Estimation error of the body surface area in psoriasis: a comparative study of physician and computer‐assisted image analysis (ImageJ)

Abstract

Background. Assessing the area involved in a skin disease, i.e. the body surface area (BSA), is essential in diagnosing disease severity, including in psoriasis. However, in psoriasis, BSA tends to be overestimated by physicians and has shown high inter-rater and intrarater variability. Furthermore, there are no reports suggesting the cause and clinical significance of overestimating BSA in psoriasiss. Aim. To investigate the errors in estimating BSA in psoriasis by comparing physicians' results with those of computer-assisted image analysis (CAIA) and to provide suggestions regarding the clinical implications of such errors. Methods. Using 43 images, 36 physicians visually estimated BSA in psoriasis, and subsequently, the images were evaluated using a CAIA program (ImageJ); the BSA values determined by the physicians and CAIA were then compared and matched. The BSA percentage was also graded on a scale from 0 to 6, as follows: Grade 0 = no lesion, Grade 1 = 1%-9%, Grade 2 = 10%-29%, Grade 3 = 30%-49%, Grade 4 = 50%-69%, Grade 5 = 70%-89% and Grade 6 = 90%-100%. Each grade range was divided, with the bottom and top 50% defined as the 'first half' and 'second half,' respectively. Results. The mean proportion of correct assessments by physicians was 49.4%. Physicians tended to overestimate the BSA of psoriatic lesions by 8.76% AE 8.82% compared with CAIA. The largest estimation error (proportion incorrect 75.7%) was observed in Grade 3 (30%-49% involvement). Estimates in the second half of the range demonstrated a higher proportion of inaccuracies compared with those in the first half. An overestimating error occurred in certain morphological characteristics of the psoriatic lesions. Conclusions. The inaccuracy of BSA estimation by physicians may be related to the fact that information from the human eye is perceived to be exaggerated compared with the actual size. Further research into using artificial intelligence technology is needed to reduce quantification error and develop an ideal BSA assessment system. Additionally, education and training are needed for physicians to measure BSA accurately.

The study on surface morphology and decorative properties of Magnesium-glass-board (MGB)

“…The analysis of the structural composition of both showed that the depth of surface pores was shallow, therefore only the surface porosity of both sides of the MGB was analyzed here. Five randomly positioned images from each side were taken for analysis, using ‘Image J’ software and machine vision learning to implement this process [ 21 , 22 ].…”

Study of aerosol dispersion and control in dental practice

“…The fluorescein aqueous solution, with a 50g/ml concentration, exhibited significant fluorescence at 480-600 nm and could be visualized through fluorescence microscopy using an excitation wavelength of 480 nm. The background of the filter paper was black-balanced using Olympus cell-Sens Standard microscope image processing software [29], and subsequent photographs of the images were taken. The particle size of fluorescein droplets was classified based on the microscope's magnification and imaging scale.…”