The relevance and accuracy of an AI algorithm-based descriptor on 23 facial attributes in a diverse female US population.

BACKGROUND: The response of AI in situations that mimic real life scenarios is poorly explored in populations of high diversity. OBJECTIVE: To assess the accuracy and validate the relevance of an automated, algorithm-based analysis geared toward facial attributes devoted to the adornment routines of women. METHODS: In a cross-sectional study, two diversified groups presenting similar distributions such as age, ancestry, skin phototype, and geographical location was created from the selfie images of 1041 female in a US population. 521 images were analyzed as part of a new training dataset aimed to improve the original algorithm and 520 were aimed to validate the performance of the AI. From a total 23 facial attributes (16 continuous and 7 categorical), all images were analyzed by 24 make-up experts and by the automated descriptor tool. RESULTS: For all facial attributes, the new and the original automated tool both surpassed the grading of the experts on a diverse population of women. For the 16 continuous attributes, the gradings obtained by the new system strongly correlated with the assessment made by make-up experts (r ≥ 0.80; p < 0.0001) and supported by a low error rate. For the seven categorical attributes, the overall accuracy of the AI-facial descriptor was improved via enrichment of the training dataset. However, some weaker performance in spotting specific facial attributes were noted. CONCLUSION: In conclusion, the AI-automatic facial descriptor tool was deemed accurate for analysis of facial attributes for diverse women although some skin complexion, eye color, and hair features required some further finetuning.

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.

A 5-hour follow-up of the impact on ageing facial signs of some foundations in Japanese women through automatically analysed selfie pictures.

OBJECTIVE: To explore the possibility of an automatic grading algorithm to detect and quantify, from selfie pictures, the subtle changes of facial signs brought by the application of a foundation. MATERIAL AND METHODS: A total of 270 Japanese differently aged women (30-54y) living in four different Japanese cities took selfies before, immediately and 5 h after having applied their own foundation, with their own routine. RESULTS: The analysis of 810 selfie pictures revealed (3 times × 270 women) that, prior to applications, all women presented a low grade of facial ageing. In most cases, the severities of less marked facial signs were detected and quantified, found affected by routine at different extents in all age-classes, but more intensely in the older age-class (45-54y) despite their more pronounced signs in bare skin status. In contrast, periorbital wrinkles were detected as more severe in all age-classes at both timing, that is, immediately and 5 h post-application as well as Nasolabial folds 5 h post-application. The amplitude of these positive or negative changes, although found of low amplitude, as decimals of the initial grades, was significantly detected. CONCLUSION: This automatic system appears apt at grading subtle changes in facial ageing signs brought by a foundation and could be a valuable help to the consumers of make-up products, in refining their individual procedure to obtain a more personalized desired facial appearance.

OBJECTIF: Explorer la possibilité pour un algorithme de scorage automatique des signes faciaux de détecter et quantifier sur la base de photographies 'selfies', les changements subtils apportés par l'application et la tenue de fonds de teint. MATÉRIEL ET MÉTHODES: 270 femmes japonaises âgées de 30 à 54 ans et vivant dans 4 villes différentes ont pris des selfies sur la base de leur smartphone avant, immédiatement et 5 heures après avoir appliqué leurs routines cosmétiques incluant leur propre fond de teint. RÉSULTATS: L'analyse des 810 selfies (3 temps×270 femmes) a révélé que, avant application, la plupart des femmes présentent des grades faibles de vieillissement facial. Dans la plupart des cas, les sévérités des signes les moins marqués, détectés et quantifiés, a été trouvée affectée à différents niveaux dans toutes les classes d'âge, mais plus intensément pour les volontaires les plus âgées (45 à 54 ans) en dépit de leurs valeurs plus élevées sur peau nue. A contrario, les rides péri-orbitales ont été mesurées comme plus sévères dans toutes les classes d'âge à tous les temps, c'est-à-dire immédiatement et 5 heures apprès application du fond de teint tandis que le sillon nasogénien a été observé comme plus sévère 5 heures après application. L'amplitude de ces changements positifs ou négatifs, bien que faible avec des valeurs décimales des grades initiaux, a été significativement détectée. CONCLUSIONS: Le système de scorage automatique apparaît capable d'évaluer des changements subtils dans les signes de vieillissement faciaux apportés par l'application de fonds de teint et se révèle une aide intéressante aux consommateurs de produits de maquillage pour affiner leurs routines individuelles afin d'obtenir des résultats plus personnalisés sur l'apparence désirée.

Virtual approach of the aesthetical fit between hair colours and skin tones in women of different ethnical origin backgrounds.

OBJECTIVE: To determine the aesthetical accordance between a given skin tone and the 11 possible colours of head hairs, covered by a marketed hair colouration product. MATERIAL AND METHODS: The photographs of professional top models, representing several ancestries (non-Hispanic European and Euro-American, East Asian, Hispanic Euro-American, and African-American ancestries), were used to virtually modify skin tones (from light, medium to dark) and hair colour by an artificial intelligence (AI)-based algorithm. Hence, 117 modified photographs were then assessed by five local panels of about 60 women each (one in China, one in France and three in US). The same questionnaire was given to the panels, written in their own language, asking which and how both skin tones and hair colours fit preferentially (or not appreciated), asking in addition the reasons of their choices, using fixed wordings. RESULTS: Answers from the five panels differed according to origin or cultural aspects, although some agreements were found among both non-Hispanic European and Euro-American groups. The Hispanic American panel in US globally much appreciated darker hair tones (HTs). Two panels (East Asian in China and African American in US) and part of non-Hispanic European panel in France declared appreciating all HTs, almost irrespective with the skin tone (light, medium and dark). This surprising result is very likely caused by gradings (in %) that differ by too low values, making the establishment of a decisive or significant assessment. By nature highly subjective (culturally and/or fashion driven), the assessments should be more viewed as trends, an unavoidable limit of the present virtual approach. The latter offers nevertheless a full respect of ethical rules as such objective could hardly be conducted in vivo: applying 10 or 11 hair colourations on the same individual is an unthinkable option. CONCLUSION: The virtual approach developed in the present study that mixes two major facial coloured phenotypes seems at the crossroad of both genetic backgrounds and the secular desire of a modified appearance. Nonetheless, this methodology could afford, at the individual level in total confidentiality, a great help to subjects exposed to some facial skin disorders or afflictions.

Developing an Artificial Intelligence (A.I)-based descriptor of facial appearance that fits with the assessments of makeup experts.

OBJECTIVE: To develop an A.I-based automatic descriptor that detects and grades, from selfie pictures, 23 facial signs, hairs included, as a help to making-up procedures. MATERIAL AND METHODS: The selfie images taken in very different conditions by 3326 women and men were used to create (90% of dataset) and validate (10% of dataset) a new algorithm architecture to appraise and grade 23 different facial signs such as lips, nose, eye color, eyebrows, eyelashes, and hair color as defined by makeup artists. Each selfie image was annotated by 12 experts and defined references to train Artificial Intelligence (A.I)-based algorithm. RESULTS: As some the 23 signs present a continuous or discontinuous feature, these were analyzed by two different statistical approaches. The results provided by the automatic descriptor system were not only in good agreement with the expert's assessments but were even found of a better precision and reproducibility. This automatic descriptor system has proven a good and robust accuracy despite the very variable conditions in the acquisition of selfie pictures. CONCLUSION: Such automatic descriptor system seems providing a valuable help in making-up procedures and may extend to other activities such as Skincare or Haircare. As such it should allow large investigations to better evaluate the consumers' needs of esthetical improvements.

Targeted, high-depth, next-generation sequencing of cancer genes in formalin-fixed, paraffin-embedded and fine-needle aspiration tumor specimens.

Implementation of highly sophisticated technologies, such as next-generation sequencing (NGS), into routine clinical practice requires compatibility with common tumor biopsy types, such as formalin-fixed, paraffin-embedded (FFPE) and fine-needle aspiration specimens, and validation metrics for platforms, controls, and data analysis pipelines. In this study, a two-step PCR enrichment workflow was used to assess 540 known cancer-relevant variants in 16 oncogenes for high-depth sequencing in tumor samples on either mature (Illumina GAIIx) or emerging (Ion Torrent PGM) NGS platforms. The results revealed that the background noise of variant detection was elevated approximately twofold in FFPE compared with cell line DNA. Bioinformatic algorithms were optimized to accommodate this background. Variant calls from 38 residual clinical colorectal cancer FFPE specimens and 10 thyroid fine-needle aspiration specimens were compared across multiple cancer genes, resulting in an accuracy of 96.1% (95% CI, 96.1% to 99.3%) compared with Sanger sequencing, and 99.6% (95% CI, 97.9% to 99.9%) compared with an alternative method with an analytical sensitivity of 1% mutation detection. A total of 45 of 48 samples were concordant between NGS platforms across all matched regions, with the three discordant calls each represented at <10% of reads. Consequently, NGS of targeted oncogenes in real-life tumor specimens using distinct platforms addresses unmet needs for unbiased and highly sensitive mutation detection and can accelerate both basic and clinical cancer research.

Western diet enhances hepatic inflammation in mice exposed to cecal ligation and puncture.

BACKGROUND: Obese patients display an exaggerated morbidity during sepsis. Since consumption of a western-style diet (WD) is a major factor for obesity in the United States, the purpose of the present study was to examine the influence of chronic WD consumption on hepatic inflammation in mice made septic via cecal ligation and puncture (CLP). Feeding mice diets high in fat has been shown to enhance evidence of TLR signaling and this pathway also mediates the hepatic response to invading bacteria. Therefore, we hypothesized that the combined effects of sepsis and feeding WD on TRL-4 signaling would exacerbate hepatic inflammation. Male C57BL/6 mice were fed purified control diet (CD) or WD that was enriched in butter fat (34.4% of calories) for 3 weeks prior to CLP. Intravital microscopy was used to evaluate leukocyte adhesion in the hepatic microcirculation. To demonstrate the direct effect of saturated fatty acid on hepatocytes, C3A human hepatocytes were cultured in medium containing 100 µM palmitic acid (PA). Quantitative real-time PCR was used to assess mRNA expression of tumor necrosis factor-alpha (TNF-α, monocyte chemotactic protein-1 (MCP-1), intercellular adhesion molecule-1 (ICAM-1), toll-like receptor-4 (TLR-4) and interleukin-8 (IL-8). RESULTS: Feeding WD increased firm adhesion of leukocytes in the sinusoids and terminal hepatic venules by 8-fold six hours after CLP; the increase in platelet adhesion was similar to the response observed with leukocytes. Adhesion was accompanied by enhanced expression of TNF-α, MCP-1 and ICAM-1. Messenger RNA expression of TLR-4 was also exacerbated in the WD+CLP group. Exposure of C3A cells to PA up-regulated IL-8 and TLR-4 expression. In addition, PA stimulated the static adhesion of U937 monocytes to C3A cells, a phenomenon blocked by inclusion of an anti-TLR-4/MD2 antibody in the culture medium. CONCLUSIONS: These findings indicate a link between obesity-enhanced susceptibility to sepsis and consumption of a western-style diet.

Role of LPS in the hepatic microvascular dysfunction elicited by cecal ligation and puncture in mice.

BACKGROUND/AIMS: Sepsis remains a leading cause of death in critically ill patients. Because endotoxemia is viewed as a key mediator of sepsis-induced inflammation, administration of bacterial endotoxin (LPS) is often used to simulate sepsis in experimental animals. This study tests the hypothesis that LPS is a critical determinant of the hepatic microvascular dysfunction in mice made septic by cecal ligation and puncture (CLP). METHODS: Intravital videomicroscopy was used to quantify sinusoidal perfusion, and platelet and leukocyte adhesion in terminal hepatic venules (THV) and sinusoids in LPS-sensitive and LPS-insensitive mice subjected to CLP or LPS (i.p.). mRNA expression of TLR-2, TLR-4, MyD-88, and Ly-96 was also assessed. RESULTS: While LPS-sensitive mice responded to both CLP and LPS challenges with elevated leukocyte and platelet adhesion in THV and sinusoids, and a reduced sinusoidal perfusion density, LPS-insensitive mice exhibited comparable blood cell adhesion and sinusoidal malperfusion following CLP, but not LPS. Hepatic mRNA of MyD-88 and TLR-2 was elevated in the CLP and LPS groups. Endotoxin was not detectable in the blood of LPS-sensitive mice after CLP, but was elevated after LPS administration. CONCLUSIONS: These findings do not support a major role for LPS in the hepatic microvascular disturbances associated with polymicrobial sepsis.

Regulation of chronic colitis in athymic nu/nu (nude) mice.

The objective of this study was to assess the roles of NK cells, B cells and/or intraepithelial lymphocytes (IEL) in suppressing the development of colitis in nude mice reconstituted with CD4(+)CD45RB(high) T cells. BALB/c nude mice were lethally irradiated and reconstituted with bone marrow from different immunodeficient mice to generate athymic chimeras devoid of one or more lymphocyte populations. Transfer of CD4(+)C45RB(high) T cells into chimeric recipients devoid of B cells, T cells and IEL produced severe colitis within 6-8 weeks, whereas transfer of these same T cells into B cell- and T cell-deficient or T cell-deficient chimeras produced little to no gut inflammation. In addition, we found that nude mice depleted of NK cells or RAG-1(-/-) mice reconstituted with IEL failed to develop colitis following transfer of CD45RB(high) T cells. Severe colitis could, however, be induced in nude mice by transfer of activated/T(h)1 CD4(+)CD45RB(low) T cells. Taken together, our data suggest that IEL, but not B cells or NK cells, play an important role in suppressing the development of chronic colitis in this model. In addition, our data demonstrate that suppression of disease may be due to polarization of naive CD4(+) cells toward a non-pathogenic and/or regulatory phenotype.

Transfection of IL-10 expression vectors into endothelial cultures attenuates alpha4beta7-dependent lymphocyte adhesion mediated by MAdCAM-1.

BACKGROUND: Enhanced expression of MAdCAM-1 (mucosal addressin cell adhesion molecule-1) is associated with the onset and progression of inflammatory bowel disease. The clinical significance of elevated MAdCAM-1 expression is supported by studies showing that immunoneutralization of MAdCAM-1, or its ligands reduce inflammation and mucosal damage in models of colitis. Interleukin-10 (IL-10) is an endogenous anti-inflammatory and immunomodulatory cytokine that has been shown to prevent inflammation and injury in several animal studies, however clinical IL-10 treatment remains insufficient because of difficulties in the route of IL-10 administration and its biological half-life. Here, we examined the ability of introducing an IL-10 expression vector into endothelial cultures to reduce responses to a proinflammatory cytokine, TNF-alpha METHODS: A human IL-10 expression vector was transfected into high endothelial venular ('HEV') cells (SVEC4-10); we then examined TNF-alpha induced lymphocyte adhesion to lymphatic endothelial cells and TNF-alpha induced expression of MAdCAM-1 and compared these responses to control monolayers. RESULTS: Transfection of the IL-10 vector into endothelial cultures significantly reduced TNF-alpha induced, MAdCAM-1 dependent lymphocyte adhesion (compared to non-transfected cells). IL-10 transfected endothelial cells expressed less than half (46 +/- 6.6%) of the MAdCAM-1 induced by TNF-alpha (set as 100%) in non-transfected (control) cells. CONCLUSION: Our results suggest that gene therapy of the gut microvasculature with IL-10 vectors may be useful in the clinical treatment of IBD.