Quantitative assessment of female pattern hair loss

Abstract

Background/Objective: The conventional approach to evaluate female pattern hair loss (FPHL) is to visually inspect and score images of balding area (BA). However, visual estimates vary widely among different physicians, and may hinder objective assessment of hair loss and subsequent treatment response. For this reason, we propose a quantitative method using a computer-aided imaging system to help physicians evaluate the severity of FPHL clinically. Methods: We use a series of digital image processing techniques to measure the width of central balding area of FPHL. A total of 184 photos were collected form 33 Chinese women with FPHL (stages I-2 to II-2 on the Savin scale). Each photograph underwent standardized exposure correction. The balding areas were detected through this computer system and then transformed into an equivalent ellipse by principal component analysis. The width of ellipse [balding width (BW)] was measured. Spearman's rank correlation was used to detect the correlation between our measurements and clinical staging. Results: Exposure correction resulted in a 16.97% (|BWcorrected − BWoriginal|/BWcorrected) difference in BW.‏ The average BW was 54.98 mm in all patients, 25.79 mm in type I-2 patients, 37.41 mm in I-3, 54.08 mm in I-4, 72.10 mm in II-1, and 85.53 mm in II-2. The values of BW were correlated with Savin scale stages clinically (rBW = 0.967), which was significant statistically (p < 0.05). Conclusion: A computer-aided imaging system could be a useful tool to assist physicians to evaluate the balding area more precisely for clinical staging in FPHL. The BW instead of the balding area is simple to use clinically to represent the severity of FPHL.

Keywords

• balding width
• female pattern hair loss
• quantitative analysis