Pilot study of an automated method to determine Melasma Area and Severity Index

Skin hyperpigmentation index in melasma: A complementary method to classic scoring systems

BACKGROUND

Due to relapsing nature of melasma with significant impact on quality of life, an objective measurement score is warranted, especially to follow-up the patients with melasma and their therapy response in a quantitative and precise manner.

AIMS

To prove concordance of skin hyperpigmentation index (SHI) with well-established scores in melasma and demonstrate its superiority regarding inter-rater reliability. Development of SHI mapping for its integration in common scores.

METHODS

Calculation of SHI and common melasma scores by five dermatologists. Inter-rater reliability was assessed by intraclass correlation coefficient (ICC) and concordance by Kendall correlation coefficient.

RESULTS

Strong concordance of SHI with melasma area and severity index (MASI)-Darkness (0.48; 95% CI: 0.32, 0.63), melasma severity index (MSI)-Pigmentation (0.45; 95% CI: 0.26, 0.61), and melasma severity scale (MSS) (0.6; 95% CI: 0.42, 0.74). Using step function for mapping SHI into pigmentation scores showed an improvement of inter-rater reliability with a difference in (ICC of 0.22 for MASI-Darkness and 0.19 for MSI-Pigmentation), leading to an excellent agreement.

CONCLUSION

Skin hyperpigmentation index could be an important additional cost-and time-conserving assessment method, to follow-up the patients with melasma undergoing brightening therapies in clinical studies, as well as in routine clinical practice. It is in strong concordance with well-established scores but superior regarding inter-rater reliability.

Automated severity scoring of atopic dermatitis patients by a deep neural network

Scoring atopic dermatitis (AD) severity with the Eczema Area and Severity Index (EASI) in an objective and reproducible manner is challenging. Automated measurement of erythema, papulation, excoriation, and lichenification severity using images has not yet been investigated. Our aim was to determine whether convolutional neural networks (CNNs) could assess erythema, papulation, excoriation, and lichenification severity at a level of competence comparable to dermatologists. We created a standard dataset of 8,000 clinical images showing AD. Each component of the EASI was scored from 0 to 3 by three dermatologists. We trained four CNNs (ResNet V1, ResNet V2, GoogLeNet, and VGG-Net) with the image dataset and determined which CNN was the most suitable for erythema, papulation, excoriation, and lichenification scoring. The brightness of the images in each dataset was adjusted to − 80% to + 80% of the original brightness (i.e., 9 levels by 20%) to investigate if the CNNs accurately measured scores if image brightness levels were changed. Compared to the dermatologists’ scoring, accuracy rates of the CNNs were 99.17% for erythema, 93.17% for papulation, 96.00% for excoriation, and 97.17% for lichenification. CNNs trained with brightness-adjusted images achieved a high accuracy without the need to standardize camera settings. These results suggested that CNNs perform at level of competence comparable to dermatologists for scoring erythema, papulation, excoriation, and lichenification severity.

Association between heterozygote Val92Met MC1R gene polymorphisms with incidence of melasma: a study of Javanese women population in Yogyakarta

Introduction: Melasma is an acquired hypermelanosis of the face. The pathogenesis of melasma is multifactorial and may be caused by interactions between genetics and the environment. Research has shown that skin pigmentation is regulated by the Melanocortin-1 Receptor gene (MC1R). In Japanese populations, Val92Met and Arg163Gln genotypes of MC1R gene polymorphisms are associated with freckles and lentigo solaris, because they have skin types II–III, but for Indonesians who are skin type IV, hyperpigmentation disorders are often melasma.

Purpose: This study aimed to identify the association between Val92Met and Arg163Gln genotypes of MC1R gene polymorphisms with the incidence of melasma in a Javanese women population.

Patients and methods: This study used unmatched case-control design, conducted by clinical examination and questionnaire. Data were analyzed with Chi-squared test and Odds Ratio (OR).

Results: This study evaluated 158 Javanese women from 18–60 years old with 79 case and 79 control subjects. The genotype of Val92Met was found more common in melasma subjects than in non-melasma (p=0.005) with (OR2.53; 95% CI:1.21–5.29). By using a bivariate test we showed sun exposure and family history of melasma were risk factors for melasma (OR:1.99; 95% CI:1.04–3.78) and (OR:35.32; 95% CI:10.25–121.70). However, genotype of Arg163Gln was not a risk factor for the incidence of melasma (OR: 0.86; 95% CI:0.39–1.89).

Conclusion: The findings showed Val92Met genotypes, sun exposure and family history were risk factors for melasma incidence. This is the first study on incidence of melasma in an Indonesian population and contributes to ongoing efforts to understand the mechanisms of melasma.

Retrospective Analysis of Endemic Melasma Patients

Melasma is an acquired diffuse hypermelanosis characterized by localized, symmetrical, irregular, light-to-dark brown maculae occurring in sun-exposed areas of skin. The aim of this retrospective study was to determine demographics of patients, analysis of etiologic factors, clinical features, efficacy and side effects of available topical treatments due to high incidence of melasma patients. In this study melasma patients in Birecik State Hospital were investigated retrospectively. Between January 2014 and October 2015, 1008 patients had diagnosis of melasma in 49,809 applications of 24,603 different patients who admitted to Dermatology Outpatient Clinics. Of the 1008 patients, 263 had completed 3-month treatment period. These patients did not receive treatment in June, July, August and September. All melasma patients were rural and dealing with agriculture. There was no significant difference between female and male patients in terms of age. Of the 253 female melasma patients, only 2 of them had not child and none of them were using hormone drug. Of the 263 patients with melasma, Fitzpatrick skin type was 3 in 79 (30%) patients, 4 in 184 (70%) patients. Şanliurfa city showed higher fertility rate, sun exposure, and skin type than Turkey as a whole. These predisposing factors may explain higher melasma occurrence in Şanliurfa. Patient information about preventive measures and treatment play important role in treatment of cosmetic condition. The most important measure seems to advise patients about sun-protection especially during pregnancy.