Validation of image analysis techniques to measure skin aging features from facial photographs

Abstract

Background: Accurate measurement of the extent skin has aged is crucial for skin aging research. Image analysis offers a quick and consistent approach for quantifying skin aging features from photographs, but is prone to technical bias and requires proper validation.

Methods: Facial photographs of 75 male and 75 female North-European participants, randomly selected from the Rotterdam Study, were graded by two physicians using photonumeric scales for wrinkles (full face, forehead, crow's feet, nasolabial fold and upper lip), pigmented spots and telangiectasia. Image analysis measurements of the same features were optimized using photonumeric grades from 50 participants, then compared to photonumeric grading in the 100 remaining participants stratified by sex.

Results: The inter-rater reliability of the photonumeric grades was good to excellent (intraclass correlation coefficients 0.65-0.93). Correlations between the digital measures and the photonumeric grading were moderate to excellent for all the wrinkle comparisons (Spearman's rho ρ = 0.52-0.89) bar the upper lip wrinkles in the men (fair, ρ = 0.30). Correlations were moderate to good for pigmented spots and telangiectasia (ρ = 0.60-0.75).

Conclusion: These comparisons demonstrate that all the image analysis measures, bar the upper lip measure in the men, are suitable for use in skin aging research and highlight areas of improvement for future refinements of the techniques.

Keywords: Digital; Grading scale; Photonumeric; Pigmented spots; Skin aging; Telangiectasia; Wrinkles.