Japanese experiment of a complete and objective automatic grading system of facial signs from selfie pictures: Validation with dermatologists and characterization of changes due to age and sun exposures

Establishment and application of perceived age prediction model for the periocular aging research of Chinese Han women

BACKGROUND

The assessment of skin aging through skin measurements faces limitations, making perceived age evaluation a more valuable and direct tool for assessing skin aging. Given that the aging process markedly affects the appearance of the eye contour, characterizing the eye region could be beneficial for perceived age assessment. This study aimed to analyze age-correlated changes in the eye contour within the Chinese Han female population and to develop, validate, and apply a multiple linear regression model for predicting perceived age.

MATERIALS AND METHODS

A naïve panel of 107 Chinese women assessed the perceived ages of 212 Chinese Han women. Instrumental analysis evaluated periorbital parameters, including palpebral fissure width (PFW), palpebral fissure height (PFH), acclivity of palpebral fissure (AX), angle of inner canthal (AEN), and angle of outer canthal (AEX). These parameters were used to construct a multiple linear regression model for predicting the perceived ages of Chinese Han women. A combined treatment using Fotona 4D and an anti-aging eye cream, formulated with plant extracts, peptides, and antioxidants, was conducted to verify the cream's anti-aging efficacy and safety. This eye cream was then tested in a large-scale clinical trial involving 101 participants. The prediction model was employed in this trial to assess the perceived ages of the women after an 8-week application of the eye cream.

RESULTS

All parameters were observed to decrease with age. An intergroup comparison indicated that eyelid aging in Chinese Han women accelerates beyond the age of 50. Consequently, a linear regression model was constructed and validated, with the perceived age being calculated as 183.159 - 1.078 * AEN - 4.487 * PFW + 6.061 * PFH - 1.003 * AX - 0.328 * AEX. The anti-aging efficacy and safety of the eye cream were confirmed through combined treatment with Fotona 4D, showing improvements in wrinkles, elasticity, and dark circles under the eyes. In a large-scale clinical evaluation using this eye cream, a perceived age prediction model was applied, suggesting that 8 weeks of use made participants appear 2.25 years younger.

CONCLUSION

Our study developed and validated a multiple linear regression model to predict the perceived age of Chinese Han women. This model was successfully utilized in a large-scale clinical evaluation of anti-aging eye cream, revealing that 8 weeks of usage made participants appear 2.25 years younger. This method effectively bridges the gap between clinical research and consumer perceptions, explores the complex factors influencing perceived age, and aims to improve anti-aging formulations.

Differences in the annotation between facial images and videos for training an artificial intelligence for skin type determination

BACKGROUND

The Grand-AID research project, consisting of GRANDEL-The Beautyness Company, the dermatology department of Augsburg University Hospital and the Chair of IT Infrastructure for Translational Medical Research at Augsburg University, is currently researching the development of a digital skin consultation tool that uses artificial intelligence (AI) to analyze the user's skin and ultimately perform a personalized skin analysis and a customized skin care routine. Training the AI requires annotation of various skin features on facial images. The central question is whether videos are better suited than static images for assessing dynamic parameters such as wrinkles and elasticity. For this purpose, a pilot study was carried out in which the annotations on images and videos were compared.

MATERIALS AND METHODS

Standardized image sequences as well as a video with facial expressions were taken from 25 healthy volunteers. Four raters with dermatological expertise annotated eight features (wrinkles, redness, shine, pores, pigmentation spots, dark circles, skin sagging, and blemished skin) with a semi-quantitative and a linear scale in a cross-over design to evaluate differences between the image modalities and between the raters.

RESULTS

In the videos, most parameters tended to be assessed with higher scores than in the images, and in some cases significantly. Furthermore, there were significant differences between the raters.

CONCLUSION

The present study shows significant differences between the two evaluation methods using image or video analysis. In addition, the evaluation of the skin analysis depends on subjective criteria. Therefore, when training the AI, we recommend regular training of the annotating individuals and cross-validation of the annotation.

Predicting human chronological age via AI analysis of dorsal hand versus facial images: A study in a cohort of Indian females

Predicting a person's chronological age (CA) from visible skin features using artificial intelligence (AI) is now commonplace. Often, convolutional neural network (CNN) models are built using images of the face as biometric data. However, hands hold telltale signs of a person's age. To determine the utility of using only hand images in predicting CA, we developed two deep CNNs based on 1) dorsal hand images (H) and 2) frontal face images (F). Subjects (n = 1454) were Indian women, 20-80 years, across three geographic cohorts (Mumbai, New Delhi and Bangalore) and having a broad variation in skin tones. Images were randomised: 70% of F and 70% of H were used to train CNNs. The remaining 30% of F and H were retained for validation. CNN validation showed mean absolute error for predicting CA using F and H of 4.1 and 4.7 years, respectively. In both cases correlations of predicted and actual age were statistically significant (r(F) = 0.93, r(H) = 0.90). The CNNs for F and H were validated for dark and light skin tones. Finally, by blurring or accentuating visible features on specific regions of the hand and face, we identified those features that contributed to the CNN models. For the face, areas of the inner eye corner and around the mouth were most important for age prediction. For the hands, knuckle texture was a key driver for age prediction. Collectively, for AI estimates of CA, CNNs based solely on hand images are a viable alternative and comparable to CNNs based on facial images.

Awareness of sun exposure risks and photoprotection for preventing pigmentary disorders in Asian populations: Survey results from three Asian countries and expert panel recommendations

BACKGROUND

In this article, we review and discuss the photoprotection behavior of Asians based on the literature, along with a subanalysis of an original online survey, and make recommendations to optimize photoprotection for Asian populations to prevent photoaging and pigmentary disorders.

METHODS

An international panel of eight dermatologists from Asia (China, Korea, Japan, Singapore, Indonesia, and Vietnam) met to discuss sunscreen photoprotection for Asian patients. Additionally, a subanalysis of an online survey by 3000 respondents from three Asian countries (China, Indonesia, and Japan) investigated general public awareness and attitudes to sun exposure.

RESULTS

A pre-meeting survey of the eight experts from Asia showed key concerns of Asian patients consulting dermatologists are pigmentary disorders, especially actinic/senile lentigo, post-inflammatory hyperpigmentation, melasma, vitiligo, and Hori's nevus. The survey subanalysis of participants from China, Indonesia, and Japan with predominantly Fitzpatrick skin types (FST) II to IV revealed that they are particularly concerned about sun exposure causing photoaging and pigmentary disorders. Most of the respondents indicated they have limited knowledge on sunlight radiation and appropriate sunscreen protection factors. Only 22%, 13%, and 3% for China, Indonesia, and Japan, respectively, systematically use multiple protective measures (using sunscreen, avoiding midday sun, staying in the shade, wearing a hat, protective clothing, and sunglasses) when exposed to the sun.

CONCLUSIONS

Further education is needed for Asian populations on the importance of comprehensive daily photoprotection, including broad-spectrum sunscreen, with high UVA and visible light protection, to reduce and prevent photoaging and pigmentary disorders.

Photoaging's portrait: The road map towards its photoprotection

OBJECTIVE

To summarize key research published by the author's group, dealing with skin photoaging and its photoprotection.

MATERIALS AND METHODS

Two methodologies (standard photographs and selfies imaging) resulting from referential skin ageing atlases were applied on 2487 subjects of different ancestries, ages and gender. These aimed at first to best assess and grade the variable severities of some facial signs (texture/wrinkles, pigmentary spots, sagging and vascular disorders) that occur progressively during the photoaging process. Second, such methodologies were used to record the benefits brought by a photoprotective regimen (671 women and men).

RESULTS

In all studied ancestries, each facial sign show an increase severity along decades, at its own pace, some showing a linear like progression, whereas some plateau at early ages. These changes differed according to skin innate colour (phototype) and with individual behaviours vis-à-vis sun exposures, more so among European women than North-East Asian women. An effect of gender (less severe alterations) was observed on Chinese men, as compared to Chinese women. Pigmentary disorders were found hallmarks of photo-aged North-East Asian women. Globally, photoaging impact the apparent age of the different subjects. The counteracting effects of strong topical Photoprotective regimens were evidenced along a 6-month seasonality in Chinese and French women or 1-year period in Brazilian women with phototypes II to VI. Photoprotection led to a more even skin complexion among Indian subjects with pigment irregularities.

CONCLUSION

Two factors clearly hamper a better assessment of the efficiency of photoprotection of the sun-induced cutaneous ageing: short durations (months) of the studies with regard to the global fate of photoaging by decades and the number of studied subjects, limited to hundreds for practical reasons. The methodology based on the automatic analysis of facial signs through selfies images could theoretically bypass both factors, allowing thousands of subjects to be studied along years.

Video-based paired comparison to evaluate some cosmetic products under camera movement for dynamic performance

OBJECTIVE

Until now, standardized evaluation of cosmetic effects was conducted mainly in still conditions such as pictures. In real life, the consumers' experience of their cosmetics' effects is dynamic and some of the benefits can be better observed under movement. In order to capture motion-related performance of cosmetics, we developed a video-based paired comparison on an online platform.

METHODS

We validated this new tool through the evaluation of eyeshadow with high light reflection and colour gradation, especially visible under motion according to the observer point of view. This formula was compared with two marketed benchmarks. The three products were applied sequentially on the eyelid of eight Japanese women. Videos were taken in standardized light, speed and face position with a rotating camera around the face. The videos were uploaded on an online secured platform and eyelid 3D effect, highlight and colour gradation were evaluated through paired comparison test by 60 Japanese women from home on their PC or tablets. Those results were compared with picture-based paired comparison by the same observers.

RESULTS

Video-based paired comparison provided higher discrimination of products compared to picture-based comparison.

CONCLUSION

As compared to still camera acquisition, the evaluation of cosmetics based on videos is closer to real-life experience and can bring higher discrimination, especially for motion-related attributes.

Objective and automatic grading system of facial signs from smartphones' pictures in South African men: Validation versus dermatologists and characterization of changes with age

OBJECTIVE

To evaluate the capacity of the automatic detection system to accurately grade, from selfie pictures, the severity of eight facial signs in South African men.

METHODS

Selfie pictures (obtained from frontal and back cameras) of 281 South African men differently aged (20-70 years) were obtained and analyzed by an automatic artificial intelligence (AI)-based automatic grading system. Data were compared with the clinical gradings made by experts and dermatologists.

RESULTS

In all facial signs, both series of gradings were found highly correlated with, however, different coefficients (0.59-0.95), those of marionette lines and cheek pores being of lower values. No differences were observed between data obtained by frontal and back cameras. With age, in most cases, gradings show up to the 50-59 year age-class, linear-like changes. When compared to men of other ancestries, South African men present lower wrinkles/texture, pigmentation, and ptosis/sagging scores till 50-59 years, albeit not much different in the cheek pores sign. The early onset (mean age) of visibility of wrinkles/texture for South African men were (i.e., reaching grade >1) 39 and 45 years for ptosis/sagging.

CONCLUSION

This study completes and enlarges the previous works conducted on men of other ancestries by showing some South African specificities and slight differences with men of comparable phototypes (Afro American).

Accuracy and clinical relevance of an automated, algorithm-based analysis of facial signs from selfie images of women in the United States of various ages, ancestries and phototypes: A cross-sectional observational study

BACKGROUND

Real-life validation is necessary to ensure our artificial intelligence (AI) skin diagnostic tool is inclusive across a diverse and representative US population of various ages, ancestries and skin phototypes.

OBJECTIVES

To explore the relevance and accuracy of an automated, algorithm-based analysis of facial signs in representative women of different ancestries, ages and phototypes, living in the same country.

METHODS

In a cross-sectional study of selfie images of 1041 US women, algorithm-based analyses of seven facial signs were automatically graded by an AI-based algorithm and by 50 US dermatologists of various profiles (age, gender, ancestry, geographical location). For automated analysis and dermatologist assessment, the same referential skin atlas was used to standardize the grading scales. The average values and their variability were compared with respect to age, ancestry and phototype.

RESULTS

For five signs, the grading obtained by the automated system were strongly correlated with dermatologists' assessments (r ≥ 0.75); cheek skin pores were moderately correlated (r = 0.63) and pigmentation signs, especially for the darkest skin tones, were weakly correlated (r = 0.40) to the dermatologist assessments. Age and ancestry had no effect on the correlations. In many cases, the automated system performed better than the dermatologist-assessed clinical grading due to 0.3-0.5 grading unit differences among the dermatologist panel that were not related to any individual characteristic (e.g. gender, age, ancestry, location). The use of phototypes, as discontinuous categorical variables, is likely a limiting factor in the assessments of grading, whether obtained by automated analysis or clinical assessment of the images.

CONCLUSIONS

The AI-based automatic procedure is accurate and clinically relevant for analysing facial signs in a diverse and inclusive population of US women, as confirmed by a diverse panel of dermatologists, although skin tone requires further improvement.

Objective and automatic grading system of facial signs from selfie pictures of South African women: Characterization of changes with age and sun‐exposures

OBJECTIVE

To evaluate the capacity of the automatic detection system to accurately grade, from smartphones' selfie pictures, the severity of fifteen facial signs in South African women and their changes related to age and sun-exposure habits.

METHODS

A two-steps approach was conducted based on self-taken selfie images. At first, to assess on 306 South African women (20-69 years) enrolled in Pretoria area (25.74°S, 28.22°E), age changes on fifteen facial signs measured by an artificial intelligence (AI)-based automatic grading system previously validated by experts/dermatologists. Second, as these South African panelists were recruited according to their usual behavior toward sun-exposure, that is, nonsun-phobic (NSP, N = 151) and sun-phobic (SP, N = 155) and through their regular and early use of a photo-protective product, to characterize the facial photo-damages.

RESULTS

(1) The automatic scores showed significant changes with age, by decade, of sagging and wrinkles/texture (p < 0.05) after 20 and 30 years, respectively. Pigmentation cluster scores presented no significant changes with age whereas cheek skin pores enlarged at a low extent with two plateaus at thirties and fifties. (2) After 60 years, a significantly increased severity of wrinkles/texture and sagging was observed in NSP versus SP women (p < 0.05). A trend of an increased pigmentation of the eye contour (p = 0.06) was observed after 50 years.

CONCLUSION

This work illustrates specific impacts of aging and sun-exposures on facial signs of South African women, when compared to previous experiments conducted in Europe or East Asia. Results significantly confirm the importance of sun-avoidance coupled with photo-protective measures to avoid long-term skin damages. In inclusive epidemiological studies that aim at investigating large human panels in very different contexts, the AI-based system offers a fast, affordable and confidential approach in the detection and quantification of facial signs and their dependency with ages, environments, and lifestyles.

Comparing the self-perceived effects of a facial anti-aging product to those automatically detected from selfie images of Chinese women of different ages and cities

OBJECTIVE

To assess the agreement, after 1-month application of a popular and efficient anti-aging product, between self-perceived facial signs of aging and those detected and graded by an automatic A.I-based system, using smartphones' selfie images.

MATERIAL AND METHODS

Of 1065 Chinese women, aged 18-60 years, from eight different Chinese cities were recruited. They were asked to apply daily, for 1 month, a referential anti-aging product onto their whole face. Selfie images were taken by all subjects at D₀ and D₂₈ and sent to our facilities for being analyzed through 10 different facial signs. At D₂₈ , all subjects were asked to fill a questionnaire on the status of their faces, through six general statements.

RESULTS

A global agreement between both approaches is reached, particularly among women older than 40 years where the severity of facial signs is already more pronounced or among younger women who present at least facial signs scored above one grading units. This limit becomes, therefore, a prerequisite in the recruitment of Chinese subjects in the case of anti-aging applied studies and possible automatically based on automatic grading system. When respecting such conditions, the positive effects of the product on most facial signs can be demonstrated after 28 days of successive applications.

CONCLUSION

Such methodological approach paves the road in fulfilling the need of consumers of a better transparency in the claims of an anti-aging product.

A preliminary study to understand the effects of mask on tinted face cosmetics

Background

The recent COVID‐19 pandemic has generalized the use of face mask in public area, and it is now common to wear it for long hours. But face mask interfere with cosmetics, and key concerns for tinted products are staining of the mask and degradation on face. Consumers have modified beauty routine by a decrease of makeup, but are now expecting new products adapted to face mask. Little is known about the mechanisms that affect most the makeup under the face mask, so that further studies are needed to develop adequate evaluation methods and products. In this study, the color transfer on mask and makeup degradation on face are assessed through a mixed approach of consumer and instrumental evaluation.

Materials and Methods

Two tinted face products (A and B) were applied by half face on 11 Japanese women, who conducted real‐life activities with a face mask during 4 hours. Panelists evaluated the stain of their face mask by visual assessment, while the makeup degradation on face was evaluated by color measurement by instrumental method.

Results

No difference was observed between the two products for lasting on face, but consumer evaluation showed a better resistance of product A for color transfer on mask.

Conclusion

The mix of instrumental and consumer evaluation is a promising way to evaluate the makeup degradation on face and color transfer on mask, which are two key factors to develop mask resistant makeup products.

Changes in facial signs due to age and their respective weights on the perception of age and skin plumpness among differently aged Korean women

OBJECTIVE

To determine the respective weights of certain facial signs on the assessment of perceived age and plumpness on Korean women of different ages.

MATERIAL AND METHODS

Photographs were taken of the faces of 112 Korean women of different ages (18-80 years) under standardized conditions. These photographs allowed to focus and define 19 facial signs, which were then graded by 15 experts and dermatologists, using standardized scales provided by a reference Skin Aging Atlas. The facial signs were dispatched into 5 clusters, namely Wrinkles/Texture, Ptosis/Sagging, Pigmentation disorders, Vascular disorders, and Cheek skin pores. A naïve panel, composed of 92 Korean women, of similar age range were asked, when viewing full-face photographs, to: (a) attribute on a 0-10 scale their perception of the skin plumpness (ie supple/hydrated/nourished) and (b) estimate the age of the subject.

RESULTS

With the exception of Vascular disorders, the severity of all 4 clusters increased with age, although at different rates. The Wrinkles/Texture or Ptosis/Sagging showed a rather regular progression. Although perceived ages and real ages were found highly correlated, half of the subjects were judged older by 2-12 years. The facial signs/clusters were significantly correlated with perceived age, with the exceptions of vascular disorders, size of pigmentary spots and cheek skin pores. The weights in perceived ages of Wrinkles/Texture and Ptosis/Sagging represent 37% each and Pigmentation disorders at 26%. Skin plumpness was logically found significantly anti-correlated with perceived age. If, surprisingly, Vascular disorders were found not impacting the plumpness aspect, Cheek skin pores presented a clear influence.

CONCLUSION

Within facial clinical clusters, Wrinkles/Texture, Ptosis/Sagging, and Pigmentation disorders are major factors in the assessment of perceived age in Korean women. The perception of a decreased skin plumpness is significantly associated with increased perceived age.