Hasil untuk "Dermatology"

Rodrigo Mota, Kelvin Cunha, Emanoel dos Santos et al.

Deep learning models for dermatological image analysis remain sensitive to acquisition variability and domain-specific visual characteristics, leading to performance degradation when deployed in clinical settings. We investigate how visual artifacts and domain shifts affect deep learning-based skin lesion classification. We propose an adaptation strategy, grounded in the idea of visual meta-domains, that transfers visual representations from larger dermoscopic datasets into clinical image domains, thereby improving generalization robustness. Experiments across multiple dermatology datasets show consistent gains in classification performance and reduced gaps between dermoscopic and clinical images. These results emphasize the importance of domain-aware training for deployable systems.

Mostafa Anoosha, Dhavalkumar Thakker, Kuniko Paxton et al.

Privacy-preserving medical inference must balance data locality, diagnostic reliability, and deployment efficiency. This paper presents EcoFair, a simulated vertically partitioned inference framework for dermatological diagnosis in which raw image and tabular data remain local and only modality-specific embeddings are transmitted for server-side multimodal fusion. EcoFair introduces a lightweight-first routing mechanism that selectively activates a heavier image encoder when local uncertainty or metadata-derived clinical risk indicates that additional computation is warranted. The routing decision combines predictive uncertainty, a safe--danger probability gap, and a tabular neurosymbolic risk score derived from patient age and lesion localisation. Experiments on three dermatology benchmarks show that EcoFair can substantially reduce edge-side inference energy in representative model pairings while remaining competitive in classification performance. The results further indicate that selective routing can improve subgroup-sensitive malignant-case behaviour in representative settings without modifying the global training objective. These findings position EcoFair as a practical framework for privacy-preserving and energy-aware medical inference under edge deployment constraints.

Xurong Liu, Jipang Zhan, Jingwen Zou et al.

Abstract Introduction Surgical excision is the standard treatment for basal cell carcinoma (BCC). For locally advanced BCC (laBCC) not suitable for surgery or radiotherapy, Hedgehog pathway inhibitors (HHIs) such as sonidegib are important options. Clinical observations have shown that sonidegib may lead to pigmentation and scarring, which can affect treatment evaluation. We evaluated the efficacy and safety of sonidegib in Chinese patients with laBCC and examined discrepancies between clinical/dermoscopic assessments and pathological findings, including posttreatment pathological changes. Methods This single-center retrospective study included 54 patients with laBCC treated with sonidegib 200 mg/day for ≥ 3 months (October 2022–July 2025). Response assessment integrated VISIA-based planimetric lesion-area regression, standardized dermoscopy, and dermoscopy-guided multi-site biopsy as the pathological gold standard. The primary endpoint was objective response rate (ORR); secondary endpoints included disease control rate (DCR) and safety. Results At 3 months, ORR was 87% (complete response [CR] 48%; partial response [PR] 39%), and DCR was 100%. Pathology showed complete clearance in 48.1% and residual tumor in 51.9%, with six cases showing apparent histologic subtype shifts. Dermoscopy in patients with complete remission still demonstrated a high false-positive rate (branching blood vessels 53.8%, blue-gray dots 61.5%), leading to decreased diagnostic specificity. Adverse events occurred in 81.5% of patients; 70.4% reported multiple events, most commonly muscle cramps (66.7%), dysgeusia (59.3%), and alopecia (55.6%). All events were grade 1–3, and no patient discontinued treatment as a result of toxicity. Conclusion In this real-world Chinese laBCC cohort, sonidegib produced a clinically meaningful response with a favorable safety profile. However, clinical and dermoscopic assessments showed substantial false positives due to posttreatment changes; pathological biopsy remains essential to confirm tumor clearance. Advanced noninvasive imaging (e.g., reflectance confocal microscopy) may further improve monitoring. Prospective studies with longer follow-up are warranted.

Mingcheng Zhu, Mingxuan Liu, Han Yuan et al.

Artificial intelligence (AI) has shown remarkable promise in dermatology, offering accurate and non-invasive diagnosis of skin cancer. While extensive research has addressed skin tone-related bias, gender bias in dermatologic AI remains underexplored, leading to unequal care and reinforcing existing gender disparities. In this study, we developed LesionAttn, a fairness-aware algorithm that integrates clinical knowledge into model design by directing attention toward lesion regions, mirroring the diagnostic focus of clinicians. Combined with Pareto-frontier optimization for dual-objective model selection, LesionAttn balances fairness and predictive accuracy. Validated on two large-scale dermatological datasets, LesionAttn significantly mitigates gender bias while maintaining high diagnostic performance, outperforming existing bias mitigation algorithms. Our study highlights the potential of embedding clinical knowledge into AI development to advance both model performance and fairness, and further to foster interdisciplinary collaboration between clinicians and AI developers.

Janet Wang, Xin Hu, Yunbei Zhang et al.

Skin Neglected Tropical Diseases (NTDs) impose severe health and socioeconomic burdens in impoverished tropical communities. Yet, advancements in AI-driven diagnostic support are hindered by data scarcity, particularly for underrepresented populations and rare manifestations of NTDs. Existing dermatological datasets often lack the demographic and disease spectrum crucial for developing reliable recognition models of NTDs. To address this, we introduce eSkinHealth, a novel dermatological dataset collected on-site in Côte d'Ivoire and Ghana. Specifically, eSkinHealth contains 5,623 images from 1,639 cases and encompasses 47 skin diseases, focusing uniquely on skin NTDs and rare conditions among West African populations. We further propose an AI-expert collaboration paradigm to implement foundation language and segmentation models for efficient generation of multimodal annotations, under dermatologists' guidance. In addition to patient metadata and diagnosis labels, eSkinHealth also includes semantic lesion masks, instance-specific visual captions, and clinical concepts. Overall, our work provides a valuable new resource and a scalable annotation framework, aiming to catalyze the development of more equitable, accurate, and interpretable AI tools for global dermatology.

Konstantinos Moutselos, Ilias Maglogiannis

This study proposes a zero-shot image segmentation framework for detecting erythema (redness of the skin) using edit-friendly inversion in diffusion models. The method synthesizes reference images of the same patient that are free from erythema via generative editing and then accurately aligns these references with the original images. Color-space analysis is performed with minimal user intervention to identify erythematous regions. This approach significantly reduces the reliance on labeled dermatological datasets while providing a scalable and flexible diagnostic support tool by avoiding the need for any annotated training masks. In our initial qualitative experiments, the pipeline successfully isolated facial erythema in diverse cases, demonstrating performance improvements over baseline threshold-based techniques. These results highlight the potential of combining generative diffusion models and statistical color segmentation for computer-aided dermatology, enabling efficient erythema detection without prior training data.

Niccolo Marini, Zhaohui Liang, Sivaramakrishnan Rajaraman et al.

Multimodal (MM) learning is emerging as a promising paradigm in biomedical artificial intelligence (AI) applications, integrating complementary modality, which highlight different aspects of patient health. The scarcity of large heterogeneous biomedical MM data has restrained the development of robust models for medical AI applications. In the dermatology domain, for instance, skin lesion datasets typically include only images linked to minimal metadata describing the condition, thereby limiting the benefits of MM data integration for reliable and generalizable predictions. Recent advances in Large Language Models (LLMs) enable the synthesis of textual description of image findings, potentially allowing the combination of image and text representations. However, LLMs are not specifically trained for use in the medical domain, and their naive inclusion has raised concerns about the risk of hallucinations in clinically relevant contexts. This work investigates strategies for generating synthetic textual clinical notes, in terms of prompt design and medical metadata inclusion, and evaluates their impact on MM architectures toward enhancing performance in classification and cross-modal retrieval tasks. Experiments across several heterogeneous dermatology datasets demonstrate that synthetic clinical notes not only enhance classification performance, particularly under domain shift, but also unlock cross-modal retrieval capabilities, a downstream task that is not explicitly optimized during training.

Marc Lalonde, Hamed Ghodrati

The task of grading atopic dermatitis (or AD, a form of eczema) from patient images is difficult even for trained dermatologists. Research on automating this task has progressed in recent years with the development of deep learning solutions; however, the rapid evolution of multimodal models and more specifically vision-language models (VLMs) opens the door to new possibilities in terms of explainable assessment of medical images, including dermatology. This report describes experiments carried out to evaluate the ability of seven VLMs to assess the severity of AD on a set of test images.

Alejandro Lozano, Min Woo Sun, James Burgess et al.

The development of vision-language models (VLMs) is driven by large-scale and diverse multimodal datasets. However, progress toward generalist biomedical VLMs is limited by the lack of annotated, publicly accessible datasets across biology and medicine. Existing efforts are restricted to narrow domains, missing the full diversity of biomedical knowledge encoded in scientific literature. To address this gap, we introduce BIOMEDICA, a scalable, open-source framework to extract, annotate, and serialize the entirety of the PubMed Central Open Access subset into an easy-to-use, publicly accessible dataset. Our framework produces a comprehensive archive with over 24 million unique image-text pairs from over 6 million articles. Metadata and expert-guided annotations are also provided. We demonstrate the utility and accessibility of our resource by releasing BMCA-CLIP, a suite of CLIP-style models continuously pre-trained on the BIOMEDICA dataset via streaming, eliminating the need to download 27 TB of data locally. On average, our models achieve state-of-the-art performance across 40 tasks - spanning pathology, radiology, ophthalmology, dermatology, surgery, molecular biology, parasitology, and cell biology - excelling in zero-shot classification with a 6.56% average improvement (as high as 29.8% and 17.5% in dermatology and ophthalmology, respectively), and stronger image-text retrieval, all while using 10x less compute. To foster reproducibility and collaboration, we release our codebase and dataset for the broader research community.

Hong-Jun Yoon, Chris Keum, Alexander Witkowski et al.

Reflectance Confocal Microscopy (RCM) is a non-invasive imaging technique used in biomedical research and clinical dermatology. It provides virtual high-resolution images of the skin and superficial tissues, reducing the need for physical biopsies. RCM employs a laser light source to illuminate the tissue, capturing the reflected light to generate detailed images of microscopic structures at various depths. Recent studies explored AI and machine learning, particularly CNNs, for analyzing RCM images. Our study proposes a segmentation strategy based on textural features to identify clinically significant regions, empowering dermatologists in effective image interpretation and boosting diagnostic confidence. This approach promises to advance dermatological diagnosis and treatment.

Aayushman, Hemanth Gaddey, Vidhi Mittal et al.

Deep learning models have achieved great success in automating skin lesion diagnosis. However, the ethnic disparity in these models' predictions needs to be addressed before deploying them. We introduce a novel approach, PatchAlign, to enhance skin condition image classification accuracy and fairness by aligning with clinical text representations of skin conditions. PatchAlign uses Graph Optimal Transport (GOT) Loss as a regularizer to perform cross-domain alignment. The representations obtained are robust and generalize well across skin tones, even with limited training samples. To reduce the effect of noise and artifacts in clinical dermatology images, we propose a learnable Masked Graph Optimal Transport for cross-domain alignment that further improves fairness metrics. We compare our model to the state-of-the-art FairDisCo on two skin lesion datasets with different skin types: Fitzpatrick17k and Diverse Dermatology Images (DDI). PatchAlign enhances the accuracy of skin condition image classification by 2.8% (in-domain) and 6.2% (out-domain) on Fitzpatrick17k, and 4.2% (in-domain) on DDI compared to FairDisCo. Additionally, it consistently improves the fairness of true positive rates across skin tones. The source code for the implementation is available at the following GitHub repository: https://github.com/aayushmanace/PatchAlign24, enabling easy reproduction and further experimentation.

Andrea Kim, Niloufar Saharkhiz, Elena Sizikova et al.

Development of artificial intelligence (AI) techniques in medical imaging requires access to large-scale and diverse datasets for training and evaluation. In dermatology, obtaining such datasets remains challenging due to significant variations in patient populations, illumination conditions, and acquisition system characteristics. In this work, we propose S-SYNTH, the first knowledge-based, adaptable open-source skin simulation framework to rapidly generate synthetic skin, 3D models and digitally rendered images, using an anatomically inspired multi-layer, multi-component skin and growing lesion model. The skin model allows for controlled variation in skin appearance, such as skin color, presence of hair, lesion shape, and blood fraction among other parameters. We use this framework to study the effect of possible variations on the development and evaluation of AI models for skin lesion segmentation, and show that results obtained using synthetic data follow similar comparative trends as real dermatologic images, while mitigating biases and limitations from existing datasets including small dataset size, lack of diversity, and underrepresentation.

Fangying Su, Tai Wang, Qunshi Qin et al.

Both bullous pemphigoid (BP) and psoriasis are common immune-related dermatological conditions in clinical practice, but the co-occurrence of these two diseases is rare. Currently, there is no consensus on the long-term safe and effective treatment for patients with both BP and psoriasis. JAK inhibitors are emerging as targeted therapeutic drugs that act by inhibiting Janus kinase activity, regulating the JAK/STAT pathway, blocking the transduction pathway of key proinflammatory cytokines, and influencing T-cell differentiation. These cytokines upstream of the JAK/STAT pathway play a pivotal role in the pathogenesis of numerous inflammatory and autoimmune disorders. Upadacitinib, a second-generation JAK inhibitor with high selectivity, demonstrates promising potential.This case report aims to provide a description of the successful treatment of bullous pemphigoid (BP) and psoriasis vulgaris by using upadacitinib, highlighting significant clinical outcomes. Additionally, we aim to analyze the underlying mechanism of upadacitinib in treating these two comorbidities by reviewing relevant literature from both domestic and international sources. Based on our clinical observations, upadacitinib appears to be a promising and well-tolerated therapeutic option for patients with concurrent BP and psoriasis, offering valuable insights for developing appropriate treatment strategies in clinical practice.

Renata Malheiro, César Magalhães, Cláudia Camila Dias et al.

Human papillomavirus (HPV) is the most prevalent sexually transmitted infection among young women. Notably, more than ten years after the introduction of HPV vaccination programs in Europe, it is essential to review the real-world evidence of the incidence of anogenital warts (GWs) among women vaccinated during childhood. In this systematic review, three databases were searched for studies published between January 2008 and September 2023. Nine cohort studies were included. A total of 890,320 HPV-vaccinated women and 1,922,033 unvaccinated women were evaluated. All the studies but one investigated the 4vHPV vaccine. The incidence rate of GWs in vaccinated women ranged from 0.0 to 1650 per 100,000 person-years. The highest incidence rates were found in women vaccinated with one dose at the age of 17–19 years old and in fully vaccinated women only after 19 years of age. Similar incidence values were reported among unvaccinated women. The incidence of GWs was lower when the age at first dose was 9–11 years old. This systematic review reveals that the incidence of GWs among HPV-vaccinated women is related to the age of vaccination and the number of vaccine doses received. In the post-vaccination era, epidemiological surveillance of the incidence of GWs and their genotypes is crucial.

Roxana Daneshjou, Mert Yuksekgonul, Zhuo Ran Cai et al.

For the deployment of artificial intelligence (AI) in high-risk settings, such as healthcare, methods that provide interpretability/explainability or allow fine-grained error analysis are critical. Many recent methods for interpretability/explainability and fine-grained error analysis use concepts, which are meta-labels that are semantically meaningful to humans. However, there are only a few datasets that include concept-level meta-labels and most of these meta-labels are relevant for natural images that do not require domain expertise. Densely annotated datasets in medicine focused on meta-labels that are relevant to a single disease such as melanoma. In dermatology, skin disease is described using an established clinical lexicon that allows clinicians to describe physical exam findings to one another. To provide a medical dataset densely annotated by domain experts with annotations useful across multiple disease processes, we developed SkinCon: a skin disease dataset densely annotated by dermatologists. SkinCon includes 3230 images from the Fitzpatrick 17k dataset densely annotated with 48 clinical concepts, 22 of which have at least 50 images representing the concept. The concepts used were chosen by two dermatologists considering the clinical descriptor terms used to describe skin lesions. Examples include "plaque", "scale", and "erosion". The same concepts were also used to label 656 skin disease images from the Diverse Dermatology Images dataset, providing an additional external dataset with diverse skin tone representations. We review the potential applications for the SkinCon dataset, such as probing models, concept-based explanations, and concept bottlenecks. Furthermore, we use SkinCon to demonstrate two of these use cases: debugging mistakes of an existing dermatology AI model with concepts and developing interpretable models with post-hoc concept bottleneck models.

Héctor Carrión, Narges Norouzi

Skin diseases affect millions of people worldwide, across all ethnicities. Increasing diagnosis accessibility requires fair and accurate segmentation and classification of dermatology images. However, the scarcity of annotated medical images, especially for rare diseases and underrepresented skin tones, poses a challenge to the development of fair and accurate models. In this study, we introduce a Fair, Efficient, and Diverse Diffusion-based framework for skin lesion segmentation and malignancy classification. FEDD leverages semantically meaningful feature embeddings learned through a denoising diffusion probabilistic backbone and processes them via linear probes to achieve state-of-the-art performance on Diverse Dermatology Images (DDI). We achieve an improvement in intersection over union of 0.18, 0.13, 0.06, and 0.07 while using only 5%, 10%, 15%, and 20% labeled samples, respectively. Additionally, FEDD trained on 10% of DDI demonstrates malignancy classification accuracy of 81%, 14% higher compared to the state-of-the-art. We showcase high efficiency in data-constrained scenarios while providing fair performance for diverse skin tones and rare malignancy conditions. Our newly annotated DDI segmentation masks and training code can be found on https://github.com/hectorcarrion/fedd.

Walter Belda, Luiz Felipe Domingues Passero, Caroline Heleno Chagas de Carvalho et al.

Chromoblastomycosis (CBM) is a neglected human disease, caused by different species of pigmented dematiaceous fungi that cause granulomatous and suppurative dermatosis. This infection is difficult to treat and there are limited therapeutic options, including terbinafine, itraconazole, and tioconazole. Classic treatment is administered for a long period of time, but some patients do not respond properly, and therefore, such therapeutic approaches possess low cure rates. Therefore, it is vital to develop new strategies for the treatment of CBM. In this regard, it has been observed that the association of immunomodulatory molecules such as glucan with therapy carried out with antifungal drugs improves cutaneous lesions in comparison to treatment with antifungal drugs alone, suggesting that drug association may be an interesting and significant approach to incorporate into CBM therapy. Thus, the aim of this work was to associate classical antifungal therapy with the adjuvants imiquimod and acitretin. In the present case, we reported a patient with extensive CBM caused by <i>Fonsaecae pedrosoi</i>, that affected an extensive area of the right leg, that was left without treatment for 11 years. He was treated with a classical combination of itraconazole and terbinafine via the oral route plus topical imiquimod and oral acitretin, as an adjuvant therapy. After five months of treatment, a significant regression of verrucous plaques was observed, suggesting that the use of these adjuvants combined with the classical antifungal drugs, intraconazole plus terbinafine, can reduce treatment time and rapidly improve the patient’s quality of life. This result confirms that the use of coadjuvant drugs may be effective in the treatment of this infectious disease.

C. Salas-Marquez, R. Bosch García, F. Rivas Ruiz et al.

Hee Eun Choi, Tae Hoon Kim, Ji Hoon Jang et al.

<b>Background:</b> This study evaluated the efficacy and safety of pulmonary rehabilitation (PR) on functional performance, exercise-related oxygen saturation, and health-related quality of life among patients with idiopathic pulmonary fibrosis (IPF). <b>Methods:</b> A total of 25 patients with IPF (13 in the PR group and 12 in the non-PR group) were enrolled between August 2019 and October 2021 at Haeundae-Paik Hospital in the Republic of Korea. A cardiopulmonary exercise test (CPET), six-minute walk test (6MWT), pulmonary function test (PFT), Saint George’s Respiratory Questionnaire (SGRQ), muscle strength test, and bioelectrical impedance analysis were performed in each group at baseline and after eight weeks of PR. <b>Results:</b> The mean age was 68 years of age and most subjects were male. Baseline characteristics were similar between the two groups. The distance during 6MWT after PR was significantly improved in the PR group (inter-group <i>p</i>-value = 0.002). VO₂max and VE/VCO₂ slopes showed a significant difference after eight weeks only in the PR group, but the rate of change did not differ significantly from the non-PR group. Total skeletal muscle mass, PFT variables, and SGRQ scores did not differ significantly between the groups. <b>Conclusions:</b> PR improved exercise capacity, as measured using CPET and 6 MWT. Further studies in larger samples are needed to evaluate the long-term efficacy of PR in IPF patients.