PubMed RSS Feed - - Characteristics of subjective recognition and computer-aided image analysis of facial erythematous skin diseases: A cornerstone of

[rss]

Characteristics of subjective recognition and computer-aided image analysis of facial erythematous skin diseases: A cornerstone of automated diagnosis.

Br J Dermatol. 2013 Dec 6;

Authors: Choi JW, Kim BR, Lee HS, Youn SW

Abstract
BACKGROUND: Rosacea and seborrheic dermatitis are common diseases that cause facial erythema. They share common features and are frequently misdiagnosed.
OBJECTIVE: To extract characteristic features of rosacea and seborrheic dermatitis through computer-aided image analysis (CAIA) and compare them with subjectively recognized features. Using these findings, we aimed for constructing a decision tree for differential diagnosis.
METHODS: In total, 34 clinical photos of facial erythema were included: 12 were diagnosed as erythrotelangiectatic rosacea (ETR), 12 as papulopustular rosacea (PPR), and 10 as seborrheic dermatitis (SEB). Five blinded dermatologists provided their impressions of each photo. The mean, standard deviation, and T-zone to U-zone (T/U) ratios of the erythema parameter a* (a* of the L*a*b* color space) were calculated for each photo using CAIA. These CAIA parameters were compared between impression groups. The most closely related CAIA parameter for each disease was established using the receiver operating characteristic (ROC) curve analysis. A decision tree which predicts the diagnosis from given CAIA parameters was constructed.
RESULTS: All PPR diagnosed photos generated impressions of PPR. However, approximately 30% of the ETR diagnosed photos generated misimpressions of SEB and vice versa. PPR was characterized by a large standard deviation of erythema of the cheek, ETR was characterized by a large mean erythema of the U-zone, and SEB was characterized by a large T/U ratio of mean erythema. Among the additional fifteen cases, the decision tree predicted the original diagnosis in fourteen cases, but mis-predicted as SEB in one case of ETR.
CONCLUSIONS: The CAIA result of facial erythema is well correlated with the actual clinical diagnosis. The accuracy of differential diagnosis using decision tree with CAIA parameters is as good as that of global examination impressions of dermatologists. This article is protected by copyright. All rights reserved.

PMID: 24354615 [PubMed - as supplied by publisher]

http://www.ncbi.nlm.nih.gov/pubmed/24354615?dopt=Abstract = URL to article