Development and application of artificial intelligence-based facial skin image diagnosis system: Changes in facial skin characteristics with ageing in Korean women.

OBJECTIVE: To develop and validate an artificial intelligence (AI)-based diagnostic system for analysing facial skin images using expert judgements and explore its feasibility for skin ageing research, specifically by evaluating facial skin changes in Korean women of various ages. METHODS: Our AI-based facial skin diagnosis system (Dr. AMORE®) uses facial images of Korean women to analyse wrinkles, pigmentation, skin pores, and other skin red spots. The system is trained using clinical expert evaluations and deep learning. We assessed the system's precision and sensitivity by analysing the correlation between the diagnoses by the AI system and those of the experts. We used 120 images of Korean women aged 10-60 years to evaluate the changes in various facial skin characteristics with ageing. RESULTS: The precision and sensitivity of the developed system were excellent (>0.9%), and the diagnosis scores using the detected area and intensity of each item were correlated significantly higher with the visual evaluation results of the clinical experts (>0.8, p < 0.001). We also analysed facial images of Korean women aged 10-60 years to quantify changes in the scores of wrinkles, pigmentation, and skin pores with age. We identified the age group with the most significant changes as 20s to 30s. Analysis of the detailed skin characteristics of each item showed that wrinkles and pigmentation changed significantly in the 20s-30s, and skin pores increased significantly in the 10s-20s. There was no significant correlation with age or change according to the age group for skin red spots. CONCLUSION: Developed AI-based facial skin diagnosis system can automatically diagnose skin conditions based on clinical expert judgement using only photographic images and analyse various items in detail, quantitatively, and visually. This AI system can provide new and useful approaches in research areas that require a lot of resources and different characterizations, such as the study of facial skin ageing.

OBJECTIF: Développer et valider un système de diagnostic basé sur l'intelligence artificielle (IA) pour analyser les images de la peau du visage à l'aide de jugements d'experts et explorer sa faisabilité pour la recherche sur le vieillissement de la peau, en particulier en évaluant les changements de la peau du visage chez les femmes Coréennes de différents âges. MÉTHODES: Notre système de diagnostic de la peau du visage basé sur l'intelligence artificielle (Dr. AMORE®) utilise des images du visage de femmes Coréennes pour analyser les rides, la pigmentation, les pores de la peau et d'autres taches rouges de la peau. Le système est entraîné à l'aide d'évaluations d'experts cliniques et de l'apprentissage profond. Nous avons évalué la précision et la sensibilité du système en analysant la corrélation entre les diagnostics du système d'IA et ceux des experts. Nous avons utilisé 120 images de femmes coréennes âgées de 10 à 60 ans pour évaluer les changements de diverses caractéristiques de la peau du visage avec le vieillissement. RÉSULTATS: la précision et la sensibilité du système développé étaient excellentes (>0.9%), et les scores de diagnostic utilisant la zone détectée et l'intensité de chaque élément étaient corrélés de manière significativement plus élevée avec les résultats de l'évaluation visuelle des experts cliniques (>.8, p < 0.001). Nous avons également analysé des images du visage de femmes coréennes âgées de 10 à 60 ans afin de quantifier les changements dans les scores des rides, de la pigmentation et des pores de la peau avec l'âge. Nous avons identifié le groupe d'âge présentant les changements les plus significatifs comme étant celui des 20­30 ans. L'analyse des caractéristiques détaillées de la peau pour chaque élément a montré que les rides et la pigmentation changeaient de manière significative chez les 20­30 ans, et que les pores de la peau augmentaient de manière significative chez les 10­20 ans. Il n'y avait pas de corrélation significative avec l'âge ou de changement en fonction du groupe d'âge pour les taches rouges de la peau. CONCLUSION: Le système de diagnostic de la peau du visage basé sur l'IA peut diagnostiquer automatiquement les affections cutanées sur la base d'un jugement d'expert clinique en utilisant uniquement des images photographiques et analyser divers éléments en détail, quantitativement et visuellement. Ce système d'IA peut fournir des approches nouvelles et utiles dans des domaines de recherché qui nécessitent beaucoup de ressources et de caractérisations différentes, comme l'étude du vieillissement de la peau du visage.

Degenerative tendon matrix induces tenogenic differentiation of mesenchymal stem cells.

PURPOSE: Mesenchymal stem cells (MSCs) react dynamically with the surrounding microenvironment to promote tissue-specific differentiation and hence increase targeted regenerative capacity. Extracellular matrix (ECM) would be the first microenvironment to interact with MSCs injected into the tissue lesion. However, degenerative tissues would have different characteristics of ECM in comparison with healthy tissues. Therefore, the influence of degenerative ECM on tissue-specific differentiation of MSCs and the formation of matrix composition need to be considered for the sophisticated therapeutic application of stem cells for tissue regeneration. METHODS: Human degenerative tendon tissues were obtained from patients undergoing rotator cuff repair and finely minced into 2 ~ 3 mm fragments. Different amounts of tendon matrix (0.005 g, 0.01 g, 0.025 g, 0.05 g, 0.1 g, 0.25 g, 0.5 g, 1 g, and 2 g) were co-cultured with bone marrow MSCs (BM MSCs) for 7 days. Six tendon-related markers, scleraxis, tenomodulin, collagen type I and III, decorin, and tenascin-C, osteogenic marker, alkaline phosphatase (ALP), and chondrogenic marker, aggrecan (ACAN), were analyzed by qRT-PCR. Cell viability and senescence-associated beta-galactosidase assays were performed. The connective tissue growth factor was used as a positive control. RESULTS: The expressions of six tendon-related markers were significantly upregulated until the amount of tendon matrix exceeded 0.5 g, the point where the mRNA expressions of all six genes analyzed started to decrease. The tendon matrix exerted an inhibitory effect on ACAN expression but had a negligible effect on ALP expression. Cell viability did not change significantly over the culture period. The amount of tendon matrix exceeding 0.01 g significantly increased the SA-ßgal activity of BM MSCs. CONCLUSION: This study successfully demonstrated tendon ECM-stimulated tenogenesis of BM MSCs through an indirect co-culture system without the use of exogenous growth factors and the alteration of cellular viability. In contrast to the initial hypothesis, the tenogenesis of BM MSCs induced with the degenerative tendon matrix accompanied cellular senescence.