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.

Chronological Skin Changes Through Postmastectomy Radiotherapy Based on Radiotherapy Techniques: Using Quantitative Dermatological Measurements.

BACKGROUND: There has been few research on how to measure skin status quantitatively throughout the course of radiotherapy (RT). We evaluated the changes in the skin induced by 2 different RT techniques using objective measurements in breast cancer patients. METHODS: In this prospective study, between August 2015 and March 2019, serial measurements of the dermatological factors during and after postmastectomy radiotherapy (PMRT) were made in 40 breast cancer patients. PMRT was performed using the conventional photon tangential technique (PTT) or patient-tailored bolus technique (PTB). We analyzed these measurements using a mixed effect model and compared the clinically evaluated radiation dermatitis and patient-reported outcomes (PROs). RESULTS: The trend of changes in melanin and erythema was significantly different between the PTB and PTT groups (p = 0.045 and 0.016, respectively). At the 3-month follow-up erythema intensity and melanin were higher in the PTB group than in PTT group (both p < 0.001). Eight patients (40% in the PTB group) reported grade 2 radiation dermatitis and 1 patient (5% in the PTB group) reported grade 3 radiation dermatitis. No grade 2 or higher radiation dermatitis was found in the PTT group. Ten patients (50%) in the PTB group and 3 patients (15%) in the PTT group reported severe erythema likely due to questionable clinical evaluation, but hyperpigmentation was rarely reported at the follow-up visits. CONCLUSION: The PTB group showed higher intensity of erythema at the end of RT than the PTT group and the increase in melanin lasted until the 3-month follow-up visits in the PTB group. Moreover, patients subjectively appealed more severe symptoms following PTB in PROs.

Quantitative changes in skin composition parameters due to chemotherapy in breast cancer patients: a cohort study.

The objective of this study is to evaluate objective changes in water content, sebum content, transepidermal water loss (TEWL), and melanin due to breast cancer chemotherapy, and their association with subjective symptoms. Prospective cohort study of 61 patients 18 years of age or older with a postoperative diagnosis of stage I-III breast cancer, who received adjuvant chemotherapy between February and September 2012 at an outpatient breast cancer clinic in Korea. Objective skin parameters, measured using a noninvasive bioengineering device, and patient-reported dryness and dullness were assessed before chemotherapy, after two cycles of chemotherapy, and 1, 3, and 6 months after completion of chemotherapy. Water content (-6.5 %), sebum (-75.5 %), and TEWL (-22.4 %) significantly decreased during chemotherapy compared to pre-chemotherapy levels (all p values <0.001). These parameters were lowest at 1 month after completion of chemotherapy and recovered thereafter but did not return to baseline levels after 6 months of follow-up. Melanin increased during chemotherapy with respect to pre-chemotherapy levels (8.4 %; p < 0.001) but decreased from the first month after completion of chemotherapy through the end of follow-up (-17.1 %; p < 0.001). The patterns of skin changes were similar in patients with or without hormone therapy. Most of patients reported dryness (57.9 %) and dullness (49.1 %) after chemotherapy, and patient-reported dryness was significantly associated with decreased sebum content. Chemotherapy-induced substantial changes in objective skin composition parameters. These changes persisted after 6 months from completion of chemotherapy and were associated with patient-reported symptoms. Additional research is needed to translate these findings into interventions for improving the dermatologic quality of life of breast cancer patients undergoing chemotherapy.

A quantitative evaluation method using processed optical images and analysis of age-dependent changes on nasolabial lines.

BACKGROUND/PURPOSE: Nasolabial lines (NL) and wrinkles of the face are major features of aging. Wrinkles have been studied widely by morphological methods using 3-dimensional (3D) photographic analysis instrument, but NL were evaluated by visual scoring usually. To evaluate NL quantitatively, another method is needed. This study is purposed to find out quantitative method for evaluation of NL. METHOD: One hundred Korean female subjects aged 20 to 60 were recruited in this study. Facial image was taken using light source adjusted VISIA-CR(®) and 3-dimensional wrinkle depth on the NL area was evaluated by Phase shift rapid in vivo measuring of human skin (PRIMOS(®)). The pixel number of NL area and the angle were obtained using processed images. The severity of NL was assessed by visual score. Skin elasticity was measured by Cutometer(®) MPA580. Statistical significance was determined at P < 0.05. RESULT: The optical images obtained by light source adjusted VISIA-CR(®) were easy to distinguish NL and significantly increased age-dependently. And three parameters of elasticity (R2, R5, and R7) on NL area were gradually decreased with age. The Pearson correlation coefficient was -0.756 (P < 0.01) between R7 parameter and ages. Also the pixel number of NL area, angle, wrinkle depth on the NL area (Ra), and visual score were decreased elasticity-dependently. The pixel number of NL area was highly related to Ra (r = 0.567, P < 0.01) and visual score (r = 0.647, P < 0.01). CONCLUSION: This study has shown that NL severity is related to decrease of dermal elasticity and age using quantitative new method by processing optical images.

Quantitative Changes in Skin Composition Parameters after Radiation Therapy According to Surgery Types Among Patients with Breast Cancer: A Prospective Study.

BACKGROUND: In the current study, we sought to evaluate and compare the objective changes in biophysical parameters and patient-reported outcomes following radiation therapy (RT) in patients with breast cancer who underwent breast-conserving surgery (BCS) or modified radical mastectomy (MRM). MATERIALS AND METHODS: Patients older than 18 years, with stage I to III breast cancer, who were expected to receive RT were recruited between August 2015 and March 2019. Skin hydration, sebum content, pigmentation, and elasticity of the irradiated and unirradiated breast or chest wall were assessed using a noninvasive bioengineering device. Assessments were performed before the initiation of RT (T0); after the 5th (T1), 15th (T2), and 25th (T3) fractions; and 1 (T4) and 3 months (T5) after the completion of RT. Patient-reported outcomes were also evaluated using Radiation Dermatitis Assessment for Breast Cancer 11. RESULTS: Hydration and sebum levels on the irradiated breast decreased during RT and had not returned to baseline at T5. Erythema on the irradiated breast increased two-fold between T0 and T3, and melanin levels were significantly higher than those at baseline and those of the contralateral unirradiated breast until T5 (106.0 vs. 115.8, P = .03). More than half of the patients continued to report skin color changes, dryness, and pain after RT. The erythema in the irradiated site at T1 was significantly higher in the MRM group than in the BCS group (P for interaction = .04), while there were no significant differences in the changes of the other parameters. CONCLUSION: RT-induced changes in hydration, sebum, and melanin, and the majority of patient-reported pain, color changes, and dryness, even 3 months after the completion of treatment. There were no remarkable differences in the measurable skin parameters according to the surgery type, with the exception of erythema, which was higher in the MRM group 1 week after the start of RT.

Impact of Breast Reconstruction on Biophysical Parameters of Mammary Skin in Patients Receiving Postmastectomy Radiotherapy for Breast Cancer.

PURPOSE: In this study, we examined the impact of reconstruction using tissue expander insertion (TEI) on the risk of radiation dermatitis in patients undergoing postmastectomy radiotherapy (PMRT). METHODS: Between August 2015 and March 2019, patients with breast cancer who had received systemic chemotherapy and PMRT were prospectively included. Skin parameters, including melanin, erythema, hydration, sebum, and elasticity, were measured using a multi-probe instrument at 6 time points: before the initiation of radiotherapy (pre-RT), at weeks 1, 3, and 5 during radiotherapy (weeks 1-5), and 1 and 3-month after radiotherapy (post-RT-1m and post-RT-3m). Patient-reported outcomes (PROs) were assessed at each time point. Changes in biophysical parameters and PRO were compared between patients with and without TEI (TEI+ vs. TEI-). RESULTS: Thirty-eight patients, including 18 with TEI+ and 20 with TEI-, were analyzed. The pattern of time-course changes in biophysical parameters and PRO did not differ between TEI+ and TEI- patients. The melanin index was highest at post-RT-1m, while the erythema index was highest at week 5. At post-RT-3m, TEI+ patients presented higher melanin values than TEI- patients, with no statistical significance (coefficient, 47.9 vs. 14.2%; p = 0.07). In all patients, water content decreased throughout the measurement period. At post-RT-3m, TEI+ patients demonstrated a further decrease in water content, while the TEI- group nearly recovered the water content to pre-RT status (coefficient, -17.1, -2.5; p = 0.11). The sebum and elasticity levels were not altered by TEI. CONCLUSION: In patients undergoing PMRT, TEI did not significantly affect the changing patterns of skin biophysical parameters and PRO during radiotherapy.

Interference with oxidative phosphorylation enhances anoxic expression of rice alpha-amylase genes through abolishing sugar regulation.

Rice has the unique ability to express alpha-amylase under anoxic conditions, a feature that is critical for successful anaerobic germination and growth. Previously, anaerobic conditions were shown to up-regulate the expression of Amy3 subfamily genes (Amy3B/C, 3D, and 3E) in rice embryos. These genes are known to be feedback regulated by the hydrolytic products of starchy endosperm such as the simple sugar glucose. It was found that oxygen deficiency interferes with the repression of Amy3D gene expression imposed by low concentrations of glucose but not with that imposed by higher amounts. This differential anoxic de-repression depending on sugar concentration suggests the presence of two distinct pathways for sugar regulation of Amy3D gene expression. Anoxic de-repression can be mimicked by treating rice embryos with inhibitors of ATP synthesis during respiration. Other sugar-regulated rice alpha-amylase genes, Amy3B/C and 3E, behave similarly to Amy3D. Treatment with a respiratory inhibitor or anoxia also relieved the sugar repression of the rice CIPK15 gene, a main upstream positive regulator of SnRK1A that is critical for Amy3D expression in response to sugar starvation. SnRK1A accumulation was previously shown to be required for MYBS1 expression, which transactivates Amy3D by binding to a cis-acting element found in the proximal region of all Amy3 subfamily gene promoters (the TA box). Taken together, these results suggest that prevention of oxidative phosphorylation by oxygen deficiency interferes with the sugar repression of Amy3 subfamily gene expression, leading to their enhanced expression in rice embryos during anaerobic germination.