Hasil untuk "Dermatology"

Omneya O. Elhagry, Ahmed M. Soliman, Hisham A. Shokeir et al.

Background Idiopathic hirsutism, characterized by excessive male-pattern hair growth in women with normal androgen levels, affects up to 10% of females and carries significant psychosocial impacts. While alexandrite laser therapy remains a gold standard for hair reduction, adjunctive treatments are sought to enhance outcomes. Liquorice (Glycyrrhiza glabra), known for its antiandrogenic properties, offers a promising alternative. Objective To compare the clinical efficacy and safety of combining topical liquorice extract with 755 nm alexandrite laser versus laser therapy alone in treating idiopathic hirsutism. Patients and methods In this comparative study, thirty women aged 18–45 years with idiopathic facial hirsutism were randomized into two groups: group A received laser treatment only, while group B received laser combined with topical liquorice extract. Treatments were conducted every four weeks for up to eight sessions. Outcomes were assessed by dermoscopic hair count, hair thickness measurements, and rates of hair regrowth, alongside photographic documentation and statistical analysis. Results Both groups showed significant improvement; however, group B demonstrated superior outcomes. A significantly higher proportion of patients in group B (86.7%) achieved greater than or equal to 85% improvement compared with group A (60%) (P=0.0303). Group B also showed significantly greater reductions in hair thickness and count (P=0.033 and P=0.0218, respectively) and slower hair regrowth (P=0.0013). No significant adverse events were reported. Conclusion Topical liquorice extract enhances the efficacy of alexandrite laser therapy in idiopathic hirsutism without added risk, offering a safe and effective adjunctive treatment strategy.

Win Min Han, Bastian Neesgaard, Michael Knappik et al.

Summary: Background: Data on cancer incidence and associated risk factors among women with HIV are limited. We investigated cancer burden among women with HIV. Methods: We included all women ≥18 years from the two large multicentre observational cohort collaborations (D:A:D and RESPOND). The primary outcomes were incidence of all cancers, HPV-related and common individual cancers including breast cancer, lung cancer, and non-Hodgkin lymphoma (NHL) from 2006 to 2021. Baseline was defined as the latest date of entry into local cohort enrolment and 1st January 2006 for D:A:D and 1st January 2012 for RESPOND. Participants were followed from baseline until the date of first cancer, final follow-up or administrative censoring—whichever occurred first. We assessed risk factors using multivariable Poisson regression by applying robust standard errors and determined a population attributable fraction (PAF) for key risk factors for cancers. Findings: Among 17,512 women included, median age at baseline was 39.5 years (interquartile range, IQR 32.5–46.0). Over 141,404 person-years (PYS) and a median 9.2 (5.5–10.1) years of follow-up, 832 women were diagnosed with any cancer; incidence rate 5.9 (95% CI 5.5–6.4)/1000 PYS, 163 HPV-related cancers (1.1 [1.0–1.3]/1000 PYS), 150 breast cancers (1.1 [0.9–1.2]/1000 PYS), 94 lung cancers (0.7 [0.5–0.8]/1000 PYS) and 72 NHL (0.5 [0.4–0.6]/1000 PYS). Older age (≥45 vs. <45 years), Southern Europe (vs. Western Europe) and smoking were associated with an increased risk of overall cancers. Lower pre-ART nadir CD4, time-updated CD4, and a prior AIDS diagnosis were associated with lung- and HPV-related cancer. In PAF analysis, smoking and HIV-related factors such as lower current CD4, nadir CD4 and HIV viremia significantly contributed to cancer risk. Interpretation: Our findings suggest that women with HIV older than 45 years, past or current immunosuppressed or current smokers could be candidates for intensified cancer screening and prevention. Funding: The Highly Active Antiretroviral Therapy Oversight Committee, The CHU St Pierre Brussels HIV Cohort, The Austrian HIV Cohort Study, The Australian HIV Observational Database, The AIDS Therapy Evaluation in the Netherlands national observational HIV cohort, The Brighton HIV Cohort, The National Croatian HIV Cohort, The EuroSIDA cohort, The Frankfurt HIV Cohort Study, The Georgian National AIDS Health Information System, The Nice HIV Cohort, The Isabel Foundation, The Modena HIV Cohort, The PISCIS Cohort Study, The Swiss HIV Cohort Study, The Swedish InfCare HIV Cohort, The Royal Free HIV Cohort Study, The San Raffaele Scientific Institute, The University Hospital Bonn HIV Cohort, The University of Cologne HIV Cohort, Merck Life Sciences, ViiV Healthcare, and Gilead Sciences.

M. A. Rasel, Sameem Abdul Kareem, Zhenli Kwan et al.

In dermoscopic images, which allow visualization of surface skin structures not visible to the naked eye, lesion shape offers vital insights into skin diseases. In clinically practiced methods, asymmetric lesion shape is one of the criteria for diagnosing melanoma. Initially, we labeled data for a non-annotated dataset with symmetrical information based on clinical assessments. Subsequently, we propose a supporting technique, a supervised learning image processing algorithm, to analyze the geometrical pattern of lesion shape, aiding non-experts in understanding the criteria of an asymmetric lesion. We then utilize a pre-trained convolutional neural network (CNN) to extract shape, color, and texture features from dermoscopic images for training a multiclass support vector machine (SVM) classifier, outperforming state-of-the-art methods from the literature. In the geometry-based experiment, we achieved a 99.00% detection rate for dermatological asymmetric lesions. In the CNN-based experiment, the best performance is found with 94% Kappa Score, 95% Macro F1-score, and 97% Weighted F1-score for classifying lesion shapes (Asymmetric, Half-Symmetric, and Symmetric).

Akhil Padmanabha, Arpit Agarwal, Catherine Li et al.

Three-dimensional (3-D) skin surface reconstruction offers promise for objective and quantitative dermatological assessment, but no portable, high-resolution device exists that has been validated and used for depth reconstruction across various body locations. We present a compact 3-D skin reconstruction probe based on GelSight tactile imaging with a custom elastic gel and a learning-based reconstruction algorithm for micron-level wrinkle height estimation. Our probe, integrated into a handheld probe with force sensing for consistent contact, achieves a mean absolute error of 12.55 micron on wrinkle-like test objects. In a study with 15 participants without skin disorders, we provide the first validated wrinkle depth metrics across multiple body regions. We further demonstrate statistically significant reductions in wrinkle height at three locations following over-the-counter moisturizer application. Our work offers a validated tool for clinical and cosmetic skin analysis, with potential applications in diagnosis, treatment monitoring, and skincare efficacy evaluation.

Nikolette Pedersen, Regitze Sydendal, Andreas Wulff et al.

Deep learning has been reported to achieve high performances in the detection of skin cancer, yet many challenges regarding the reproducibility of results and biases remain. This study is a replication (different data, same analysis) of a previous study on Alzheimer's disease detection, which studied the robustness of logistic regression (LR) and convolutional neural networks (CNN) across patient sexes. We explore sex bias in skin cancer detection, using the PAD-UFES-20 dataset with LR trained on handcrafted features reflecting dermatological guidelines (ABCDE and the 7-point checklist), and a pre-trained ResNet-50 model. We evaluate these models in alignment with the replicated study: across multiple training datasets with varied sex composition to determine their robustness. Our results show that both the LR and the CNN were robust to the sex distribution, but the results also revealed that the CNN had a significantly higher accuracy (ACC) and area under the receiver operating characteristics (AUROC) for male patients compared to female patients. The data and relevant scripts to reproduce our results are publicly available (https://github.com/ nikodice4/Skin-cancer-detection-sex-bias).

Runhao Liu, Ziming Chen, Guangzhen Yao et al.

Skin cancer is one of the most prevalent and deadly forms of cancer worldwide, highlighting the critical importance of early detection and diagnosis in improving patient outcomes. Deep learning (DL) has shown significant promise in enhancing the accuracy and efficiency of automated skin disease diagnosis, particularly in detecting and classifying skin lesions. However, several challenges remain for DL-based skin cancer diagnosis, including complex features, image noise, intra-class variation, inter-class similarity, and data imbalance. This review synthesizes recent research and discusses innovative approaches to address these challenges, such as data augmentation, hybrid models, and feature fusion. Furthermore, the review highlights the integration of DL models into clinical workflows, offering insights into the potential of deep learning to revolutionize skin disease diagnosis and improve clinical decision-making. This review uniquely integrates a PRISMA-based methodology with a challenge-oriented taxonomy, providing a systematic and transparent synthesis of recent deep learning advances for skin disease diagnosis. It further highlights emerging directions such as hybrid CNN-Transformer architectures and uncertainty-aware models, emphasizing its contribution to future dermatological AI research.

Serra Aksoy

Attribution methods explain neural network predictions by identifying influential input features, but their evaluation suffers from threshold selection bias that can reverse method rankings and undermine conclusions. Current protocols binarize attribution maps at single thresholds, where threshold choice alone can alter rankings by over 200 percentage points. We address this flaw with a threshold-free framework that computes Area Under the Curve for Intersection over Union (AUC-IoU), capturing attribution quality across the full threshold spectrum. Evaluating seven attribution methods on dermatological imaging, we show single-threshold metrics yield contradictory results, while threshold-free evaluation provides reliable differentiation. XRAI achieves 31% improvement over LIME and 204% over vanilla Integrated Gradients, with size-stratified analysis revealing performance variations up to 269% across lesion scales. These findings establish methodological standards that eliminate evaluation artifacts and enable evidence-based method selection. The threshold-free framework provides both theoretical insight into attribution behavior and practical guidance for robust comparison in medical imaging and beyond.

Shaoyu Pei, Renxiong Wu, Hao Zheng et al.

Skin, the primary regulator of heat exchange, relies on sweat glands for thermoregulation. Alterations in sweat gland morphology play a crucial role in various pathological conditions and clinical diagnoses. Current methods for observing sweat gland morphology are limited by their two-dimensional, in vitro, and destructive nature, underscoring the urgent need for real-time, non-invasive, quantifiable technologies. We proposed a novel three-dimensional (3D) transformer-based multi-object segmentation framework, integrating a sliding window approach, joint spatial-channel attention mechanism, and architectural heterogeneity between shallow and deep layers. Our proposed network enables precise 3D sweat gland segmentation from skin volume data captured by optical coherence tomography (OCT). For the first time, subtle variations of sweat gland 3D morphology in response to temperature changes, have been visualized and quantified. Our approach establishes a benchmark for normal sweat gland morphology and provides a real-time, non-invasive tool for quantifying 3D structural parameters. This enables the study of individual variability and pathological changes in sweat gland structure, advancing dermatological research and clinical applications, including thermoregulation and bromhidrosis treatment.

Kuniko Paxton, Zeinab Dehghani, Koorosh Aslansefat et al.

Skin color has historically been a focal point of discrimination, yet fairness research in machine learning for medical imaging often relies on coarse subgroup categories, overlooking individual-level variations. Such group-based approaches risk obscuring biases faced by outliers within subgroups. This study introduces a distribution-based framework for evaluating and mitigating individual fairness in skin lesion classification. We treat skin tone as a continuous attribute rather than a categorical label, and employ kernel density estimation (KDE) to model its distribution. We further compare twelve statistical distance metrics to quantify disparities between skin tone distributions and propose a distance-based reweighting (DRW) loss function to correct underrepresentation in minority tones. Experiments across CNN and Transformer models demonstrate: (i) the limitations of categorical reweighting in capturing individual-level disparities, and (ii) the superior performance of distribution-based reweighting, particularly with Fidelity Similarity (FS), Wasserstein Distance (WD), Hellinger Metric (HM), and Harmonic Mean Similarity (HS). These findings establish a robust methodology for advancing fairness at individual level in dermatological AI systems, and highlight broader implications for sensitive continuous attributes in medical image analysis.

Philipp Arnold, Fanni Annamária Boros, Jochen Mattner et al.

ABSTRACT Extracellular vesicles (EVs) have gained increasing attention in recent years due to their pivotal role in both health and disease. Emerging from both eukaryotic and prokaryotic cells, EVs serve as essential mediators of intercellular communication, exceeding the simplistic interactions observed with individual molecules. In this comprehensive review, we will focus on both Bacterial Extracellular Vesicles (BEV) and on Host derived Extracellular Vesicles (HEV) and highlight mechanistic principles, as well as their transformation into diagnostic and therapeutic tools. We will start with a short introduction into the biogenesis and principal properties of BEV and HEV. We will then focus on the composition of BEV and introduce OMICs‐based studies that helped to unravel their complex constitution. As both BEV and HEV interact with different epithelial and endothelial barriers and shape their properties, we will highlight mechanistic principles for both EV types. Starting from the intestinal system, where we will look at BEV and how these BEV overcome the intestinal barrier to change distant organs and the patient's immune system. We will then visit other endothelial and epithelial sites of the human body and summarize how HEV shapes these barriers and how HEV can overcome these barriers. We will then turn towards diagnostic and therapeutic approaches. As both BEV and HEV are currently suggested as diagnostic markers and are being investigated as potential therapeutic agents. Lastly, we will discuss current challenges and provide an outlook on the future in the field. This review seeks to raise awareness for both bacterial and host‐derived EVs, highlighting that they present two sides of the same coin.

Rohan Reddy Mekala, Frederik Pahde, Simon Baur et al.

In the realm of dermatological diagnoses, where the analysis of dermatoscopic and microscopic skin lesion images is pivotal for the accurate and early detection of various medical conditions, the costs associated with creating diverse and high-quality annotated datasets have hampered the accuracy and generalizability of machine learning models. We propose an innovative unsupervised augmentation solution that harnesses Generative Adversarial Network (GAN) based models and associated techniques over their latent space to generate controlled semiautomatically-discovered semantic variations in dermatoscopic images. We created synthetic images to incorporate the semantic variations and augmented the training data with these images. With this approach, we were able to increase the performance of machine learning models and set a new benchmark amongst non-ensemble based models in skin lesion classification on the HAM10000 dataset; and used the observed analytics and generated models for detailed studies on model explainability, affirming the effectiveness of our solution.

Galib Muhammad Shahriar Himel, Md. Masudul Islam, Kh Abdullah Al-Aff et al.

Skin cancer is a global health concern, necessitating early and accurate diagnosis for improved patient outcomes. This study introduces a groundbreaking approach to skin cancer classification, employing the Vision Transformer, a state-of-the-art deep learning architecture renowned for its success in diverse image analysis tasks. Utilizing the HAM10000 dataset of 10,015 meticulously annotated skin lesion images, the model undergoes preprocessing for enhanced robustness. The Vision Transformer, adapted to the skin cancer classification task, leverages the self-attention mechanism to capture intricate spatial dependencies, achieving superior performance over traditional deep learning architectures. Segment Anything Model aids in precise segmentation of cancerous areas, attaining high IOU and Dice Coefficient. Extensive experiments highlight the model's supremacy, particularly the Google-based ViT patch-32 variant, which achieves 96.15% accuracy and showcases potential as an effective tool for dermatologists in skin cancer diagnosis, contributing to advancements in dermatological practices.

Tariq M Khan, Dawn Lin, Shahzaib Iqbal et al.

Incorporating modern computer vision techniques into clinical protocols shows promise in improving skin lesion segmentation. The U-Net architecture has been a key model in this area, iteratively improved to address challenges arising from the heterogeneity of dermatologic images due to varying clinical settings, lighting, patient attributes, and hair density. To further improve skin lesion segmentation, we developed TAFM-Net, an innovative model leveraging self-adaptive transformer attention (TA) coupled with focal modulation (FM). Our model integrates an EfficientNetV2B1 encoder, which employs TA to enhance spatial and channel-related saliency, while a densely connected decoder integrates FM within skip connections, enhancing feature emphasis, segmentation performance, and interpretability crucial for medical image analysis. A novel dynamic loss function amalgamates region and boundary information, guiding effective model training. Our model achieves competitive performance, with Jaccard coefficients of 93.64\%, 86.88\% and 92.88\% in the ISIC2016, ISIC2017 and ISIC2018 datasets, respectively, demonstrating its potential in real-world scenarios.

Jayanth Mohan, Arrun Sivasubramanian, V Sowmya et al.

Skin diseases affect over a third of the global population, yet their impact is often underestimated. Automating skin disease classification to assist doctors with their prognosis might be difficult. Nevertheless, due to efficient feature extraction pipelines, deep learning techniques have shown much promise for various tasks, including dermatological disease identification. This study uses a skin disease dataset with 31 classes and compares it with all versions of Vision Transformers, Swin Transformers and DivoV2. The analysis is also extended to compare with benchmark convolution-based architecture presented in the literature. Transfer learning with ImageNet1k weights on the skin disease dataset contributes to a high test accuracy of 96.48\% and an F1-Score of 0.9727 using DinoV2, which is almost a 10\% improvement over this data's current benchmark results. The performance of DinoV2 was also compared for the HAM10000 and Dermnet datasets to test the model's robustness, and the trained model overcomes the benchmark results by a slight margin in test accuracy and in F1-Score on the 23 and 7 class datasets. The results are substantiated using explainable AI frameworks like GradCAM and SHAP, which provide precise image locations to map the disease, assisting dermatologists in early detection, prompt prognosis, and treatment.

Jirarat Songsri, Moragot Chatatikun, Sueptrakool Wisessombat et al.

Background: Burkholderia pseudomallei, a Gram-negative pathogen, causes melioidosis. Although various clinical laboratory identification methods exist, culture-based techniques lack comprehensive evaluation. Thus, this systematic review and meta-analysis aimed to assess the diagnostic accuracy of culture-based automation and non-automation methods. Methods: Data were collected via PubMed/MEDLINE, EMBASE, and Scopus using specific search strategies. Selected studies underwent bias assessment using QUADAS-2. Sensitivity and specificity were computed, generating pooled estimates. Heterogeneity was assessed using I2 statistics. Results: The review encompassed 20 studies with 2988 B. pseudomallei samples and 753 non-B. pseudomallei samples. Automation-based methods, particularly with updating databases, exhibited high pooled sensitivity (82.79%; 95% CI 64.44–95.85%) and specificity (99.94%; 95% CI 98.93–100.00%). Subgroup analysis highlighted superior sensitivity for updating-database automation (96.42%, 95% CI 90.01–99.87%) compared to non-updating (3.31%, 95% CI 0.00–10.28%), while specificity remained high at 99.94% (95% CI 98.93–100%). Non-automation methods displayed varying sensitivity and specificity. In-house latex agglutination demonstrated the highest sensitivity (100%; 95% CI 98.49–100%), followed by commercial latex agglutination (99.24%; 95% CI 96.64–100%). However, API 20E had the lowest sensitivity (19.42%; 95% CI 12.94–28.10%). Overall, non-automation tools showed sensitivity of 88.34% (95% CI 77.30–96.25%) and specificity of 90.76% (95% CI 78.45–98.57%). Conclusion: The study underscores automation's crucial role in accurately identifying B. pseudomallei, supporting evidence-based melioidosis management decisions. Automation technologies, especially those with updating databases, provide reliable and efficient identification.

Afshin Bozorgpour, Yousef Sadegheih, Amirhossein Kazerouni et al.

Skin lesion segmentation plays a critical role in the early detection and accurate diagnosis of dermatological conditions. Denoising Diffusion Probabilistic Models (DDPMs) have recently gained attention for their exceptional image-generation capabilities. Building on these advancements, we propose DermoSegDiff, a novel framework for skin lesion segmentation that incorporates boundary information during the learning process. Our approach introduces a novel loss function that prioritizes the boundaries during training, gradually reducing the significance of other regions. We also introduce a novel U-Net-based denoising network that proficiently integrates noise and semantic information inside the network. Experimental results on multiple skin segmentation datasets demonstrate the superiority of DermoSegDiff over existing CNN, transformer, and diffusion-based approaches, showcasing its effectiveness and generalization in various scenarios. The implementation is publicly accessible on \href{https://github.com/mindflow-institue/dermosegdiff}{GitHub}

Christoph F. Kurz, Adriana N. König

Objective: To determine whether machine learning methods can generate useful potion recipes for research and teaching at Hogwarts School of Witchcraft and Wizardry. Design: Using deep neural networks to classify generated recipes into a standard drug classification system. Setting: Hogwarts School of Witchcraft and Wizardry. Data sources: 72 potion recipes from the Hogwarts curriculum, extracted from the Harry Potter Wiki. Results: Most generated recipes fall into the categories of psychoanaleptics and dermatologicals. The number of recipes predicted for each category reflected the number of training recipes. Predicted probabilities were often above 90% but some recipes were classified into 2 or more categories with similar probabilities which complicates anticipating the predicted effects. Conclusions: Machine learning powered methods are able to generate potentially useful potion recipes for teaching and research at Hogwarts. This corresponds to similar efforts in the non-magical world where such methods have been applied to identify potentially effective drug combinations.

Fabian Gröger, Simone Lionetti, Philippe Gottfrois et al.

Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance. In this paper, we revisit the task of data cleaning and formalize it as either a ranking problem, which significantly reduces human inspection effort, or a scoring problem, which allows for automated decisions based on score distributions. We find that a specific combination of context-aware self-supervised representation learning and distance-based indicators is effective in finding issues without annotation biases. This methodology, which we call SelfClean, surpasses state-of-the-art performance in detecting off-topic images, near duplicates, and label errors within widely-used image datasets, such as ImageNet-1k, Food-101N, and STL-10, both for synthetic issues and real contamination. We apply the detailed method to multiple image benchmarks, identify up to 16% of issues, and confirm an improvement in evaluation reliability upon cleaning. The official implementation can be found at: https://github.com/Digital-Dermatology/SelfClean.

María Agustina Ricci Lara, Candelaria Mosquera, Enzo Ferrante et al.

In recent years the development of artificial intelligence (AI) systems for automated medical image analysis has gained enormous momentum. At the same time, a large body of work has shown that AI systems can systematically and unfairly discriminate against certain populations in various application scenarios. These two facts have motivated the emergence of algorithmic fairness studies in this field. Most research on healthcare algorithmic fairness to date has focused on the assessment of biases in terms of classical discrimination metrics such as AUC and accuracy. Potential biases in terms of model calibration, however, have only recently begun to be evaluated. This is especially important when working with clinical decision support systems, as predictive uncertainty is key for health professionals to optimally evaluate and combine multiple sources of information. In this work we study discrimination and calibration biases in models trained for automatic detection of malignant dermatological conditions from skin lesions images. Importantly, we show how several typically employed calibration metrics are systematically biased with respect to sample sizes, and how this can lead to erroneous fairness analysis if not taken into consideration. This is of particular relevance to fairness studies, where data imbalance results in drastic sample size differences between demographic sub-groups, which, if not taken into account, can act as confounders.

Xia QIN, Guiyan DENG, Xiangui CHENG et al.

A case of atypical genital herpes in a child is reported. A 2-year-old girl presented with blisters sized from rice to green bean and some erosion on the vulva, bilateral medial femur and perianal area for 3 days. Some blisters appeared umbilicated with thick wall, clear fluid and erosion, but without lymphadenopathy. Herpes simplex virus Ⅱ-DNA and serum HSV-Ⅱ IgM were positive. A diagnosis of genital herpes was made. Lesions were improved after one week of antiviral therapy. No recurrence was observed during 1-year follow-up.