Hasil untuk "Dermatology"

E. Errichetti, G. Stinco

Over the last few years, dermoscopy has been shown to be a useful tool in assisting the noninvasive diagnosis of various general dermatological disorders. In this article, we sought to provide an up-to-date practical overview on the use of dermoscopy in general dermatology by analysing the dermoscopic differential diagnosis of relatively common dermatological disorders grouped according to their clinical presentation, i.e. dermatoses presenting with erythematous-desquamative patches/plaques (plaque psoriasis, eczematous dermatitis, pityriasis rosea, mycosis fungoides and subacute cutaneous lupus erythematosus), papulosquamous/papulokeratotic dermatoses (lichen planus, pityriasis rosea, papulosquamous sarcoidosis, guttate psoriasis, pityriasis lichenoides chronica, classical pityriasis rubra pilaris, porokeratosis, lymphomatoid papulosis, papulosquamous chronic GVHD, parakeratosis variegata, Grover disease, Darier disease and BRAF-inhibitor-induced acantholytic dyskeratosis), facial inflammatory skin diseases (rosacea, seborrheic dermatitis, discoid lupus erythematosus, sarcoidosis, cutaneous leishmaniasis, lupus vulgaris, granuloma faciale and demodicidosis), acquired keratodermas (chronic hand eczema, palmar psoriasis, keratoderma due to mycosis fungoides, keratoderma resulting from pityriasis rubra pilaris, tinea manuum, palmar lichen planus and aquagenic palmar keratoderma), sclero-atrophic dermatoses (necrobiosis lipoidica, morphea and cutaneous lichen sclerosus), hypopigmented macular diseases (extragenital guttate lichen sclerosus, achromic pityriasis versicolor, guttate vitiligo, idiopathic guttate hypomelanosis, progressive macular hypomelanosis and postinflammatory hypopigmentations), hyperpigmented maculopapular diseases (pityriasis versicolor, lichen planus pigmentosus, Gougerot-Carteaud syndrome, Dowling-Degos disease, erythema ab igne, macular amyloidosis, lichen amyloidosus, friction melanosis, terra firma-forme dermatosis, urticaria pigmentosa and telangiectasia macularis eruptiva perstans), itchy papulonodular dermatoses (hypertrophic lichen planus, prurigo nodularis, nodular scabies and acquired perforating dermatosis), erythrodermas (due to psoriasis, atopic dermatitis, mycosis fungoides, pityriasis rubra pilaris and scabies), noninfectious balanitis (Zoon’s plasma cell balanitis, psoriatic balanitis, seborrheic dermatitis and non-specific balanitis) and erythroplasia of Queyrat, inflammatory cicatricial alopecias (scalp discoid lupus erythematosus, lichen planopilaris, frontal fibrosing alopecia and folliculitis decalvans), nonscarring alopecias (alopecia areata, trichotillomania, androgenetic alopecia and telogen effluvium) and scaling disorders of the scalp (tinea capitis, scalp psoriasis, seborrheic dermatitis and pityriasis amiantacea).

Zhangtianyi Chen, Yuhao Shen, Florensia Widjaja et al.

While recent advancements in Large Language Models have significantly advanced dermatological diagnosis, monolithic LLMs frequently struggle with fine-grained, large-scale multi-class diagnostic tasks and rare skin disease diagnosis owing to training data sparsity, while also lacking the interpretability and traceability essential for clinical reasoning. Although multi-agent systems can offer more transparent and explainable diagnostics, existing frameworks are primarily concentrated on Visual Question Answering and conversational tasks, and their heavy reliance on static knowledge bases restricts adaptability in complex real-world clinical settings. Here, we present SkinGPT-X, a multimodal collaborative multi-agent system for dermatological diagnosis integrated with a self-evolving dermatological memory mechanism. By simulating the diagnostic workflow of dermatologists and enabling continuous memory evolution, SkinGPT-X delivers transparent and trustworthy diagnostics for the management of complex and rare dermatological cases. To validate the robustness of SkinGPT-X, we design a three-tier comparative experiment. First, we benchmark SkinGPT-X against four state-of-the-art LLMs across four public datasets, demonstrating its state-of-the-art performance with a +9.6% accuracy improvement on DDI31 and +13% weighted F1 gain on Dermnet over the state-of-the-art model. Second, we construct a large-scale multi-class dataset covering 498 distinct dermatological categories to evaluate its fine-grained classification capabilities. Finally, we curate the rare skin disease dataset, the first benchmark to address the scarcity of clinical rare skin diseases which contains 564 clinical samples with eight rare dermatological diseases. On this dataset, SkinGPT-X achieves a +9.8% accuracy improvement, a +7.1% weighted F1 improvement, a +10% Cohen's Kappa improvement.

Siyuan Yan, Xieji Li, Dan Mo et al.

Medical foundation models have shown promise in controlled benchmarks, yet widespread deployment remains hindered by reliance on task-specific fine-tuning. Here, we introduce DermFM-Zero, a dermatology vision-language foundation model trained via masked latent modelling and contrastive learning on over 4 million multimodal data points. We evaluated DermFM-Zero across 20 benchmarks spanning zero-shot diagnosis and multimodal retrieval, achieving state-of-the-art performance without task-specific adaptation. We further evaluated its zero-shot capabilities in three multinational reader studies involving over 1,100 clinicians. In primary care settings, AI assistance enabled general practitioners to nearly double their differential diagnostic accuracy across 98 skin conditions. In specialist settings, the model significantly outperformed board-certified dermatologists in multimodal skin cancer assessment. In collaborative workflows, AI assistance enabled non-experts to surpass unassisted experts while improving management appropriateness. Finally, we show that DermFM-Zero's latent representations are interpretable: sparse autoencoders unsupervisedly disentangle clinically meaningful concepts that outperform predefined-vocabulary approaches and enable targeted suppression of artifact-induced biases, enhancing robustness without retraining. These findings demonstrate that a foundation model can provide effective, safe, and transparent zero-shot clinical decision support.

Partha Shah, Durva Sankhe, Maariyah Rashid et al.

Artificial intelligence (AI) models to automatically classify skin lesions from dermatology images have shown promising performance but also susceptibility to bias by skin tone. The most common way of representing skin tone information is the Fitzpatrick Skin Tone (FST) scale. The FST scale has been criticised for having greater granularity in its skin tone categories for lighter-skinned subjects. This paper conducts an investigation of the impact (on performance and bias) on AI classification models of granularity in the FST scale. By training multiple AI models to classify benign vs. malignant lesions using FST-specific data of differing granularity, we show that: (i) when training models using FST-specific data based on three groups (FST 1/2, 3/4 and 5/6), performance is generally better for models trained on FST-specific data compared to a general model trained on FST-balanced data; (ii) reducing the granularity of FST scale information (from 1/2 and 3/4 to 1/2/3/4) can have a detrimental effect on performance. Our results highlight the importance of the granularity of FST groups when training lesion classification models. Given the question marks over possible human biases in the choice of categories in the FST scale, this paper provides evidence for a move away from the FST scale in fair AI research and a transition to an alternative scale that better represents the diversity of human skin tones.

Francisco Filho, Emanoel Santos, Rodrigo Mota et al.

AI algorithms have become valuable in aiding professionals in healthcare. The increasing confidence obtained by these models is helpful in critical decision demands. In clinical dermatology, classification models can detect malignant lesions on patients' skin using only RGB images as input. However, most learning-based methods employ data acquired from dermoscopic datasets on training, which are large and validated by a gold standard. Clinical models aim to deal with classification on users' smartphone cameras that do not contain the corresponding resolution provided by dermoscopy. Also, clinical applications bring new challenges. It can contain captures from uncontrolled environments, skin tone variations, viewpoint changes, noises in data and labels, and unbalanced classes. A possible alternative would be to use transfer learning to deal with the clinical images. However, as the number of samples is low, it can cause degradations on the model's performance; the source distribution used in training differs from the test set. This work aims to evaluate the gap between dermoscopic and clinical samples and understand how the dataset variations impact training. It assesses the main differences between distributions that disturb the model's prediction. Finally, from experiments on different architectures, we argue how to combine the data from divergent distributions, decreasing the impact on the model's final accuracy.

Yuhao Shen, Zhangtianyi Chen, Yuanhao He et al.

The clinical translation of dermatological AI is hindered by opaque reasoning and systematic performance disparities across skin tones. Here we present SkinGPT-R1, a multimodal large language model that integrates chain-of-thought diagnostic reasoning with a fairness-aware mixture-of-experts architecture for interpretable and equitable skin disease diagnosis. Through parameter-efficient adaptation of a frozen reasoning backbone, SkinGPT-R1 generates structured diagnostic reports comprising visual findings, differential reasoning, and final diagnosis. Across seven external datasets spanning diverse pathologies and imaging conditions, SkinGPT-R1 achieves state-of-the-art accuracy on six benchmarks, including 82.50\% on a challenging 40-class long-tail classification task (+19.30\% over leading baselines). Blinded evaluation by five board-certified dermatologists on 1,000 phenotypically balanced cases yields a mean score of 3.6 out of 5, with the highest ratings in safety (3.8) and reasoning coherence (3.6), indicating that the generated rationales are clinically safe, logically grounded, and suitable for supporting diagnostic decision-making. Critically, SkinGPT-R1 mitigates algorithmic bias across the full Fitzpatrick spectrum, achieving a robust worst-group performance of 41.40\% on the Fitz17k benchmark and a five-fold relative improvement in lower-bound accuracy on the DDI dataset compared to standard multimodal baselines. These results establish a framework for trustworthy, fair, and explainable AI-assisted dermatological diagnosis.

Matthew Lynch, Sophie Manoy, Peter D. Sly et al.

Summary: Background: Ataxia-telangiectasia (A-T) is a rare multisystem disease characterised by neurodegenerative cerebellar ataxia, lung disease, immune deficiency, high cancer risk, and mitochondrial dysfunction. A-T cells demonstrate defective endoplasmic reticulum-mitochondrial connectivity disrupting calcium homoeostasis and mitochondrial fusion, which are corrected in vitro by the triheptanoin metabolite, heptanoate. Methods: We performed a Phase 2a/b trial of triheptanoin with a three-arm placebo-controlled dose-escalation design. Doses escalated at 2-month intervals for 12 months in the sequence 0%, 10%, 20%, 35% of calculated caloric intake. The primary outcome was cell death in respiratory epithelial cells. Key secondary outcomes included scales for assessment and rating of ataxia (SARA), international cooperative ataxia rating scale (ICARS), speech and swallowing function, and novel biomarker discovery. Findings: 31 participants with A-T were enrolled aged from 4 to 37 years (median 16-years). For the maximum dose vs. placebo or no dose, significant improvements was observed for the primary outcome percent nasal cell death (mean difference (MD) = −9.7%, 95% confidence interval (CI) −16.0, 4.6). The SARA subscale kinetic function improved (MD = −5.8, 95% CI −10.4, −1.2), as did ICARS subscales gait (MD = −0.5, 95% CI −0.9, −0.1) and fine motor disturbance (MD = −2.7, 95% CI −4.3, −1.1). Speech intelligibility (MD = −12.8, 95% CI −21.2, −4.3) and swallowing safety (−0.9, 95% CI −1.6, −0.3) improved. Adverse events including abdominal pain, nausea, vomiting, and diarrhoea, requiring dose capping at 20%, were observed in 12 (38%) participants. Interpretation: Improvements in mitochondrial function in A-T cells in vivo in patients occurred after triheptanoin. The biomarkers neurofilament light chain and interferon signature stimulated gene scores may allow for monitoring of disease progression and treatment response. Funding: Funded by Medical Researcher Futures Fund Australia (GA89314), The University of Queensland, Wesley Research Institute, and BrAshA-T.

Siyuan Yan, Zhen Yu, Clare Primiero et al.

Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities. While current deep learning models excel at specific tasks like skin cancer diagnosis from dermoscopic images, they struggle to meet the complex, multimodal requirements of clinical practice. Here, we introduce PanDerm, a multimodal dermatology foundation model pretrained through self-supervised learning on over 2 million real-world skin disease images from 11 clinical institutions across 4 imaging modalities. We evaluated PanDerm on 28 diverse benchmarks, including skin cancer screening, risk stratification, differential diagnosis of common and rare skin conditions, lesion segmentation, longitudinal monitoring, and metastasis prediction and prognosis. PanDerm achieved state-of-the-art performance across all evaluated tasks, often outperforming existing models when using only 10% of labeled data. We conducted three reader studies to assess PanDerm's potential clinical utility. PanDerm outperformed clinicians by 10.2% in early-stage melanoma detection through longitudinal analysis, improved clinicians' skin cancer diagnostic accuracy by 11% on dermoscopy images, and enhanced non-dermatologist healthcare providers' differential diagnosis by 16.5% across 128 skin conditions on clinical photographs. These results demonstrate PanDerm's potential to improve patient care across diverse clinical scenarios and serve as a model for developing multimodal foundation models in other medical specialties, potentially accelerating the integration of AI support in healthcare. The code can be found at https://github.com/SiyuanYan1/PanDerm.

Kumar Abhishek, Aditi Jain, Ghassan Hamarneh

The remarkable progress of deep learning in dermatological tasks has brought us closer to achieving diagnostic accuracies comparable to those of human experts. However, while large datasets play a crucial role in the development of reliable deep neural network models, the quality of data therein and their correct usage are of paramount importance. Several factors can impact data quality, such as the presence of duplicates, data leakage across train-test partitions, mislabeled images, and the absence of a well-defined test partition. In this paper, we conduct meticulous analyses of three popular dermatological image datasets: DermaMNIST, its source HAM10000, and Fitzpatrick17k, uncovering these data quality issues, measure the effects of these problems on the benchmark results, and propose corrections to the datasets. Besides ensuring the reproducibility of our analysis, by making our analysis pipeline and the accompanying code publicly available, we aim to encourage similar explorations and to facilitate the identification and addressing of potential data quality issues in other large datasets.

Ching-Hao Chiu, Yu-Jen Chen, Yawen Wu et al.

In medical image diagnosis, fairness has become increasingly crucial. Without bias mitigation, deploying unfair AI would harm the interests of the underprivileged population and potentially tear society apart. Recent research addresses prediction biases in deep learning models concerning demographic groups (e.g., gender, age, and race) by utilizing demographic (sensitive attribute) information during training. However, many sensitive attributes naturally exist in dermatological disease images. If the trained model only targets fairness for a specific attribute, it remains unfair for other attributes. Moreover, training a model that can accommodate multiple sensitive attributes is impractical due to privacy concerns. To overcome this, we propose a method enabling fair predictions for sensitive attributes during the testing phase without using such information during training. Inspired by prior work highlighting the impact of feature entanglement on fairness, we enhance the model features by capturing the features related to the sensitive and target attributes and regularizing the feature entanglement between corresponding classes. This ensures that the model can only classify based on the features related to the target attribute without relying on features associated with sensitive attributes, thereby improving fairness and accuracy. Additionally, we use disease masks from the Segment Anything Model (SAM) to enhance the quality of the learned feature. Experimental results demonstrate that the proposed method can improve fairness in classification compared to state-of-the-art methods in two dermatological disease datasets.

Junho Moon, Haejun Chung, Ikbeom Jang

Facial wrinkle detection plays a crucial role in cosmetic dermatology. Precise manual segmentation of facial wrinkles is challenging and time-consuming, with inherent subjectivity leading to inconsistent results among graders. To address this issue, we propose two solutions. First, we build and release the first public facial wrinkle dataset, 'FFHQ-Wrinkle', an extension of the NVIDIA FFHQ dataset. It includes 1,000 images with human labels and 50,000 images with automatically generated weak labels. This dataset could serve as a foundation for the research community to develop advanced wrinkle detection algorithms. Second, we introduce a simple training strategy utilizing texture maps, applicable to various segmentation models, to detect wrinkles across the face. Our two-stage training strategy first pretrain models on a large dataset with weak labels (N=50k), or masked texture maps generated through computer vision techniques, without human intervention. We then finetune the models using human-labeled data (N=1k), which consists of manually labeled wrinkle masks. The network takes as input a combination of RGB and masked texture map of the image, comprising four channels, in finetuning. We effectively combine labels from multiple annotators to minimize subjectivity in manual labeling. Our strategies demonstrate improved segmentation performance in facial wrinkle segmentation both quantitatively and visually compared to existing pretraining methods. The dataset is available at https://github.com/labhai/ffhq-wrinkle-dataset.

A. Trettel, L. Eissing, M. Augustin

R. Knobler, P. Moinzadeh, N. Hunzelmann et al.

Deval Mehta, Brigid Betz-Stablein, Toan D Nguyen et al.

The surge in developing deep learning models for diagnosing skin lesions through image analysis is notable, yet their clinical black faces challenges. Current dermatology AI models have limitations: limited number of possible diagnostic outputs, lack of real-world testing on uncommon skin lesions, inability to detect out-of-distribution images, and over-reliance on dermoscopic images. To address these, we present an All-In-One \textbf{H}ierarchical-\textbf{O}ut of Distribution-\textbf{C}linical Triage (HOT) model. For a clinical image, our model generates three outputs: a hierarchical prediction, an alert for out-of-distribution images, and a recommendation for dermoscopy if clinical image alone is insufficient for diagnosis. When the recommendation is pursued, it integrates both clinical and dermoscopic images to deliver final diagnosis. Extensive experiments on a representative cutaneous lesion dataset demonstrate the effectiveness and synergy of each component within our framework. Our versatile model provides valuable decision support for lesion diagnosis and sets a promising precedent for medical AI applications.

Mustapha Zokay, Hicham Saylani

In this paper we propose a new approach to identify melanoma diseases by identifying the distribution of its main skin chromophores (melanin, oxyhemoglobin and deoxyhemoglobin) from multispectral dermatological images. Based on Blind Source Separation (BSS), our approach takes into account the shading present in most of the images. Assuming that the multispectral images have at least 4 spectral bands, it allows to estimate the distribution of each chromophore in addition to the shading without any a priori information, contrary to all existing methods that use 3 bands, i.e. RGB images. Indeed, the fact of neglecting the shading degrades their performance. To validate our method, we used a database of real multispectral dermatological images of skin affected by melanoma cancer. To measure our performance, in addition to the classical criterion of visually analyzing the estimated distributions with referring to the physiological knowledge of the disease, we proposed a new criterion that is based on our independence hypothesis. Using these two criteria, we could see that our approach is very efficient for the identification of melanoma.

Hye Sung Han, Young Gue Koh, Jun Ki Hong et al.

Background Dupilumab facial redness (DFR) is a side effect of dupilumab treatment that has only been recently reported. We previously reported on two patients with DFR who were successfully treated with a topical formulation containing human adipose tissue-derived mesenchymal stem cell-derived exosomes (ASCEs). Objectives The study aimed to evaluate the efficacy and safety of ASCEs in DFR. Participants and methods We performed 12-week prospective study at single center. Twenty adult atopic dermatitis patients diagnosed with DFR were enrolled. They were treated with a topical application of the exosome formulation every week for five consecutive weeks. Results After exosome treatment, both the average investigator global assessment score and clinical erythema assessment scale scores decreased. 19 patients (95%) were satisfied with the treatment. Compared to baseline, erythema index at week 4 were decreased by 31, 27, 13, and 25 units on the forehead, chin, right and left cheek respectively. The analysis of stratum corneum samples revealed the expression of IL-1α and human thymic stromal lymphopoietin was suppressed after exosome treatment, whereas filaggrin and vascular endothelial growth factor expression increased. Conclusions This study suggests topical formulation containing ASCEs can alleviate DFR by downregulating local inflammation and restoring skin barrier function.

F. Addor

The skin cells continuously produce, through cellular respiration, metabolic processes or under external aggressions, highly reactive molecules oxidation products, generally called free radicals. These molecules are immediately neutralized by enzymatic and non-enzymatic systems in a physiological and dynamic balance. In situations where this balance is broken, various cellular structures, such as the cell membrane, nuclear or mitochondrial DNA may suffer structural modifications, triggering or worsening skin diseases. several substances with alleged antioxidant effects has been offered for topical or oral use, but little is known about their safety, possible associations and especially their mechanism of action. The management of topical and oral antioxidants can help dermatologist to intervene in the oxidative processes safely and effectively, since they know the mechanisms, limitations and potential risks of using these molecules as well as the potential benefits of available associations.

Raluca Jalaboi, Frederik Faye, Mauricio Orbes-Arteaga et al.

Dermatological diagnosis automation is essential in addressing the high prevalence of skin diseases and critical shortage of dermatologists. Despite approaching expert-level diagnosis performance, convolutional neural network (ConvNet) adoption in clinical practice is impeded by their limited explainability, and by subjective, expensive explainability validations. We introduce DermX and DermX+, an end-to-end framework for explainable automated dermatological diagnosis. DermX is a clinically-inspired explainable dermatological diagnosis ConvNet, trained using DermXDB, a 554 image dataset annotated by eight dermatologists with diagnoses, supporting explanations, and explanation attention maps. DermX+ extends DermX with guided attention training for explanation attention maps. Both methods achieve near-expert diagnosis performance, with DermX, DermX+, and dermatologist F1 scores of 0.79, 0.79, and 0.87, respectively. We assess the explanation performance in terms of identification and localization by comparing model-selected with dermatologist-selected explanations, and gradient-weighted class-activation maps with dermatologist explanation maps, respectively. DermX obtained an identification F1 score of 0.77, while DermX+ obtained 0.79. The localization F1 score is 0.39 for DermX and 0.35 for DermX+. These results show that explainability does not necessarily come at the expense of predictive power, as our high-performance models provide expert-inspired explanations for their diagnoses without lowering their diagnosis performance.

Mohamed Akrout, Hayet Amdouni, Amal Feriani et al.

The evolution of behavior of dermatology patients has seen significantly accelerated change over the past decade, driven by surging availability and adoption of digital tools and platforms. Through our longitudinal analysis of this behavior within Tunisia over a 35-year time frame, we identify behavioral patterns across economic and cultural dimensions and how digital tools have impacted those patterns in preceding years. Throughout this work, we highlight the witnessed effects of available digital tools as experienced by patients, and conclude by presenting a vision for how future tools can help address the issues identified across economic and cultural manifestations. Our analysis is further framed around three types of digital tools: "Dr. Google", social media, and artificial intelligence (AI) tools, and across three stages of clinical care: pre-visit, in-visit, and post-visit.

Luke W. Sagers, James A. Diao, Matthew Groh et al.

Dermatological classification algorithms developed without sufficiently diverse training data may generalize poorly across populations. While intentional data collection and annotation offer the best means for improving representation, new computational approaches for generating training data may also aid in mitigating the effects of sampling bias. In this paper, we show that DALL$\cdot$E 2, a large-scale text-to-image diffusion model, can produce photorealistic images of skin disease across skin types. Using the Fitzpatrick 17k dataset as a benchmark, we demonstrate that augmenting training data with DALL$\cdot$E 2-generated synthetic images improves classification of skin disease overall and especially for underrepresented groups.