Development and evaluation of an automatic acne lesion detection program using digital image processing

Abstract

Background/purpose: Existing acne grading methods, which depend on overall impression, require a long training period and there is a high degree of variability among raters, including trained dermatologists. The use of lesion count provides fair reproducibility but the method is time consuming. New technologies in photographic equipment and software allow solutions to the problem of acne evaluation. This study was conducted to develop the automatic acne lesion program and evaluation of its usefulness.

Methods: We made the conditions to optimize characterization of acne lesions and developed the counting program. Twenty-five volunteers with acne lesions were enrolled. Automated lesion counting for five subtypes of acne (papule, nodule, pustule, whitehead comedone, and blackhead comedone) was performed with image processing. The usefulness of the automatic lesion count program was assessed by a comparison with manual counting performed by an expert dermatologist.

Results: In a comparison with manual counting performed by an expert dermatologist, the sensitivity and positive predictive value of the lesion-counting program was greater than 70% for papules, nodules, pustules, and whitehead comedo. In a comparison with manual counting, findings with the use of the lesion-counting program were well correlated for papules, nodules, pustules, and whitehead comedo (r > 0.9).

Conclusion: Automatic lesion-counting program can be a useful tool for acne severity evaluation.