Hasil untuk "Dermatology"

S. Grover, R. Grewal

Jinghan Ru, Siyuan Yan, Yuguo Yin et al.

Multimodal Large Language Models (MLLMs) show promise for medical applications, yet progress in dermatology lags due to limited training data, narrow task coverage, and lack of clinically-grounded supervision that mirrors expert diagnostic workflows. We present a comprehensive framework to address these gaps. First, we introduce DermoInstruct, a large-scale morphology-anchored instruction corpus comprising 211,243 images and 772,675 trajectories across five task formats, capturing the complete diagnostic pipeline from morphological observation and clinical reasoning to final diagnosis. Second, we establish DermoBench, a rigorous benchmark evaluating 11 tasks across four clinical axes: Morphology, Diagnosis, Reasoning, and Fairness, including a challenging subset of 3,600 expert-verified open-ended instances and human performance baselines. Third, we develop DermoGPT, a dermatology reasoning MLLM trained via supervised fine-tuning followed by our Morphologically-Anchored Visual-Inference-Consistent (MAVIC) reinforcement learning objective, which enforces consistency between visual observations and diagnostic conclusions. At inference, we deploy Confidence-Consistency Test-time adaptation (CCT) for robust predictions. Experiments show DermoGPT significantly outperforms 16 representative baselines across all axes, achieving state-of-the-art performance while substantially narrowing the human-AI gap. DermoInstruct, DermoBench and DermoGPT will be made publicly available at https://github.com/mendicant04/DermoGPT upon acceptance.

Mohammad Tahmid Noor, B. M. Shahria Alam, Tasmiah Rahman Orpa et al.

Skin cancer can be life-threatening if not diagnosed early, a prevalent yet preventable disease. Globally, skin cancer is perceived among the finest prevailing cancers and millions of people are diagnosed each year. For the allotment of benign and malignant skin spots, an area of critical importance in dermatological diagnostics, the application of two prominent deep learning models, VGG16 and DenseNet201 are investigated by this paper. We evaluate these CNN architectures for their efficacy in differentiating benign from malignant skin lesions leveraging enhancements in deep learning enforced to skin cancer spotting. Our objective is to assess model accuracy and computational efficiency, offering insights into how these models could assist in early detection, diagnosis, and streamlined workflows in dermatology. We used two deep learning methods DenseNet201 and VGG16 model on a binary class dataset containing 3297 images. The best result with an accuracy of 93.79% achieved by DenseNet201. All images were resized to 224x224 by rescaling. Although both models provide excellent accuracy, there is still some room for improvement. In future using new datasets, we tend to improve our work by achieving great accuracy.

Eri Ohta, Eri Ohta, Etsuko Okada et al.

Generalized pustular psoriasis (GPP) is a rare, potentially life-threatening inflammatory disease characterized by neutrophilic pustules and systemic inflammation. We report a case of severe GPP triggered by SARS-CoV-2 infection in a 46-year-old woman with a long history of psoriasis. Eleven days after recovery from COVID-19 pneumonia, she developed widespread pustules and fever. Histopathology revealed subcorneal spongiform pustules and dermal neutrophilic infiltration consistent with GPP. Systemic corticosteroids followed by etretinate and deucravacitinib achieved complete remission. A literature review identified 11 infection- and 10 vaccine-related GPP cases. Compared with vaccine-associated cases, infection-related flares showed longer latency and higher corticosteroid use. Mechanistically, both SARS-CoV-2 infection and vaccination may be associated with IL-36 axis activation, potentially via spike protein–driven, Toll-like receptor–mediated innate immune signaling. This case highlights that distinct immune kinetics may underlie infection- and vaccine-related GPP, while supporting a putative role of IL-36–driven inflammation in COVID-19–associated disease exacerbation.

Ismam Nur Swapnil, Aranya Saha, Tanvir Ahmed Khan et al.

Vision-Language Models (VLMs) show promise in medical image analysis, yet their capacity for structured reasoning in complex domains like dermatology is often limited by data scarcity and the high computational cost of advanced training techniques. To address these challenges, we introduce DermIQ-VLM, a VLM developed through a multi-stage, resource-efficient methodology designed to emulate a dermatologist's diagnostic process. Our primary contribution is a modified version of Grouped Relative Policy Optimization (GRPO), called GRPO++, which stabilizes the powerful but data-intensive GRPO framework. Our proposed training pipeline first employs GRPO++ for reasoning-oriented disease recognition, followed by supervised fine-tuning for conversational ability. To mitigate factual errors introduced during this step, we then align the model using Direct Preference Optimization (DPO), leveraging a Knowledge Graph-based system as a scalable proxy for expert preference. A preliminary evaluation on a curated dermatological dataset demonstrates that our proposed methodology yields notable performance gains over standard fine-tuning approaches. These findings validate the potential of our pipeline as a feasible pathway for developing specialized, reliable VLMs in resource-constrained environments.

Kiran Nijjer, Ryan Bui, Derek Jiu et al.

SkinGPT-4, a large vision-language model, leverages annotated skin disease images to augment clinical workflows in underserved communities. However, its training dataset predominantly represents lighter skin tones, limiting diagnostic accuracy for darker tones. Here, we evaluated performance biases in SkinGPT-4 across skin tones on common skin diseases, including eczema, allergic-contact dermatitis, and psoriasis using the open-sourced SCIN dataset. We leveraged the SkinGPT-4 backbone to develop finetuned models for custom skin disease classification tasks and explored bias mitigation strategies. Clinical evaluation by board-certified dermatologists on six relevant skin diseases from 300 SCIN cases assessed images for diagnostic accuracy, informativity, physician utility, and patient utility. Model fairness metrics, including demographic parity and equalized odds, were calculated across skin tones. SkinGPT-4 achieved an average demographic parity of 0.10 across Fitzpatrick types, with notable differences of 0.10-0.15 between lightest and darkest tones across evaluation metrics. Model hallucinations in artifacts and anatomy occurred at a rate of 17.8. Our customized models achieved average F1, precision, and AUROC of 0.75, 0.78, and 0.78 across visually similar disease pairs. Fairness analysis showed an average demographic parity of 0.75, with a maximum disparity of 0.21 across skin tones. The best model achieved parity scores of 0.83, 0.83, 0.76, 0.89, 0.90, and 0.90 for Fitzpatrick I-VI, indicating robust fairness. Large language models such as SkinGPT-4 showed weaker performance on darker tones. Model biases exist across evaluation criteria, and hallucinations may affect diagnostic efficacy. These findings demonstrate the efficacy of training accurate, fair models using existing backbones for custom skin disease classification.

Enam Ahmed Taufik, Abdullah Khondoker, Antara Firoz Parsa et al.

Accurate skin disease classification is a critical yet challenging task due to high inter-class similarity, intra-class variability, and complex lesion textures. While deep learning-based computer-aided diagnosis (CAD) systems have shown promise in automating dermatological assessments, their performance is highly dependent on image pre-processing and model architecture. This study proposes a deep learning framework for multi-class skin disease classification, systematically evaluating three image pre-processing techniques: standard RGB, CMY color space transformation, and Contrast Limited Adaptive Histogram Equalization (CLAHE). We benchmark the performance of pre-trained convolutional neural networks (DenseNet201, Efficient-NetB5) and transformer-based models (ViT, Swin Transformer, DinoV2 Large) using accuracy and F1-score as evaluation metrics. Results show that DinoV2 with RGB pre-processing achieves the highest accuracy (up to 93%) and F1-scores across all variants. Grad-CAM visualizations applied to RGB inputs further reveal precise lesion localization, enhancing interpretability. These findings underscore the importance of effective pre-processing and model choice in building robust and explainable CAD systems for dermatology.

Thales Bezerra, Emanoel Thyago, Kelvin Cunha et al.

AI-based dermatology adoption remains limited by biased datasets, variable image quality, and limited validation. We introduce DermAI, a lightweight, smartphone-based application that enables real-time capture, annotation, and classification of skin lesions during routine consultations. Unlike prior dermoscopy-focused tools, DermAI performs on-device quality checks, and local model adaptation. The DermAI clinical dataset, encompasses a wide range of skin tones, ethinicity and source devices. In preliminary experiments, models trained on public datasets failed to generalize to our samples, while fine-tuning with local data improved performance. These results highlight the importance of standardized, diverse data collection aligned with healthcare needs and oriented to machine learning development.

Nusrat Munia, Abdullah-Al-Zubaer Imran

Skin diseases, such as skin cancer, are a significant public health issue, and early diagnosis is crucial for effective treatment. Artificial intelligence (AI) algorithms have the potential to assist in triaging benign vs malignant skin lesions and improve diagnostic accuracy. However, existing AI models for skin disease diagnosis are often developed and tested on limited and biased datasets, leading to poor performance on certain skin tones. To address this problem, we propose a novel generative model, named DermDiff, that can generate diverse and representative dermoscopic image data for skin disease diagnosis. Leveraging text prompting and multimodal image-text learning, DermDiff improves the representation of underrepresented groups (patients, diseases, etc.) in highly imbalanced datasets. Our extensive experimentation showcases the effectiveness of DermDiff in terms of high fidelity and diversity. Furthermore, downstream evaluation suggests the potential of DermDiff in mitigating racial biases for dermatology diagnosis. Our code is available at https://github.com/Munia03/DermDiff

Brigitte Dréno, Pierre Lévy, Gregory Caillet et al.

The objective of this retrospective observational study was to estimate the prevalence of actinic keratosis (AK) in individuals aged ≥ 40 years in France, to describe the characteristics of affected patients, and to describe treatments. A representative panel of 20,000 households with ≥ 1 member aged ≥ 40 years were invited to participate. Participants who reported AK lesions diagnosed by a physician were eligible. The study questionnaire collected data on demographics, lesion characteristics, Fitzpatrick phototype, diagnosis, and treatments. In total, 15,246 questionnaires (78.5%) were returned and 639 responders were eligible. The adjusted prevalence of AK was 4.03% (95% CI: 3.73–4.35). Prevalence is probably underestimated due to data collection by self-report and low awareness of AK. 177 participants (27.7%) were aged < 65 years. AK was diagnosed by a dermatologist for 521 participants (81.6%). Some 200 participants (31.3%) had no lesions at the time of the survey and 243 (37.9%) had never been treated; 312 participants (78.6%) were prescribed physical treatment, principally cryotherapy; and 125 (31.5%) were prescribed topical treatment, principally 5-fluorouracil or imiquimod. In conclusion, improving diagnosis of AK in everyday clinical practice is important to ensure that all individuals with AK are treated optimally and encouraged to take sun protection measures to prevent progression to SCC.

Arun J Kozhuppakalam, B Raghu Kiran, G. Narasimha Rao Netha et al.

Juliana Pinzon-Luna, Martha Liliana Duque, Andrés Felipe García et al.

Introducción: La rosácea es una afección cutánea inflamatoria recurrente crónica común que afecta principalmente a la parte central de la cara. Si bien no pone en peligro la vida, la rosácea se asocia con una morbilidad psicosocial significativa. Informes de personas con rosácea reportan aumento de depresión y ansiedad que pueden afectar negativamente actividades diarias de rutina. La RosaQol es una herramienta validada internacionalmente que permite medir los efectos específicos sobre la calidad de vida en los pacientes con rosácea. El objetivo del trabajo de investigación es traducir al español colombiano y validar la escala RosaQol. Materiales y métodos: Validación de escala de medición en salud. Se incluyeron 105 pacientes con diagnóstico de rosácea mayores de 18 años y se determinaron varias etapas entre ellas la selección de la escala, traducción, prueba preliminar, pruebas de validez, pruebas de confiabilidad y determinación de su utilidad. Resultados: Se realizaron 105 encuestas y se encontró que la prueba de alfa de Cronbach fue confiable, se calculó un valor de coeficiente de 0.849, el cual se consideró aceptable al estar entre 0.7 y 0.9. Conclusión: RosaQol, mostró en su traducción y validación su consistencia, correlación y confiabilidad para la población encuestada. Estos hallazgos podrían permitir el uso de esta versión para evaluar el impacto de la calidad de vida en pacientes con rosácea.

Nadia Saeed

The MEDIQA-M3G 2024 challenge necessitates novel solutions for Multilingual & Multimodal Medical Answer Generation in dermatology (wai Yim et al., 2024a). This paper addresses the limitations of traditional methods by proposing a weakly supervised learning approach for open-ended medical question-answering (QA). Our system leverages readily available MEDIQA-M3G images via a VGG16-CNN-SVM model, enabling multilingual (English, Chinese, Spanish) learning of informative skin condition representations. Using pre-trained QA models, we further bridge the gap between visual and textual information through multimodal fusion. This approach tackles complex, open-ended questions even without predefined answer choices. We empower the generation of comprehensive answers by feeding the ViT-CLIP model with multiple responses alongside images. This work advances medical QA research, paving the way for clinical decision support systems and ultimately improving healthcare delivery.

Dimitrios P. Panagoulias, Evridiki Tsoureli-Nikita, Maria Virvou et al.

The rise of Artificial Intelligence creates great promise in the field of medical discovery, diagnostics and patient management. However, the vast complexity of all medical domains require a more complex approach that combines machine learning algorithms, classifiers, segmentation algorithms and, lately, large language models. In this paper, we describe, implement and assess an Artificial Intelligence-empowered system and methodology aimed at assisting the diagnosis process of skin lesions and other skin conditions within the field of dermatology that aims to holistically address the diagnostic process in this domain. The workflow integrates large language, transformer-based vision models and sophisticated machine learning tools. This holistic approach achieves a nuanced interpretation of dermatological conditions that simulates and facilitates a dermatologist's workflow. We assess our proposed methodology through a thorough cross-model validation technique embedded in an evaluation pipeline that utilizes publicly available medical case studies of skin conditions and relevant images. To quantitatively score the system performance, advanced machine learning and natural language processing tools are employed which focus on similarity comparison and natural language inference. Additionally, we incorporate a human expert evaluation process based on a structured checklist to further validate our results. We implemented the proposed methodology in a system which achieved approximate (weighted) scores of 0.87 for both contextual understanding and diagnostic accuracy, demonstrating the efficacy of our approach in enhancing dermatological analysis. The proposed methodology is expected to prove useful in the development of next-generation tele-dermatology applications, enhancing remote consultation capabilities and access to care, especially in underserved areas.

Yiqin Luo, Tianlong Gu

With the rapid advancement of deep learning technologies, artificial intelligence has become increasingly prevalent in the research and application of dermatological disease diagnosis. However, this data-driven approach often faces issues related to decision bias. Existing fairness enhancement techniques typically come at a substantial cost to accuracy. This study aims to achieve a better trade-off between accuracy and fairness in dermatological diagnostic models. To this end, we propose a novel fair dermatological diagnosis network, named FairDD, which leverages domain incremental learning to balance the learning of different groups by being sensitive to changes in data distribution. Additionally, we incorporate the mixup data augmentation technique and supervised contrastive learning to enhance the network's robustness and generalization. Experimental validation on two dermatological datasets demonstrates that our proposed method excels in both fairness criteria and the trade-off between fairness and performance.

Abbi Ward, Jimmy Li, Julie Wang et al.

Background: Health datasets from clinical sources do not reflect the breadth and diversity of disease in the real world, impacting research, medical education, and artificial intelligence (AI) tool development. Dermatology is a suitable area to develop and test a new and scalable method to create representative health datasets. Methods: We used Google Search advertisements to invite contributions to an open access dataset of images of dermatology conditions, demographic and symptom information. With informed contributor consent, we describe and release this dataset containing 10,408 images from 5,033 contributions from internet users in the United States over 8 months starting March 2023. The dataset includes dermatologist condition labels as well as estimated Fitzpatrick Skin Type (eFST) and Monk Skin Tone (eMST) labels for the images. Results: We received a median of 22 submissions/day (IQR 14-30). Female (66.72%) and younger (52% < age 40) contributors had a higher representation in the dataset compared to the US population, and 32.6% of contributors reported a non-White racial or ethnic identity. Over 97.5% of contributions were genuine images of skin conditions. Dermatologist confidence in assigning a differential diagnosis increased with the number of available variables, and showed a weaker correlation with image sharpness (Spearman's P values <0.001 and 0.01 respectively). Most contributions were short-duration (54% with onset < 7 days ago ) and 89% were allergic, infectious, or inflammatory conditions. eFST and eMST distributions reflected the geographical origin of the dataset. The dataset is available at github.com/google-research-datasets/scin . Conclusion: Search ads are effective at crowdsourcing images of health conditions. The SCIN dataset bridges important gaps in the availability of representative images of common skin conditions.

Soham Gadgil, Mahtab Bigverdi

AI in dermatology is evolving at a rapid pace but the major limitation to training trustworthy classifiers is the scarcity of data with ground-truth concept level labels, which are meta-labels semantically meaningful to humans. Foundation models like CLIP providing zero-shot capabilities can help alleviate this challenge by leveraging vast amounts of image-caption pairs available on the internet. CLIP can be fine-tuned using domain specific image-caption pairs to improve classification performance. However, CLIP's pre-training data is not well-aligned with the medical jargon that clinicians use to perform diagnoses. The development of large language models (LLMs) in recent years has led to the possibility of leveraging the expressive nature of these models to generate rich text. Our goal is to use these models to generate caption text that aligns well with both the clinical lexicon and with the natural human language used in CLIP's pre-training data. Starting with captions used for images in PubMed articles, we extend them by passing the raw captions through an LLM fine-tuned on the field's several textbooks. We find that using captions generated by an expressive fine-tuned LLM like GPT-3.5 improves downstream zero-shot concept classification performance.

Siddharth Srikakolapu, MD, Dev R. Sahni, MD, Lauren M. Madigan, MD

Rezvan Elahifar, Mohammad Mahdi Parvizi, Hossein Fatemian et al.

Abstract Background Evidence-based medicine is defined as searching for medical information, reviewing and comparing it to each patient’s situation, and then judging the optimal decision. We aimed to measure the psychometric properties of the Evidence-Based Performance Profile (EBP2) Questionnaire among the students of health-related fields at Shiraz University of Medical Sciences. Methods This cross-sectional study was conducted in 2021. The EBP2 questionnaire, which includes 74 five-Likert-scale items, was translated into the Persian language using the forward-backward translation method. A panel of five experts approved the face, content, and structural validity of the questionnaire. The Cronbach’s alpha and McDonald’s Omega coefficients were utilized to assess the questionnaire’s internal consistency. Furthermore, both confirmatory and exploratory factor analyses were used to assess the questionnaire’s construct validity. SPSS software version 25 and LISREL software version 8.8 were used for statistical analysis. Results Overall, 339 students participated in this study. The cultural adaptability, linguistic equivalence, and content validity of the Persian version of the EBP2 questionnaire were approved by a five-member team of medical experts. In addition, the results showed excellent internal consistency of the Persian version of the EBP2 questionnaire (Cronbach’s alpha = 0.962, McDonald’s Omega (ML) = 0.963). Moreover, all domains had acceptable reliability (> 0.7), except the Practice domain which had a marginally acceptable Cronbach’s alpha coefficient equal to 0.686. Exploratory factor analysis discovered six domains for the questionnaire. Moreover, the confirmatory factor analysis demonstrated that all indices except the comparative fit index (CFI) and adjusted goodness of fit (AGFI) confirmed the validity of the EBP2 questionnaire. Conclusion The study’s findings indicate that the Persian translated of the EBP2 questionnaire exhibited satisfactory validity and reliability for assessing students’ evidence-based performance in health-related fields.

Annunziata Dattola, Nicoletta Bernardini, Francesca Svara et al.

Introduction: Psoriasis is a chronic immune-mediated disease that can be challenging to treat, especially in patients with severe disease or high body weight. Tildrakizumab is a monoclonal antibody which inhibits IL-23, approved for moderate-to-severe psoriasis with a standard 100 mg dose. A 200 mg dose may provide greater efficacy for patients over 90 kg or with high disease burden.Methods: This multicenter, prospective study evaluated the effectiveness and safety of tildrakizumab 200 mg in patients with moderate-to-severe psoriasis, focusing on those with specific challenges: body weight over 90 kg, baseline PASI ≥20, and difficult-to-treat areas. The study also compared bio-naive versus bio-experienced and male versus female patients. Adults received tildrakizumab 200 mg subcutaneously at weeks 0 and 4, then every 12 weeks.Results: Clinical improvements were assessed using PASI, DLQI, genital PASI, and NAPSI scores. After 24 weeks, the mean PASI score dropped from 14.6 to 0.4, with PASI 90 and PASI 100 scores exceeding 80% (100.0% and 80.3%, respectively). DLQI scores improved from 14.2 to 1.8, and significant improvements were seen in genital PASI and NAPSI scores. No significant adverse events occurred.Conclusions: Tildrakizumab 200 has been shown to be an effective therapeutic option, particularly for patients with high body weight, significant disease burden, and involvement of sensitive areas with no new safety signals.