis is a skin disorder which is caused by a genetic fault. Although there is no cure for psoriasis, there are many treatment modalities to help control the disease. To evaluate treatment efficacy, the current gold standard method, PASI (Psoriasis Area and Severity Index), is used to measure psoriasis severity by evaluating the area, erythema, scaliness and thickness of the plaques. However, the determination of PASI can be tedious and subjective. In this work, we develop a computer vision method that determines one of the PASI parameters, the lesion area. The method isolates healthy and healed skin areas from lesion areas by analysing the hue and chroma information in the CIE L*a*b* colour space. Centroids of healthy skin and psoriasis in the hue-chroma space are determined from selected sample. The Euclidean distance of all pixels from each centroid is calculated. Pixels are assigned to either healthy skin or psorasis lesion classes based on the minimum Euclidean distance. The study involves patients from different ethnic origins having three different skin tones. Results obtained show that the proposed method is able to determine lesion areas with accuracy higher than 90% for 28 out of 30 cases.

Serum Squamous Cell Carcinoma Antigen in Psoriasis: A Potential Quantitative Biomarker for Disease Severity

“…Objective and quantitative evaluation of psoriasis severity is important but still lacking practice and research in the care of psoriasis. The evaluation of psoriasis is usually carried out by the estimation of the psoriasis area severity index (PASI) [2], a method which is subjective, not truly quantitative, and varies among clinicians.…”

First review on psoriasis severity risk stratification: An engineering perspective

“…On medication around 75% reduction in PASI score considered as a good improvement [19]. Table 1 shows description of stratification for erythema, scaliness and thickness and Table 2 shows the psoriatic lesion area scoring system based on the psoriatic lesion area in percentage [19,31]. The examples for stratification of erythema, scaliness and thickness are shown in Figs.…”

“…The proposed method works even in the presence of artifacts such as eyes, eyebrows, lips, nipples, hairs and varying illumination conditions. The performance is evaluated by similar approach proposed in [31] and the average accuracy is reported as 98.10%. The drawback of the approach is its small database and preselected blue color background makes the skin segmentation task trivial.…”

“…However, manual segmentation of psoriatic lesion is a time consuming process and may be erroneous due to monotony. Another approach which is based on analyzing the hue and chroma information in the CIE Lnanbn color space is presented in [31]. Ln, an and bn components of CIE Lnanbn color space represent lightness, degree of redness to greenness and degree of yellowness to blueness, respectively.…”

“…It consists of two steps: (i) segmentation of region of interest (ROI) which is entire skin region including psoriatic lesions, and (ii) segmentation of psoriatic lesion. Then, the percentage of psoriatic lesion area is calculated by taking the ratio of the area of psoriatic lesion to area of ROI [31].…”