Abstract Background The coronavirus disease 2019 (COVID-19) pandemic has had a wide-ranging impact on the lives and mental health of adolescents. Aims & Objectives We need to assess changes in adolescents' mental health and lifestyle habits. Method We conducted a secondary analysis using from a national cross-sectional cohort (Korean Youth Risk Behavior Web-Based Survey, KYRBS) collected before the COVID-19 outbreak (2018, 2019), during the pandemic (2020, 2021), and after the pandemic (2022). Results The degree of recovery from fatigue due to sleep showed improvement after the outbreak of the pandemic, but showed a pattern of worsening after the pandemic ended. The physical activity time has actually decreased due to the pandemic. Even though physical activity time has increased since the end of the pandemic, sleep quality appears to have decreased. The frequency of feeling sad and desperate decreased slightly during the pandemic, but increased after the pandemic compared to before the pandemic. Suicide-related indicators of suicidal thoughts, plans, and attempts also showed the same pattern, decreasing during the pandemic and then increasing again. the rate of male students experiencing sadness increased significantly after the end of the pandemic. Discussion & Conclusion Mental health-related problems among adolescents in Korea appear to be equal to or more severe than before the outbreak of the pandemic. We can see that the end of the COVID-19 pandemic cannot be equated with the end of the threat to youth mental health.

Facial analysis exhibits task-specific feature variations. While Convolutional Neural Networks (CNNs) have enabled the fine-grained representation of spatial information, Vision Transformers (ViTs) have facilitated the representation of semantic information at the patch level. Although the generalization of conventional methodologies has advanced visual interpretability, there remains paucity of research that preserves the unified feature representation on single task learning during the training process. In this work, we introduce ET-Fuser, a novel methodology for learning ensemble token by leveraging attention mechanisms based on task priors derived from pre-trained models for facial analysis. Specifically, we propose a robust prior unification learning method that generates a ensemble token within a self-attention mechanism, which shares the mutual information along the pre-trained encoders. This ensemble token approach offers high efficiency with negligible computational cost. Our results show improvements across a variety of facial analysis, with statistically significant enhancements observed in the feature representations.

PURPOSE:The coronavirus disease-2019 pandemic has severely affected mental health. This study aimed to examine the patterns and differences in mental and behavioral health in adolescents across distinct pandemic phases. METHODS:Data for a total of 278,989 adolescents from the KYRBS, covering the pre-pandemic (2018-2019), during-pandemic (2020-2021), and post-pandemic (2022) periods, were analyzed. Subgroups were compared based on sex, age, and socioeconomic status. Multiple linear regression analyses were conducted to examine temporal changes in perceived stress, sleep recovery, and physical activity during the pandemic period. RESULTS:The proportion of adolescents who reported feelings of perceived stress within the last 12 months exhibited a slight decline at the onset of the COVID-19 pandemic, followed by a rebound, and subsequently showed a marked increase in the post-pandemic period. Female and high-school students consistently exhibited high-stress levels across all time points, and adolescents from low socioeconomic backgrounds reported persistently high stress with minimal fluctuation. DISCUSSION:The findings highlighted the unequal impact of the pandemic on different adolescent populations, suggesting the need for targeted mental health support and recovery strategies. This study underscores the importance of understanding subgroup variations in order to effectively address the long-term effects of global crises on the mental health of adolescents.

BACKGROUND:Recommendations for cosmetics are gaining popularity, but they are not being made with consideration of the analysis of cosmetic ingredients, which customers consider important when selecting cosmetics.AIMS:This article aims to propose a method for estimating the efficacy of cosmetics based on their ingredients and introduces a system that recommends personalized products for consumers, combined with AI skin analysis.METHODS:We constructed a deep neural network architecture to analyze sequentially arranged cosmetic ingredients in the product and incorporated skin analysis models to get the precise skin status of users from frontal face images. Our recommendation system makes decisions based on the results optimized for the individual.RESULTS:Our cosmetic recommendation system has shown its effectiveness through reliable evaluation metrics, and numerous examples have demonstrated its ability to make reasonable recommendations for various skin problems.CONCLUSION:The result shows that deep learning methods can be used to predict the effects of products based on their cosmetic ingredients and are available for use in personalized cosmetic recommendations.

Facial acne is a prevalent dermatological condition regularly observed in the general population. However, it is important to detect acne early as the condition can worsen if not treated. For this purpose, deep-learning-based methods have been proposed to automate detection, but acquiring acne training data is not easy. Therefore, this study proposes a novel deep learning model for facial acne segmentation utilizing a semi-supervised learning method known as bidirectional copy–paste, which synthesizes images by interchanging foreground and background parts between labeled and unlabeled images during the training phase. To overcome the lower performance observed in the labeled image training part compared to the previous methods, a new framework was devised to directly compute the training loss based on labeled images. The effectiveness of the proposed method was evaluated against previous semi-supervised learning methods using images cropped from facial images at acne sites. The proposed method achieved a Dice score of 0.5205 in experiments utilizing only 3% of labels, marking an improvement of 0.0151 to 0.0473 in Dice score over previous methods. The proposed semi-supervised learning approach for facial acne segmentation demonstrated an improvement in performance, offering a novel direction for future acne analysis.

Cross-polarized images are beneficial for skin pigment analysis due to the enhanced visualization of melanin and hemoglobin regions. However, the required imaging equipment can be bulky and optically complex. Additionally, preparing ground truths for training pigment analysis models is labor-intensive. This study aims to introduce an integrated approach for generating cross-polarized images and creating skin melanin and hemoglobin maps without the need for ground truth preparation for pigment distributions. We propose a two-component approach: a cross-polarized image generation module and a skin analysis module. Three generative adversarial networks (CycleGAN, pix2pix, and pix2pixHD) are compared for creating cross-polarized images. The regression analysis network for skin analysis is trained with theoretically reconstructed ground truths based on the optical properties of pigments. The methodology is evaluated using the VISIA VAESTRO clinical system. The cross-polarized image generation module achieved a peak signal-to-noise ratio of 35.514 dB. The skin analysis module demonstrated correlation coefficients of 0.942 for hemoglobin and 0.922 for melanin. The integrated approach yielded correlation coefficients of 0.923 for hemoglobin and 0.897 for melanin, respectively. The proposed approach achieved a reasonable correlation with the professional system using actually captured images, offering a promising alternative to existing professional equipment without the need for additional optical instruments or extensive ground truth preparation.

Facial acne is a very common skin condition that can worsen or leave scars if left untreated. Hence, deep learning-based methods have been proposed to automatically detect acne. However, acquiring medical images like acne is difficult, and generating labels without expert advice is challenging. This study generated synthetic images using GAN and then improved acne segmentation performance through semi-supervised learning methods. To validate this, acne images were acquired using skin analysis equipment, and these were divided into labeled images with ground truth and unlabeled images without it. The GAN was then trained using the labeled images. By using the generated GAN model for semi-supervised learning to train an acne segmentation model, a performance of 71.47% was achieved, surpassing the 70.62% obtained through supervised learning alone. Furthermore, the performance reached 71.48% when trained on real unlabeled images, demonstrating that GAN use can produce results that are comparable to those obtained with real images.

One common approach to separatingmelanin and hemoglobin distribution from a color image is Independent Component Analysis (ICA). In this study, we propose a method based on deep learning to automatically detect suitable areas for successful facial pigmentation analysis. To do that, three deep learning models are utilized for segmentation and localization to offer a candidate region for ICA. The experiment was conducted using cross-polarized facial images selected from 200 subjects, and results showed that the deep learning-guided ICA can effectively identify regions of hyperpigmentation and successfully separate melanin and hemoglobin maps for evaluation.

Objectives: South Korea has the highest suicide rate among Organisation for Economic Co-operation and Development countries; there is an increasing trend in suicide attempts among middle and high school students. Various factors contribute to the risk of suicide among adolescents, and the perception of suicide prevention has emerged as a significant factor. This study aimed to investigate the association between emotional and behavioral difficulties among middle and high school students and their perceptions of suicide prevention and to explore differences in suicide perception according to age. Methods: A survey was conducted among community middle and high school students, including 530 participants, between 2020 and 2021. Emotional and behavioral difficulties were assessed using the Strengths and Difficulties Questionnaire-Korean version, and participants were asked to complete a questionnaire on the importance and possibility of suicide prevention. A correlation test and analysis of variance were used to examine the relationships between the variables, and suicide awareness was compared according to age. Results: The participants who displayed higher strength or lower difficulty were more likely to respond positively to suicide prevention measures. They also exhibited high strength and low difficulty levels, thus agreeing with the importance of suicide prevention. Regarding age-related perceptions of suicide, adults aged 20-29 years reported the lowest probability of suicide prevention. Conclusion: Suicide perceptions influence the incidence of suicide. Therefore, active societal engagement through suicide prevention campaigns and related education is essential to improve such perceptions. Continuous attention and support are required to address this issue.

Background:Deep learning in dermatology presents promising tools for automated diagnosis but faces challenges, including labor-intensive ground truth preparation and a primary focus on visually identifiable features. Spectrum-based approaches offer professional-level information like pigment distribution maps, but encounter practical limitations such as complex system requirements.Methods:This study introduces a spectrum-based framework for training a deep learning model to generate melanin and hemoglobin distribution maps from skin images. This approach eliminates the need for manually prepared ground truth by synthesizing output maps into skin images for regression analysis. The framework is applied to acquire spectral data, create pigment distribution maps, and simulate pigment variations.Results:Our model generated reflectance spectra and spectral images that accurately reflect pigment absorption properties, outperforming spectral upsampling methods. It produced pigment distribution maps with correlation coefficients of 0.913 for melanin and 0.941 for hemoglobin compared to the VISIA system. Additionally, the model’s simulated images of pigment variations exhibited a proportional correlation with adjustments made to pigment levels. These evaluations are based on pigment absorption properties, the Individual Typology Angle (ITA), and pigment indices.Conclusion:The model produces pigment distribution maps comparable to those from specialized clinical equipment and simulated images with numerically adjusted pigment variations. This approach demonstrates significant promise for developing professional-level diagnostic tools for future clinical applications.

Objective We aimed to classify subgroups of suicidality among adolescents and identify the influencing factors of the classification of these latent classes.Methods Suicidal thought, plans, and attempts as well as the feelings of sadness/hopelessness and loneliness were utilized as indicators to derive the suicidality classes. Additionally, health behaviors, such as dietary habits, physical activity, experiences of violence victimization, sexual activity, and deviant behavior, along with demographic factors, such as sex, school year, grades, and household income, were considered as influencing factors. The analysis utilized data from the 18th Youth Health Behavior Survey (2022) conducted by the Korea Disease Control and Prevention Agency, involving 51,850 middle and high school students.Results The findings revealed three latent classes of suicidality among adolescents: “active suicidality,” “passive suicidality,” and “non-suicidality.” The influencing factor analysis indicated that all factors, with the exception of high-intensity physical activities, significantly influenced the classification of latent classes of suicidality. Notably, walking exercise and the frequency of exercise during physical education class were found to be factors that differentiated between active and passive suicidality within the suicidality classes.Conclusion This study employed nationwide data to identify the exhibited suicidality classes among adolescents and tested the influencing factors necessary for predicting such classes. The study’s findings offer valuable insights for policy development in suicide prevention and suggest the need for developing customized interventions tailored to each identified class.

Facial acne is a common skin condition that can easily occur in oily skin. Since acne is a small area and its occurrence largely depends on the skin condition, it is difficult to detect it accurately. In this paper, we propose a new method for detecting facial acne based on semantic segmentation. As the layers in a typical CNN-based deep learning model become deeper, the spatial dimension decreases and the number of channels increases. However, since acne is a small object, its spatial information can be lost as the layers get deeper, and it is critical for detecting facial acne. To alleviate this problem, we propose a center point loss, which maintains the center of the acne even in the reduced spatial dimension of the layers and improves the detection performance. First, we generated a center point ground truth indicating the center of each acne from an acne ground truth and applied two max-pooling layers having different kernel sizes, respectively. Following that, center point maps were obtained from the acne segmentation model's two deep decoders, and center point losses were calculated with the center point ground truth. In addition, a semantic segmentation loss was computed by comparing the final feature map and the acne ground truth. Finally, we used the center point losses and the segmentation loss to train the acne segmentation model. Our proposed method was tested using images obtained from a commercial image acquisition system using facial skin analysis equipment. In our experiments, the performance was improved by using the center point loss, which showed higher IoU performance than the existing deep supervision method that used multi-losses for decoders.

Significance:Melanin and hemoglobin have been measured as important diagnostic indicators of facial skin conditions for aesthetic and diagnostic purposes. Commercial clinical equipment provides reliable analysis results, but it has several drawbacks: exclusive to the acquisition system, expensive, and computationally intensive.Aim:We propose an approach to alleviate those drawbacks using a deep learning model trained to solve the forward problem of light-tissue interactions. The model is structurally extensible for various light sources and cameras and maintains the input image resolution for medical applications.Approach:A facial image is divided into multiple patches and decomposed into melanin, hemoglobin, shading, and specular maps. The outputs are reconstructed into a facial image by solving the forward problem over skin areas. As learning progresses, the difference between the reconstructed image and input image is reduced, resulting in the melanin and hemoglobin maps becoming closer to their distribution of the input image.Results:The proposed approach was evaluated on 30 subjects using the professional clinical system, VISIA VAESTRO. The correlation coefficients for melanin and hemoglobin were found to be 0.932 and 0.857, respectively. Additionally, this approach was applied to simulated images with varying amounts of melanin and hemoglobin.Conclusion:The proposed approach showed high correlation with the clinical system for analyzing melanin and hemoglobin distribution, indicating its potential for accurate diagnosis. Further calibration studies using clinical equipment can enhance its diagnostic ability. The structurally extensible model makes it a promising tool for various image acquisition conditions.

This study aimed to discuss mental health services for children and adolescents that are being implemented as initiatives of the Korean government and to review the functions and roles of these projects during the COVID-19 pandemic. Three government departments are in charge of providing mental health services for children and adolescents: Ministry of Education, Ministry of Gender Equality and Family, and Ministry of Health and Welfare. The Ministry of Education has implemented several policies to facilitate the early detection of mental health issues among school students (from preventive interventions to selective interventions for high-risk students). The Ministry of Gender Equality and Family additionally serves out-of-school children and adolescents by facilitating early identification of adolescents in crises and providing temporary protection or emergency assistance (as required) through the Community Youth Safety-Net Project. Furthermore, the Ministry of Health and Welfare operates relevant mental health agencies for individuals of all ages including children and adolescents. Any high-risk students who have been screened through the projects of the Ministry of Education are supported through referrals to the following institutions for appropriate treatment of their symptoms: specialized hospitals, the Youth Counseling and Welfare Center operated by the Ministry of Gender Equality and Family, the National Youth Healing Center, the Mental Health Welfare Center operated by the Ministry of Health and Welfare, the Suicide Prevention Center, and the Child Welfare Center. To assist students who are facing any psychological difficulties because of the COVID-19 pandemic, the Ministry of Education has established a psychiatric support group for providing emergency mental health care; furthermore, schools are promoting psychological surveillance (e.g., provision of non-face-to-face counseling services that are centered around the Wee Center). The Ministry of Education, Ministry of Gender Equality and Family, and Ministry of Health and Welfare have provided varied mental health support services in order to address the challenges faced by children and adolescents during the pandemic. Nevertheless, the mental health services operated by each ministry do show some limitations because their service provision system is insufficiently collaborative. The present study discussed the positive effects of each initiative as well as its limitations; furthermore, it suggested improvements for facilitating the healthy development of children and adolescents' mental health.

This study presents a deep learning-based approach for consistent Sun Protection Factor (SPF) grading by quantifying skin erythema. Despite strict international standards, the current human-based Minimum Erythema Dose (MED) determination method for SPF evaluation suffers from inconsistency due to subjective criteria and the visual characteristics of erythema's large variance. We propose DeepErythema, a novel method that uses erythema quantification for MED determination. The proposed method comprises pre-processing methods, a deep learning segmentation model, and post-processing methods. The pre-processing methods include the UV irradiation area pointing, which accurately detects the inspection area as a UV-irradiated port. Additionally, the Median Gradation Reduction eliminates the gradation that arises due to the digital image collection environment. The deep learning segmentation model parts introduce a methodology for improving performance using various feature extractors and methodologies such as SeLu, Reverse Attention Gate, and MixedLoss. For post-processing, Perspective Transform Rectangle Restoration restores a distorted inspection area, and Relative Density Evaluation calculates a density score to consider skin characteristics and tone. We verified that utilizing the DeepErythema score in the UV SPF MED Evaluation (USME) dataset reduced the distribution of human-based MED decisions from 36 to 9 in the experimental results. This reduction in MED decision scope leads to improved consistency in SPF Index grading. Overall, the study contributes to the development of an objective and consistent evaluation method for SPF grading.

BackgroundSkin tone and pigmented regions, associated with melanin and hemoglobin, are critical indicators of skin condition. While most prior research focuses on pigment analysis, the capability to simulate diverse pigmentation conditions could greatly broaden the range of applications. However, current methodologies have limitations in terms of numerical control and versatility.MethodsWe introduce a hybrid technique that integrates optical methods with deep learning to produce skin tone and pigmented region-modified images with numerical control. The pigment discrimination model produces melanin, hemoglobin, and shading maps from skin images. The outputs are reconstructed into skin images using a forward problem-solving approach, with model training aimed at minimizing the discrepancy between the reconstructed and input images. By adjusting the melanin and hemoglobin maps, we create pigment-modified images, allowing precise control over changes in melanin and hemoglobin levels. Changes in pigmentation are quantified using the individual typology angle (ITA) for skin tone and melanin and erythema indices for pigmented regions, validating the intended modifications.ResultsThe pigment discrimination model achieved correlation coefficients with clinical equipment of 0.915 for melanin and 0.931 for hemoglobin. The alterations in the melanin and hemoglobin maps exhibit a proportional correlation with the ITA and pigment indices in both quantitative and qualitative assessments. Additionally, regions overlaying melanin and hemoglobin are demonstrated to verify independent adjustments.ConclusionThe proposed method offers an approach to generate modified images of skin tone and pigmented regions. Potential applications include visualizing alterations for clinical assessments, simulating the effects of skincare products, and generating datasets for deep learning.

BACKGROUND:This study aimed to gather a homogeneous sample of adolescent patients to analyze the differences in functional connectivity and brain network parameters between suicidal and non-suicidal major depressive disorder (MDD) patients using a data-driven whole-brain approach. METHODS:Patients recruited at the psychiatry department of Korea University Guro Hospital from November 2014 to March 2020 were diagnosed with MDD, were 13-18 years old, had IQ scores >80, had no family history of psychotic or personality disorders, had no smoking or alcohol consumption history, and were drug-naïve to psychotropic medication. Depressive symptoms were assessed using the Hamilton Depression Rating Scale and the Children's Depression Inventory. Structural and functional MRI scans were conducted and analyzed using the CONN toolbox. RESULTS:Of 74 enrolled patients, 62 were analyzed. Regions of interest (ROIs) showing higher betweenness centrality in non-suicidal patients were the left superior temporal gyrus and left supramarginal gyrus. ROIs showing higher betweenness centrality in suicidal patients were the right hippocampus, left intracalcarine cortex, right inferior temporal gyrus, and the lateral visual network. Suicidal patients also showed different resting state functional connectivity profiles from non-suicidal patients. LIMITATIONS:Small sample size. CONCLUSION:Suicidal patients may overthink and overvalue future risks while having a more negatively biased autobiographical memory. Social cognition and the ability to overcome egocentricity bias seem to weaken. Such features can disrupt cognitive recovery and resilience, leading to more suicidal behaviors. Therefore, increased suicidality is not acquired, but is an innate trait.

Facial wrinkles are important indicators of human aging. Recently, a method using deep learning and a semi-automatic labeling was proposed to segment facial wrinkles, which showed much better performance than conventional image-processing-based methods. However, the difficulty of wrinkle segmentation remains challenging due to the thinness of wrinkles and their small proportion in the entire image. Therefore, performance improvement in wrinkle segmentation is still necessary. To address this issue, we propose a novel loss function that takes into account the thickness of wrinkles based on the semi-automatic labeling approach. First, considering the different spatial dimensions of the decoder in the U-Net architecture, we generated weighted wrinkle maps from ground truth. These weighted wrinkle maps were used to calculate the training losses more accurately than the existing deep supervision approach. This new loss computation approach is defined as weighted deep supervision in our study. The proposed method was evaluated using an image dataset obtained from a professional skin analysis device and labeled using semi-automatic labeling. In our experiment, the proposed weighted deep supervision showed higher Jaccard Similarity Index (JSI) performance for wrinkle segmentation compared to conventional deep supervision and traditional image processing methods. Additionally, we conducted experiments on the labeling using a semi-automatic labeling approach, which had not been explored in previous research, and compared it with human labeling. The semi-automatic labeling technology showed more consistent wrinkle labels than human-made labels. Furthermore, to assess the scalability of the proposed method to other domains, we applied it to retinal vessel segmentation. The results demonstrated superior performance of the proposed method compared to existing retinal vessel segmentation approaches. In conclusion, the proposed method offers high performance and can be easily applied to various biomedical domains and U-Net-based architectures. Therefore, the proposed approach will be beneficial for various biomedical imaging approaches. To facilitate this, we have made the source code of the proposed method publicly available at: https://github.com/resemin/WeightedDeepSupervision.

Objective: Cyber addiction, which is more vulnerable in adolescents, is defined as the excessive use of computers and the Internet that causes serious psychological, social, and physical problems. In this study, we investigated the resting-state functional connectivity (rsFC) in adolescents with cyber addiction.Methods: We collected and analyzed resting-state functional neuroimaging data of 20 patients with cyber addiction, aged 13-18 years, and 27 healthy controls. Based on previous studies, the seed regions included the dorsolateral prefrontal cortex, medial orbitofrontal cortex, lateral orbitofrontal cortex, dorsal anterior cingulate cortex, insula, hippo -campus, amygdala, nucleus accumbens, and the ventral tegmental area. Seed-to-voxel analyses were performed to inves-tigate the differences between patients and healthy controls. A correlation analysis between rsFC and cyber addiction severity was also performed.Results: Patients with cyber addiction showed the following characteristics: increased positive rsFC between the left insular-right middle temporal gyrus; increased positive rsFC between the right hippocampus-right precentral gyrus; increased positive rsFC between the right amygdala-right precentral gyrus and right parietal operculum cortex; in-creased negative rsFC between the left nucleus accumbens-right cerebellum crus II and right cerebellum VI. Conclusion: Adolescents with cyber addiction show altered functional connectivity during the resting state. The findings of this study may help us better understand the neuropathology of cyber addiction in adolescents.