Search Results (336)

Most camera view planning algorithms are employed in exploration tasks that maximise information gain, but few address the specific challenge of observing targeted surface areas with optimal image quality. This paper presents a novel camera view planning algorithm designed for dermoscopic mole mapping, which is crucial for early melanoma detection. Traditional full-body scanners, though beneficial, suffer from fixed camera positions that can compromise image quality due to varying body contours and patient sizes. Our algorithm addresses this limitation by dynamically optimizing the camera position on a set of collaborative robot (cobot) arms to enhance image resolution, safety, and viewing angles during skin examinations. The proposed method formulates the problem as a non-linear least-squares optimisation that ensures no camera occlusion and a safe distance from the end effector encapsulating the camera to the patient while adjusting the pose of the camera based on the topography of the body. This approach not only maintains optimal imaging conditions by considering resolution and angle of incidence but also prioritises patient safety by preventing physical contact between the camera and the patient. Extensive testing demonstrates that our algorithm adapts effectively to different body shapes and sizes, ensuring high-resolution images across various patient demographics. Moreover, the integration of our camera view planning algorithm into an intelligent dermoscopy system has shown promising results in improving the efficiency and geometric quality of dermoscopic image acquisition, which could lead to more reliable and faster diagnoses. This technology holds significant potential to transform melanoma screening and diagnosis, providing a scalable, safer, and more precise approach to dermatological imaging. Full article

Cutaneous melanoma is one of the most aggressive skin cancers, and early diagnosis remains essential to reduce mortality. Reflectance Confocal Microscopy (RCM) provides non-invasive, quasi-histological images of the epidermis, dermoepidermal junction (DEJ), and dermis, enabling real-time assessment of melanocytic lesions. However, interpretation still relies on expert visual evaluation, which is time-consuming and subjective. In this context, Artificial Intelligence (AI) and Computer-Assisted Detection (CAD) systems are emerging as valuable tools to improve diagnostic accuracy and reproducibility. This review summarizes research on AI applications in RCM imaging for melanoma, focusing on three major areas: delineation of skin strata, segmentation of tissues and morphological patterns, and classification of benign versus malignant lesions. Early approaches included Bayesian classifiers, wavelet-based decision trees, and logistic regression, while recent studies have employed support vector machines, random forests, and increasingly deep learning architectures such as convolutional and recurrent neural networks. The results demonstrate encouraging accuracy in DEJ localization, the segmentation of diagnostically relevant patterns, and the discrimination of melanoma from benign nevi. We distinguish the maturity of dermoscopy-based AI (AUC (ROC) > 0.80 on large multicenter cohorts) from the still-exploratory evidence for RCM-based AI. Nonetheless, current studies are often limited by small datasets, heterogeneous protocols, and a lack of multicenter validation. Overall, progress in AI applied to RCM supports the development of CAD systems that could assist clinicians during acquisition and diagnosis, reducing unnecessary biopsies and improving early melanoma detection. Future work should address standardization, dataset expansion, and the integration of advanced AI methods to move closer to clinical implementation. Full article

Background/Objectives: The surgical treatment of basal cell carcinoma (BCC) remains challenging due to the time-consuming, expensive and invasive nature of Mohs micrographic surgery. The objective is to develop a standardized protocol for managing diagnosis, surgery, and margin control within a single patient visit. Methods: Several protocols were tested to establish a “BCC-One-Stop-Shop”, combining in vivo and ex vivo margin mapping of BCC, pre- and postoperatively using Line-field confocal optical coherence tomography (LC-OCT). We introduce an algorithm enabling real-time localization of LC-OCT acquisitions on a previously acquired dermoscopy image. Additionally, an artificial intelligence model provides a BCC probability score based on LC-OCT images. Together, the co-localization algorithm and AI BCC model generate a color-coded visualization of the tumor within the dermoscopy image, allowing precise pre-operative in vivo margin assessment. Results: We found our protocol, the implementation of the co-localization tool and the AI model, to be quick to apply, easy to learn and helpful regarding the initial determination of BCC tumor margins. Patients responded positively to the recognizable visualization of the disease. Conclusions: Pre- and postoperative margin mapping using LC-OCT imaging appears to be effective and feasible and could reduce time, costs, resources, excision sizes and patient burden by sparing additional excision steps in micrographic surgery. The integration of real-time co-localization and the AI-calculated probability score represent meaningful and practical enhancements for routine clinical use. To further evaluate the efficacy and safety of the BCC-One-Stop-Shop-Method and the newly introduced device features, larger-scale studies are warranted and are currently being conducted. Full article

Background: Cutaneous melanoma metastases (CMM) represent a clinically relevant manifestation of advanced melanoma and may constitute the first sign of disseminated disease. Their diagnosis is challenging because CMM shows highly variable clinical and dermoscopic presentations and frequently mimic other benign or malignant skin lesions. Although dermoscopy is routinely used to improve skin lesion assessment, dermoscopic criteria specific to CMM remain poorly defined and still non-standardized. Methods: We performed a narrative review of the literature to summarize dermoscopic features reported in CMM. MedLine (via PubMed) and Web of Science were searched up to 3 December 2025 using the keywords “dermoscopy” and “melanoma metastasis,” complemented by manual reference screening. Eligible studies were English-language full-text articles in peer-reviewed journals providing a complete dermoscopic description. Extracted data included patient demographics and major dermoscopic criteria, categorized as global patterns and focal dermoscopic and vascular structures. Due to heterogeneity, results were synthesized descriptively. Results: Twenty studies were included, comprising 774 patients. Dermoscopic findings were markedly heterogeneous. Globally, lesions frequently showed homogeneous pigmentation with variable colors and included amelanotic presentations. Commonly evaluated focal features included irregular dots and globules, crystalline structures, peripheral gray dots, and lacuna-like areas. Vascular patterns were prominent, particularly serpentine and corkscrew-like vessels. Conclusions: CMM dermoscopy is characterized by substantial heterogeneity and a lack of standardized criteria. Systematic classification of recurring dermoscopic features may improve diagnostic consistency and provide an interpretable framework for future artificial intelligence-based approaches supporting non-invasive recognition of melanoma metastases. Full article

Precision oncology has been evolving rapidly, with increasing emphasis on early detection and personalized diagnostic approaches that translate into tailored treatment algorithms. The integration of molecular markers, quantitative imaging approaches and artificial intelligence (AI) in the diagnostic workflow of cutaneous squamous cell carcinoma (cSCC) has increased accuracy and has the potential to improve early detection rates in these cancers. Sun exposure is the primary etiologic factor in the development of cSCC. The primary objective of this review is to evaluate the current state and future directions of modalities and practices in diagnostic techniques for cSCC. Specifically, this review summarizes the key genetic alterations and potential molecular targets in cSCC. High-risk genetic mutations and pathways implicated in the pathogenesis of cSCC include p53, NOTCH, RAS/MAPK, cell-cycle, and adhesion pathways. This review further explores current and emerging modalities in optical imaging techniques and molecular-based diagnostic modalities in cSCC. Further, we discuss the role of radiomics and AI in the diagnostic work-up of cSCC. These techniques have the potential to enable more accurate risk models that refine conventional histopathology and guide personalized interventions. However, there are limitations to the clinical application of several of these modalities, with cost being an important driver. These challenges have been discussed in detail within this review. Nevertheless, ongoing research is focused on improving the workflow and initiating a shift in clinical practice with application of precision diagnostics as a standard of care. Full article

Objectives: To evaluate the impact of non-invasive imaging techniques such as dermoscopy, reflectance confocal microscopy (RCM) and optical coherence tomography (OCT) to monitor the efficacy of risankizumab on plaque psoriasis of the legs by analyzing morpho-histological changes. Materials and Methods: Multicentre, real-world retrospective study involving 37 adults with moderate-to-severe plaque psoriasis. Assessments performed during routine visits at baseline, Week 4 and Week 12 included clinical response, dermoscopy, RCM and OCT. Results: Thirty-seven patients were included (mean age 52.1 years; 54% male; mean BMI 27.0 kg/m²). Dermoscopy showed progressive vascular normalization: at Week 12, 94.29% of lesions had minimal or no vascular pattern. White and yellow scales decreased significantly. On RCM, dilated vessels, inflammatory infiltrate, and papillomatosis progressively normalized. OCT showed reduction in epidermal and stratum corneum thickness and a decline in vascular intensity at multiple depths. Baseline haemorrhagic dots predicted early complete response: 44.8% of lesions with dots achieved complete clearance at Week 4 versus 0% without. Conclusions: Risankizumab induced rapid, significant regression of psoriatic changes, normalizing vascular patterns and skin architecture and reducing epidermal thickness. Findings support its efficacy and rapid onset of action in difficult-to-treat areas and highlight the value of non-invasive imaging for monitoring. Full article

Background: In actinic keratosis (AK), clinical clearance after field-directed therapies does not necessarily correspond to histological resolution, resulting in subclinical persistence and risk of recurrence. Objective: To provide a practical, up-to-date framework for non-invasive monitoring of treatment response in AK, integrating clinical assessment and dermoscopy with high-resolution imaging techniques, reflectance confocal microscopy (RCM), line-field confocal optical coherence tomography (LC-OCT), and high-frequency ultrasound (HFUS), and to discuss emerging optical biomarkers based on Raman spectroscopy. Results: For each modality, we summarize pre- and post-treatment imaging patterns, proposed response criteria, recommended follow-up timing, and correlations with clinical outcomes (including clearance and AKASI) and, when available, histological findings. The available evidence is derived from a limited number of observational studies, predominantly involving RCM and LC-OCT, whereas data on HFUS and Raman spectroscopy remain comparatively scarce. RCM and LC-OCT allow in vivo assessment of epidermal architectural normalization and reduction of intraepidermal keratinocyte atypia. HFUS captures quantitative trajectories of superficial dermal remodeling, including changes in the subepidermal low-echogenic band (SLEB) and dermal echogenicity after photodynamic therapy and other field treatments. Dermoscopy remains the first-line tool for routine follow-up but may fail to detect minimal subclinical persistence. Finally, we discuss the potential role of in vivo Raman spectroscopy for dynamic molecular endpoints and its possible integration with artificial intelligence–based analytical approaches. Conclusions: A standardized multimodal follow-up strategy improves the accuracy of treatment-response assessment compared with clinical evaluation alone. We propose a technique-specific checklist of minimal response criteria and a pragmatic temporal assessment scheme, and outline a research roadmap to support validation and clinical implementation of non-invasive imaging-guided monitoring in actinic keratosis. Full article

Melanoma is the most lethal form of skin cancer, and early detection is critical for improving patient outcomes. Although dermoscopy combined with deep learning has advanced automated skin-lesion analysis, progress is hindered by limited access to large, well-annotated datasets and by severe class imbalance, where melanoma images are substantially underrepresented. To address these challenges, we present the first systematic benchmarking study comparing four GAN architectures—DCGAN, StyleGAN2, and two StyleGAN3 variants (T and R)—for high-resolution ($512\times 512$) melanoma-specific synthesis. We train and optimize all models on two expert-annotated benchmarks (ISIC 2018 and ISIC 2020) under unified preprocessing and hyperparameter exploration, with particular attention to R1 regularization tuning. Image quality is assessed through a multi-faceted protocol combining distribution-level metrics (FID), sample-level representativeness (FMD), qualitative dermoscopic inspection, downstream classification with a frozen EfficientNet-based melanoma detector, and independent evaluation by two board-certified dermatologists. StyleGAN2 achieves the best balance of quantitative performance and perceptual quality, attaining FID scores of 24.8 (ISIC 2018) and 7.96 (ISIC 2020) at $\gamma =0.8$. The frozen classifier recognizes 83% of StyleGAN2-generated images as melanoma, while dermatologists distinguish synthetic from real images at only 66.5% accuracy (chance = 50%), with low inter-rater agreement ($\kappa =0.17$). In a controlled augmentation experiment, adding synthetic melanoma images to address class imbalance improved melanoma detection AUC from 0.925 to 0.945 on a held-out real-image test set. These findings demonstrate that StyleGAN2-generated melanoma images preserve diagnostically relevant features and can provide a measurable benefit for mitigating class imbalance in melanoma-focused machine learning pipelines. Full article

Background: Assessing image quality is critical in medical imaging to ensure diagnostic reliability. Traditional no-reference image quality assessment (IQA) metrics designed for natural images often fail to address the complexities of medical images. This study proposes DermaIQA, a novel no-reference metric for dermoscopic images that aligns quality scores with clinical perception. Methods: We developed a degradation pipeline simulating realistic artifacts without requiring extensive manual labeling. From 812 expert-classified images, we generated a comprehensive dataset (>125,000 images) using controlled blur and compression techniques. An iterative ranking procedure converted these degradations into a continuous quality scale, which was used to train a vision transformer model. Results: The proposed IQA metric outperformed both heuristic and deep learning techniques, achieving 92% accuracy in distinguishing high-quality vs. low-quality images. The approach demonstrated robust generalization when tested on external datasets with different acquisition characteristics, confirming its relevance across varied imaging conditions. Conclusions: DermaIQA represents the first dermatology-specific quality metric that minimizes expert annotation requirements while maintaining clinical relevance. This tool enhances workflows through real-time acquisition feedback and acts as a gatekeeper for AI diagnostic systems, ensuring only high-quality images are processed. The trained model and inference scripts are publicly available. Full article

Background/Objectives: Melanoma remains one of the most malignant types of skin cancer with rising incidence numbers, despite the progress made in the prevention and management of the disease. Recent technological advancements, such as developments in the field of molecular biology, imaging, and artificial intelligence (AI), have led to a paradigm shift in the diagnosis, assessment, and management of melanoma. The current review aims to integrate current research on melanoma, moving beyond the boundaries of conventional histological analysis. Methods: This is a critical appraisal narrative review that focuses on recent studies in the areas of translation research and digital health with regard to melanoma. This research particularly targeted recent studies within the last five years, with landmark studies implicated when appropriate. Evidence was synthesized within the major categories that include epidemiology, early diagnosis, histopathology, predictive biomarkers, genetic/epigenetic changes, AI-assisted diagnostic platforms, and novel therapeutic platforms & targets. Results: Early detection techniques, innovative imaging, and biomarker-guided risk adjustment can improve diagnostic accuracy and prognostic stratification. The potential of AI in dermoscopy, digital pathology, and decision analytical systems is evident, although validation, bias, and integration issues need to be addressed. Advances in immunotherapy, targeted therapies, and novel molecular/immunological targets are expanding and facilitating integrated and personalized management. Conclusions: There is a trend in melanoma research to shift towards an integrated diagnostic platform that involves the use of AI, molecular characterization, and clinical inputs to enable more accurate and personalized diagnoses. To realize this potential, there is a need to validate, collaborate, and address ethics and implementation. Full article

Background/Objectives: Accurate and reliable automated dermoscopic lesion classification remains challenging. This is due to pronounced dataset bias, limited expert-annotated data, and poor cross-dataset generalization of conventional supervised deep learning models. In clinical dermatology, these limitations restrict the deployment of data-driven diagnostic systems across diverse acquisition settings and patient populations. Methods: Motivated by these challenges, this study proposes a transformer-based, dermatology-specific foundation model. The model learns transferable visual representations from large collections of unlabeled dermoscopic images via self-supervised pretraining. It integrates large-scale dermatology-oriented self-supervised learning with a hierarchical vision transformer backbone. This enables effective capture of both fine-grained lesion textures and global morphological patterns. The evaluation is conducted across three publicly available dermoscopic datasets: ISIC 2018, HAM10000, and PH2. The study assesses in-dataset, cross-dataset, limited-label, ablation, and computational-efficiency settings. Results: The proposed approach achieves in-dataset classification accuracies of 94.87%, 97.32%, and 98.17% on ISIC 2018, HAM10000, and PH2, respectively. It outperforms strong transformer and hybrid baselines. Cross-dataset transfer experiments show consistent performance gains of 3.5–5.8% over supervised counterparts. This indicates improved robustness to domain shift. Furthermore, when fine-tuned with only 10% of the labeled training data, the model achieves performance comparable to fully supervised baselines. Conclusions: This highlights strong data efficiency. These results demonstrate that dermatology-specific foundation learning offers a principled and practical solution for robust dermoscopic lesion classification under realistic clinical constraints. Full article

Background/Objectives: Melanoma is the most lethal cutaneous neoplasm, with Breslow thickness being a key prognostic factor. This retrospective cohort study aimed to assess the impact of screening frequency and diagnostic methods on tumour stage at diagnosis and to explore implications for risk-adapted strategies. Methods: Between 2017 and 2024, 475 cases of melanoma were diagnosed in 397 patients. Screening frequency, diagnostic method, and patient risk were analyzed in relation to tumour stage. Results: Compared with first-visit cases, patients who underwent screening within two years prior to diagnosis were more often diagnosed with melanoma in situ (32.6% vs. 44–51%; p < 0.05) and had thinner invasive tumours (0.68–0.73 mm vs. 1.8 mm; p ≤ 0.001), though no differences were seen between screening frequencies. Full-body examination was associated with more in situ melanomas (46% vs. 34%; p = 0.016) and thinner invasive tumours (0.92 vs. 2.05 mm; p = 0.2) compared with lesion-directed screening, but this effect disappeared after excluding first-visit cases. Invasive melanomas diagnosed by mole mapping were significantly thinner than by dermoscopy (0.55 vs. 1.07; p = 0.035). In high-risk patients, tumour thickness decreased with more frequent visits (0.905 mm without screening vs. 0.40–0.55 mm with ≥1 visit; p = 0.001). Moreover, mole mapping identified thinner melanomas in the high-risk group compared with dermoscopy (0.47 vs. 0.60 mm; p = 0.02). Conclusions: Screening is associated with thinner melanomas and more in situ diagnoses. Digital mole mapping offers additional benefits, with high-risk patients profiting most, while low-risk individuals could be managed with less resource-intensive approaches. These findings support risk-adapted screening strategies focusing on intensive, digitally supported modalities for high-risk groups. Full article

Introduction: Subungual squamous cell carcinoma is a rare malignancy of the nail unit that is frequently misdiagnosed as benign nail disease, leading to prolonged diagnostic delays and sometimes invasive spread. Objective: To synthesize the dermoscopic features of histologically confirmed subungual squamous cell carcinoma and to compare patterns between invasive and in situ disease. Methods: We performed a systematic review and meta-analysis (PROSPERO CRD42023470387) following PRISMA and MOOSE guidance. PubMed, Scopus and Cochrane CENTRAL were searched. Extracted data included study design, lesion counts, histologic subtype and specific dermoscopic signs. Random-effects meta-analysis (DerSimonian–Laird with Freeman–Tukey transformation) produced pooled prevalences with 95% confidence intervals. Between-study heterogeneity was assessed with Cochran’s Q and I². We used subgroup and meta-regression analyses to explore the influence of histologic subtype, sample size and publication year. When the data allowed, diagnostic odds ratios were calculated versus common benign mimickers. Results: Twenty studies comprising 121 lesions (96 invasive, 25 in situ) were included. In invasive lesions, the most common dermoscopic findings were subungual hyperkeratosis (pooled prevalence 89%; 95% CI 78–97; I² = 0%), onycholysis (85%; 75–93; I² = 28%), irregular borders (72%; 50–90; I² = 42%), and splinter hemorrhages (52%; 40–65; I² = 36%). In situ lesions more often presented with melanonychia (89%) and showed lower rates of hyperkeratosis (50%). Meta-regression identified histologic subtype as a significant predictor of feature prevalence (p < 0.01). Key comparative performance estimates included a diagnostic odds ratio of 12.6 (95% CI 8.3–19.1) for polymorphous vessels distinguishing squamous cell carcinoma from warts and 6.8 (95% CI 3.2–14.5) for hyperkeratosis versus onychomycosis. Conclusions: Dermoscopy reliably identifies features, particularly hyperkeratosis, onycholysis, irregular margins and hemorrhagic spots, that are common in invasive subungual squamous cell carcinoma; in situ disease more commonly presents with pigmentary changes. Recognition of these signs should lower the threshold for biopsy of suspicious single-digit nail lesions and may facilitate earlier diagnosis and treatment. Full article

Background and Objectives: Dermatology relies on a complex terminology encompassing lesion types, distribution patterns, colors, and specialized sites such as hair and nails, while dermoscopy adds an additional descriptive framework, making interpretation subjective and challenging. Our study aims to evaluate the ability of a chatbot (Gemini 2) to generate dermatology descriptions across multiple languages and image types, and to assess the influence of prompt language on readability, completeness, and terminology consistency. Our research is based on the concept that non-English prompts are not mere translations of the English prompts but are independently generated texts that reflect medical and dermatological knowledge learned from non-English material used in the chatbot’s training. Materials and Methods: Five macroscopic and five dermoscopic images of common skin lesions were used. Images were uploaded to Gemini 2 with language-specific prompts requesting short paragraphs describing visible features and possible diagnoses. A total of 2400 outputs were analyzed for readability using LIX score and CLEAR (comprehensiveness, accuracy, evidence-based content, appropriateness, and relevance) assessment, while terminology consistency was evaluated via SNOMED CT mapping across English, French, German, and Greek outputs. Results: English and French descriptions were found to be harder to read and more sophisticated, while SNOMED CT mapping revealed the largest terminology mismatch in German and the smallest in French. English texts and macroscopic images achieved the highest accuracy, completeness, and readability based on CLEAR assessment, whereas dermoscopic images and non-English texts presented greater challenges. Conclusions: Overall, partial terminology inconsistencies and cross-lingual variations highlighted that the language of the prompt plays a critical role in shaping AI-generated dermatology descriptions. Full article