Hasil untuk "Dermatology"

M. Basra, M. Salek, L. Camilleri et al.

Lijun Liu, Linwei Chen, Zhishou Zhang et al.

General-purpose Large Vision-Language Models (LVLMs), despite their massive scale, often falter in dermatology due to "diffuse attention" - the inability to disentangle subtle pathological lesions from background noise. In this paper, we challenge the assumption that parameter scaling is the only path to medical precision. We introduce SkinFlow, a framework that treats diagnosis as an optimization of visual information transmission efficiency. Our approach utilizes a Virtual-Width Dynamic Vision Encoder (DVE) to "unfold" complex pathological manifolds without physical parameter expansion, coupled with a two-stage Reinforcement Learning strategy. This strategy sequentially aligns explicit medical descriptions (Stage I) and reconstructs implicit diagnostic textures (Stage II) within a constrained semantic space. Furthermore, we propose a clinically grounded evaluation protocol that prioritizes diagnostic safety and hierarchical relevance over rigid label matching. Empirical results are compelling: our 7B model establishes a new state-of-the-art on the Fitzpatrick17k benchmark, achieving a +12.06% gain in Top-1 accuracy and a +28.57% boost in Top-6 accuracy over the massive general-purpose models (e.g., Qwen3VL-235B and GPT-5.2). These findings demonstrate that optimizing geometric capacity and information flow yields superior diagnostic reasoning compared to raw parameter scaling.

Stathis Galanakis, Alexandros Koliousis, Stefanos Zafeiriou

Despite recent advances in deep generative modeling, skin lesion classification systems remain constrained by the limited availability of large, diverse, and well-annotated clinical datasets, resulting in class imbalance between benign and malignant lesions and consequently reduced generalization performance. We introduce DermaFlux, a rectified flow-based text-to-image generative framework that synthesizes clinically grounded skin lesion images from natural language descriptions of dermatological attributes. Built upon Flux.1, DermaFlux is fine-tuned using parameter-efficient Low-Rank Adaptation (LoRA) on a large curated collection of publicly available clinical image datasets. We construct image-text pairs using synthetic textual captions generated by Llama 3.2, following established dermatological criteria including lesion asymmetry, border irregularity, and color variation. Extensive experiments demonstrate that DermaFlux generates diverse and clinically meaningful dermatology images that improve binary classification performance by up to 6% when augmenting small real-world datasets, and by up to 9% when classifiers are trained on DermaFlux-generated synthetic images rather than diffusion-based synthetic images. Our ImageNet-pretrained ViT fine-tuned with only 2,500 real images and 4,375 DermaFlux-generated samples achieves 78.04% binary classification accuracy and an AUC of 0.859, surpassing the next best dermatology model by 8%.

Rocio Mexia Diaz, Yasmin Greenway, Petru Manescu

Bias remains a major barrier to the clinical adoption of AI in dermatology, as diagnostic models underperform on darker skin tones. We present LesionTABE, a fairness-centric framework that couples adversarial debiasing with dermatology-specific foundation model embeddings. Evaluated across multiple datasets covering both malignant and inflammatory conditions, LesionTABE achieves over a 25\% improvement in fairness metrics compared to a ResNet-152 baseline, outperforming existing debiasing methods while simultaneously enhancing overall diagnostic accuracy. These results highlight the potential of foundation model debiasing as a step towards equitable clinical AI adoption.

Dipayan Sengupta, Saumya Panda

Background: Evaluating AI-generated treatment plans is a key challenge as AI expands beyond diagnostics, especially with new reasoning models. This study compares plans from human experts and two AI models (a generalist and a reasoner), assessed by both human peers and a superior AI judge. Methods: Ten dermatologists, a generalist AI (GPT-4o), and a reasoning AI (o3) generated treatment plans for five complex dermatology cases. The anonymized, normalized plans were scored in two phases: 1) by the ten human experts, and 2) by a superior AI judge (Gemini 2.5 Pro) using an identical rubric. Results: A profound 'evaluator effect' was observed. Human experts scored peer-generated plans significantly higher than AI plans (mean 7.62 vs. 7.16; p=0.0313), ranking GPT-4o 6th (mean 7.38) and the reasoning model, o3, 11th (mean 6.97). Conversely, the AI judge produced a complete inversion, scoring AI plans significantly higher than human plans (mean 7.75 vs. 6.79; p=0.0313). It ranked o3 1st (mean 8.20) and GPT-4o 2nd, placing all human experts lower. Conclusions: The perceived quality of a clinical plan is fundamentally dependent on the evaluator's nature. An advanced reasoning AI, ranked poorly by human experts, was judged as superior by a sophisticated AI, revealing a deep gap between experience-based clinical heuristics and data-driven algorithmic logic. This paradox presents a critical challenge for AI integration, suggesting the future requires synergistic, explainable human-AI systems that bridge this reasoning gap to augment clinical care.

Ian Mateos Gonzalez, Estefani Jaramilla Nava, Abraham Sánchez Morales et al.

The identification of dermatological disease is an important problem in Mexico according with different studies. Several works in literature use the datasets of different repositories without applying a study of the data behavior, especially in medical images domain. In this work, we propose a methodology to preprocess dermaMNIST dataset in order to improve its quality for the classification stage, where we use lightweight convolutional neural networks. In our results, we reduce the number of instances for the neural network training obtaining a similar performance of models as ResNet.

Iván Matas, Carmen Serrano, Miguel Nogales et al.

Deep learning has transformed computer vision but relies heavily on large labeled datasets and computational resources. Transfer learning, particularly fine-tuning pretrained models, offers a practical alternative; however, models pretrained on natural image datasets such as ImageNet may fail to capture domain-specific characteristics in medical imaging. This study introduces an unsupervised learning framework that extracts high-value dermatological features instead of relying solely on ImageNet-based pretraining. We employ a Variational Autoencoder (VAE) trained from scratch on a proprietary dermatological dataset, allowing the model to learn a structured and clinically relevant latent space. This self-supervised feature extractor is then compared to an ImageNet-pretrained backbone under identical classification conditions, highlighting the trade-offs between general-purpose and domain-specific pretraining. Our results reveal distinct learning patterns. The self-supervised model achieves a final validation loss of 0.110 (-33.33%), while the ImageNet-pretrained model stagnates at 0.100 (-16.67%), indicating overfitting. Accuracy trends confirm this: the self-supervised model improves from 45% to 65% (+44.44%) with a near-zero overfitting gap, whereas the ImageNet-pretrained model reaches 87% (+50.00%) but plateaus at 75% (+19.05%), with its overfitting gap increasing to +0.060. These findings suggest that while ImageNet pretraining accelerates convergence, it also amplifies overfitting on non-clinically relevant features. In contrast, self-supervised learning achieves steady improvements, stronger generalization, and superior adaptability, underscoring the importance of domain-specific feature extraction in medical imaging.

Satya Narayana Panda, Vaishnavi Kukkala, Spandana Iyer

Dermatological conditions affect 1.9 billion people globally, yet accurate diagnosis remains challenging due to limited specialist availability and complex clinical presentations. Family history significantly influences skin disease susceptibility and treatment responses, but is often underutilized in diagnostic processes. This research addresses the critical question: How can AI-powered systems integrate family history data with clinical imaging to enhance dermatological diagnosis while supporting clinical trial validation and real-world implementation? We developed a comprehensive multi-modal AI framework that combines deep learning-based image analysis with structured clinical data, including detailed family history patterns. Our approach employs interpretable convolutional neural networks integrated with clinical decision trees that incorporate hereditary risk factors. The methodology includes prospective clinical trials across diverse healthcare settings to validate AI-assisted diagnosis against traditional clinical assessment. In this work, validation was conducted with healthcare professionals to assess AI-assisted outputs against clinical expectations; prospective clinical trials across diverse healthcare settings are proposed as future work. The integrated AI system demonstrates enhanced diagnostic accuracy when family history data is incorporated, particularly for hereditary skin conditions such as melanoma, psoriasis, and atopic dermatitis. Expert feedback indicates potential for improved early detection and more personalized recommendations; formal clinical trials are planned. The framework is designed for integration into clinical workflows while maintaining interpretability through explainable AI mechanisms.

Asif Newaz, Masum Mushfiq Ishti, A Z M Ashraful Azam et al.

Skin diseases are among the most prevalent health concerns worldwide, yet conventional diagnostic methods are often costly, complex, and unavailable in low-resource settings. Automated classification using deep learning has emerged as a promising alternative, but existing studies are mostly limited to dermoscopic datasets and a narrow range of disease classes. In this work, we curate a large dataset of over 50 skin disease categories captured with mobile devices, making it more representative of real-world conditions. We evaluate multiple convolutional neural networks and Transformer-based architectures, demonstrating that Transformer models, particularly the Swin Transformer, achieve superior performance by effectively capturing global contextual features. To enhance interpretability, we incorporate Gradient-weighted Class Activation Mapping (Grad-CAM), which highlights clinically relevant regions and provides transparency in model predictions. Our results underscore the potential of Transformer-based approaches for mobile-acquired skin lesion classification, paving the way toward accessible AI-assisted dermatological screening and early diagnosis in resource-limited environments.

Ishrat Binti Ismail, Yasmeen Jabeen Bhat, Mohd Shurjeel ul Islam

Introduction Vitiligo is a common disorder of depigmentation caused by the progressive destruction of melanocytes that affects the skin, hair, and mucous membranes, clinically presenting as depigmented macules and leukotrichia. This condition, affecting millions of people worldwide, has a significant psychosocial burden on patients’ quality of life, particularly in relation to skin colour. The etiopathogenesis of this disorder is obscure, but multiple factors contribute to the loss of melanocytes in the skin, like oxidative stress, inflammation, genetics, and autoimmunity. The treatment of vitiligo has been challenging over the past years, but recent developments in understanding the etiopathogenesis of the disease have paved the way for the development of more effective and promising therapeutic treatment options. Objective The aim of this review was to provide an overview of the underlying mechanisms and highlight the latest advances in the treatment of vitiligo. Methodology This review was performed according to PRISMA (Preferred Reporting Items for Systematic Reviews and Metanalyses) guidelines. A comprehensive search of the literature was carried out through the PubMed electronic database from inception to 31 December 2023 using the following search terms “vitiligo” AND “JAK inhibitors”, “vitiligo” AND “prostaglandin”, “vitiligo” AND “afamelanotide”, “vitiligo” AND “antioxidants”, “vitiligo” AND “vitamin D3”, “vitiligo AND “statins”, “vitiligo” AND “TNF-alpha”, “vitiligo” AND “interleukin”, “vitiligo” AND “light therapy”. Two independent reviewers screened titles, abstracts, and full texts to select papers dealing with vitiligo and its treatment. Conclusion The advent of treatment modalities like Janus kinase inhibitors, prostaglandin analogues, antioxidants, TNF-α inhibitors, targeted phototherapy, and excimer lasers has revolutionized the therapeutic possibilities, offering a ray of hope to the individuals suffering from this devastating condition.  

HE Pingxiu, XIA Bixia, WU Yi et al.

[Objective] To investigate the characteristics of multiple superficial basal cell carcinoma. [Methods] The clinical data from 6 patients with multiple superficial basal cell carcinoma were retrospectively analyzed. [Results] The mean age of the patients was 71.66 years, and the median course of disease was 2 years. Patients with lesions on the exposed sites accounted for 83.33%(5/6). Skin lesions often presented as erythemas or plaques, with erosions, scabs, and ulcers on the surface. Pathological examination showed that 2 cases (33.33%) were complicated with other subtypes of BCC, and the coincidence rate of clinical and pathological diagnosis was 33.33%. [Conclusions] Multiple superficial basal cell carcinoma is more common on the head of the elderly, and skin lesions present as erythemas and plaques with erosion and crust. It can be easily misdiagnosed in clinic. The diagnosis can be confirmed by histopathological examination. A histopathologic feature of this disease is accompanied by other pathological subtypes. Correct understanding of this disease is beneficial for early diagnosis and timely treatment.

Rajeev V. Rikhye, Aaron Loh, Grace Eunhae Hong et al.

Recently, there has been great progress in the ability of artificial intelligence (AI) algorithms to classify dermatological conditions from clinical photographs. However, little is known about the robustness of these algorithms in real-world settings where several factors can lead to a loss of generalizability. Understanding and overcoming these limitations will permit the development of generalizable AI that can aid in the diagnosis of skin conditions across a variety of clinical settings. In this retrospective study, we demonstrate that differences in skin condition distribution, rather than in demographics or image capture mode are the main source of errors when an AI algorithm is evaluated on data from a previously unseen source. We demonstrate a series of steps to close this generalization gap, requiring progressively more information about the new source, ranging from the condition distribution to training data enriched for data less frequently seen during training. Our results also suggest comparable performance from end-to-end fine tuning versus fine tuning solely the classification layer on top of a frozen embedding model. Our approach can inform the adaptation of AI algorithms to new settings, based on the information and resources available.

Philippe Gottfrois, Fabian Gröger, Faly Herizo Andriambololoniaina et al.

Africa faces a huge shortage of dermatologists, with less than one per million people. This is in stark contrast to the high demand for dermatologic care, with 80% of the paediatric population suffering from largely untreated skin conditions. The integration of AI into healthcare sparks significant hope for treatment accessibility, especially through the development of AI-supported teledermatology. Current AI models are predominantly trained on white-skinned patients and do not generalize well enough to pigmented patients. The PASSION project aims to address this issue by collecting images of skin diseases in Sub-Saharan countries with the aim of open-sourcing this data. This dataset is the first of its kind, consisting of 1,653 patients for a total of 4,901 images. The images are representative of telemedicine settings and encompass the most common paediatric conditions: eczema, fungals, scabies, and impetigo. We also provide a baseline machine learning model trained on the dataset and a detailed performance analysis for the subpopulations represented in the dataset. The project website can be found at https://passionderm.github.io/.

Kavita Sultanpure, Bhairavi Shirsath, Bhakti Bhande et al.

In recent years, there has been a notable advancement in the integration of healthcare and technology, particularly evident in the field of medical image analysis. This paper introduces a pioneering approach in dermatology, presenting a robust method for the detection of hair and scalp diseases using state-of-the-art deep learning techniques. Our methodology relies on Convolutional Neural Networks (CNNs), well-known for their efficacy in image recognition, to meticulously analyze images for various dermatological conditions affecting the hair and scalp. Our proposed system represents a significant advancement in dermatological diagnostics, offering a non-invasive and highly efficient means of early detection and diagnosis. By leveraging the capabilities of CNNs, our model holds the potential to revolutionize dermatology, providing accessible and timely healthcare solutions. Furthermore, the seamless integration of our trained model into a web-based platform developed with the Django framework ensures broad accessibility and usability, democratizing advanced medical diagnostics. The integration of machine learning algorithms into web applications marks a pivotal moment in healthcare delivery, promising empowerment for both healthcare providers and patients. Through the synergy between technology and healthcare, our paper outlines the meticulous methodology, technical intricacies, and promising future prospects of our system. With a steadfast commitment to advancing healthcare frontiers, our goal is to significantly contribute to leveraging technology for improved healthcare outcomes globally. This endeavor underscores the profound impact of technological innovation in shaping the future of healthcare delivery and patient care, highlighting the transformative potential of our approach.

Ming-Chang Chiu, Yingfei Wang, Yen-Ju Kuo et al.

Skin tone as a demographic bias and inconsistent human labeling poses challenges in dermatology AI. We take another angle to investigate color contrast's impact, beyond skin tones, on malignancy detection in skin disease datasets: We hypothesize that in addition to skin tones, the color difference between the lesion area and skin also plays a role in malignancy detection performance of dermatology AI models. To study this, we first propose a robust labeling method to quantify color contrast scores of each image and validate our method by showing small labeling variations. More importantly, applying our method to \textit{the only} diverse-skin tone and pathologically-confirmed skin disease dataset DDI, yields \textbf{DDI-CoCo Dataset}, and we observe a performance gap between the high and low color difference groups. This disparity remains consistent across various state-of-the-art (SoTA) image classification models, which supports our hypothesis. Furthermore, we study the interaction between skin tone and color difference effects and suggest that color difference can be an additional reason behind model performance bias between skin tones. Our work provides a complementary angle to dermatology AI for improving skin disease detection.

Sajib Acharjee Dip, Kazi Hasan Ibn Arif, Uddip Acharjee Shuvo et al.

In the realm of dermatology, the complexity of diagnosing skin conditions manually necessitates the expertise of dermatologists. Accurate identification of various skin ailments, ranging from cancer to inflammatory diseases, is paramount. However, existing artificial intelligence (AI) models in dermatology face challenges, particularly in accurately diagnosing diseases across diverse skin tones, with a notable performance gap in darker skin. Additionally, the scarcity of publicly available, unbiased datasets hampers the development of inclusive AI diagnostic tools. To tackle the challenges in accurately predicting skin conditions across diverse skin tones, we employ a transfer-learning approach that capitalizes on the rich, transferable knowledge from various image domains. Our method integrates multiple pre-trained models from a wide range of sources, including general and specific medical images, to improve the robustness and inclusiveness of the skin condition predictions. We rigorously evaluated the effectiveness of these models using the Diverse Dermatology Images (DDI) dataset, which uniquely encompasses both underrepresented and common skin tones, making it an ideal benchmark for assessing our approach. Among all methods, Med-ViT emerged as the top performer due to its comprehensive feature representation learned from diverse image sources. To further enhance performance, we conducted domain adaptation using additional skin image datasets such as HAM10000. This adaptation significantly improved model performance across all models.

Justus Kaufmann, Maximilian Haist, Ivan-Maximiliano Kur et al.

The growth pattern of oropharyngeal squamous cell carcinomas (OPSCC) varies from compact tumor cell aggregates to diffusely infiltrating tumor cell-clusters. The influence of the growth pattern on local tumor control and survival has been studied mainly for surgically treated oral cavity carcinomas on a visual basis. In this study, we used multiplex immunofluorescence staining (mIF) to examine the antigens pan-cytokeratin, p16INK4a, Ki67, CD271, PD-L1, and CD8 in pretherapeutic biopsies from 86 OPSCC. We introduce Tumor-stroma contact ratio (TSC), a novel parameter, to quantify the relationship between tumor cells in contact with the stromal surface and the total number of epithelial tumor cells. mIF tumor cores were analyzed at the single-cell level, and tumor-stromal contact area was quantified using the R package ''Spatstat''. TSC was correlated with the visually assessed invasion pattern by two independent investigators. Furthermore, TSC was analyzed in relation to clinical parameters and patient survival data to evaluate its potential prognostic significance.Higher TSC correlated with poor response to (chemo-)radiotherapy (r = 0.3, p < 0.01), and shorter overall (OS) and progression-free (PFS) survival (median OS: 13 vs 136 months, p < 0.0001; median PFS: 5 vs 85 months, p < 0.0001). Visual categorization of growth pattern according to established criteria of tumor aggressiveness showed interobserver variability increasing with more nuanced categories (2 categories: k = 0.7, 95 %-CI: 0.55 - 0.85; 4 categories k = 0.48, 95 %-CI: 0.35 - 0.61).In conclusion, TSC is an objective and reproducible computer-based parameter to quantify tumor-stroma contact area. We demonstrate its relevance for the response of oropharyngeal carcinomas to primary (chemo-)radiotherapy.

Meng Liu, Ruimin Bai, Guanfei Zhang et al.

Abstract Skin cutaneous melanoma (SKCM) is a highly malignant form of skin cancer, known for its unfavorable prognosis and elevated mortality rate. RARRES1, a gene responsive to retinoic acid receptors, displays varied functions in various cancer types. However, the specific role and underlying mechanisms of RARRES1 in SKCM are still unclear. GSE15605 was utilized to analyze the expression of RARRES1 in SKCM. Subsequently, the TCGA and GEO databases were employed to investigate the relationships between RARRES1 and clinicopathological parameters, as well as the prognostic implications and diagnostic efficacy of RARRES1 in SKCM. GO, KEGG, and GSEA analyses were conducted to explore the potential functions of RARRES1. Furthermore, the associations between RARRES1 and immune infiltration were examined. Genomic alterations and promoter methylation levels of RARRES1 in SKCM were assessed using cBioPortal, UALCAN, and the GEO database. Finally, RARRES1 expression in SKCM was validated through immunohistochemistry, and its functional role in SKCM progression was elucidated via in vivo and in vitro experiments. We found that RARRES1 was downregulated in SKCM compared with normal tissues, and this low expression was associated with worse clinicopathological features and poor prognosis of SKCM. The diagnostic efficacy of RARRES1, as determined by ROC analysis, was 0.732. Through GO, KEGG, and GSEA enrichment analysis, we identified 30 correlated genes and pathways that were mainly enriched in the tumor immune microenvironment, proliferation, apoptosis, and autophagy. Additionally, RARRES1 expression was found to be positively related to the infiltration of various immune cells in SKCM, particularly macrophages and T helper cells, among others. Analysis of genomic alterations and promoter methylation revealed that shallow deletion and hypermethylation of the RARRES1 promoter could lead to reduced RARRES1 expression. IHC validation confirmed the downregulation of RARRES1 in SKCM. Moreover, overexpression of RARRES1 inhibited the proliferation and migration of A375 cells, promoted apoptosis, and inhibited autophagic flux. In the mouse xenograft model, RARRES1 overexpression also suppressed SKCM tumor growth. Collectively, these findings suggest that RARRES1 may function as a suppressor and could potentially serve as a prognostic biomarker and therapeutic target for SKCM.

Verónica Castellanos-Molina, Camilo Andrés Morales-Cardona

Los tumores muco-cutáneos de rápido crecimiento son motivo de preocupación para los pacientes y un reto para el dermatólogo, tanto por su impacto en la calidad de vida como por el riesgo de malignidad. A continuación, se presenta el caso de una paciente de 50 años con un tumor de rápido crecimiento localizado en el labio inferior, en quien se realizó escisión completa de la lesión.

Linda Tognetti, Alessandra Cartocci, Elvira Moscarella et al.

“Harald Kittler” was not included as an author in the original publication [...]