Explore the vast range of titles available.

The rapid increase in telemedicine coupled with recent advances in diagnostic artificial intelligence (AI) create the imperative to consider the opportunities and risks of inserting AI-based support into new paradigms of care. Here we build on recent achievements in the accuracy of image-based AI for skin cancer diagnosis to address the effects of varied representations of AI-based support across different levels of clinical expertise and multiple clinical workflows. We find that good quality AI-based support of clinical decision-making improves diagnostic accuracy over that of either AI or physicians alone, and that the least experienced clinicians gain the most from AI-based support. We further find that AI-based multiclass probabilities outperformed content-based image retrieval (CBIR) representations of AI in the mobile technology environment, and AI-based support had utility in simulations of second opinions and of telemedicine triage. In addition to demonstrating the potential benefits associated with good quality AI in the hands of non-expert clinicians, we find that faulty AI can mislead the entire spectrum of clinicians, including experts. Lastly, we show that insights derived from AI class-activation maps can inform improvements in human diagnosis. Together, our approach and findings offer a framework for future studies across the spectrum of image-based diagnostics to improve human–computer collaboration in clinical practice. A systematic evaluation of the value of AI-based decision support in skin tumor diagnosis demonstrates the superiority of human–computer collaboration over each individual approach and supports the potential of automated approaches in diagnostic medicine.

Whether machine-learning algorithms can diagnose all pigmented skin lesions as accurately as human experts is unclear. The aim of this study was to compare the diagnostic accuracy of state-of-the-art machine-learning algorithms with human readers for all clinically relevant types of benign and malignant pigmented skin lesions. For this open, web-based, international, diagnostic study, human readers were asked to diagnose dermatoscopic images selected randomly in 30-image batches from a test set of 1511 images. The diagnoses from human readers were compared with those of 139 algorithms created by 77 machine-learning labs, who participated in the International Skin Imaging Collaboration 2018 challenge and received a training set of 10 015 images in advance. The ground truth of each lesion fell into one of seven predefined disease categories: intraepithelial carcinoma including actinic keratoses and Bowen's disease; basal cell carcinoma; benign keratinocytic lesions including solar lentigo, seborrheic keratosis and lichen planus-like keratosis; dermatofibroma; melanoma; melanocytic nevus; and vascular lesions. The two main outcomes were the differences in the number of correct specific diagnoses per batch between all human readers and the top three algorithms, and between human experts and the top three algorithms. Between Aug 4, 2018, and Sept 30, 2018, 511 human readers from 63 countries had at least one attempt in the reader study. 283 (55·4%) of 511 human readers were board-certified dermatologists, 118 (23·1%) were dermatology residents, and 83 (16·2%) were general practitioners. When comparing all human readers with all machine-learning algorithms, the algorithms achieved a mean of 2·01 (95% CI 1·97 to 2·04; p<0·0001) more correct diagnoses (17·91 [SD 3·42] vs 19·92 [4·27]). 27 human experts with more than 10 years of experience achieved a mean of 18·78 (SD 3·15) correct answers, compared with 25·43 (1·95) correct answers for the top three machine algorithms (mean difference 6·65, 95% CI 6·06–7·25; p<0·0001). The difference between human experts and the top three algorithms was significantly lower for images in the test set that were collected from sources not included in the training set (human underperformance of 11·4%, 95% CI 9·9–12·9 vs 3·6%, 0·8–6·3; p<0·0001). State-of-the-art machine-learning classifiers outperformed human experts in the diagnosis of pigmented skin lesions and should have a more important role in clinical practice. However, a possible limitation of these algorithms is their decreased performance for out-of-distribution images, which should be addressed in future research. None.

Sentinel lymph node biopsy has been proposed as a diagnostic method for estimation of the malignant potential of atypical Spitz tumours. However, although cell deposits are commonly detected in the sentinel lymph nodes of patients with atypical Spitz tumours, their prognosis is substantially better than that of patients with melanoma and positive sentinel lymph node biopsies. We did a systematic review of published reports to assess the role of sentinel lymph node biopsy as a prognostic method in the management of atypical Spitz tumours. The results of our analysis did not show any prognostic benefit of sentinel lymph node biopsy; having a positive sentinel lymph node does not seem to predict a poorer outcome for patients with atypical Spitz tumours. These findings indicate that, especially in the paediatric population, it might be prudent initially to use complete excision with clear margins and careful clinical follow-up in patients with atypical Spitz tumours.

Background Merkel cell carcinoma (MCC) is a rare, aggressive, cutaneous tumour with high mortality and frequently delayed diagnosis. Clinically, it often manifests as a rapidly growing erythematous to purple nodule usually located on the lower extremities or face and scalp of elderly patients. There is limited available data on the dermoscopic findings of MCC, and there are no specific features that can be used to definitively diagnose MCC. Aim of the study Here, we aimed to summarize existing published literature on dermatoscopic and reflectance confocal microscopy (RCM) features of MCC. Materials and methods To find relevant studies, we searched the PubMed and Scopus databases from inception to April 12, 2023. Our goal was to identify all pertinent research that had been written in English. The following search strategy was employed: (“ dermoscopy” OR “ dermatoscopy” OR “ videodermoscopy” OR “ videodermatoscopy” OR “ reflectance confocal microscopy”) AND “ Merkel cell carcinoma”. Two dermatologists, DK and GE, evaluated the titles and abstracts separately for eligibility. For inclusion, only works written in English were taken into account. Results In total 16 articles were retrieved (68 cases). The main dermoscopic findings of MCC are a polymorphous vascular pattern including linear irregular, arborizing, glomerular, and dotted vessels on a milky red background, with shiny or non-shiny white areas. Pigmentation was lacking in all cases. The RCM images showed a thin and disarranged epidermis, and small hypo-reflective cells that resembled lymphocytes arranged in solid aggregates outlined by fibrous tissue in the dermis. Additionally, there were larger polymorphic hyper-reflective cells that likely represented highly proliferative cells. Conclusion Dermoscopic findings of MCC may play a valuable role in evaluating MCC, aiding in the early detection and differentiation from other skin lesions. Further prospective case-control studies are needed to validate these results.

Despite durable responses achieved with Immune Checkpoint Inhibitors (ICIs), data about optimal duration of treatment, especially in the context of adverse events, remain scarce. To systematically review the evidence concerning the impact of treatment discontinuation with ICIs for reasons other than progressive disease (PD) on relapse rates and survival of melanoma patients. A systematic literature search was conducted in three electronic databases until July 2024. Studies referring to melanoma patients who ceased ICIs electively (i.e. due to complete response (CR), protocol completion or patient/physician's wish) or due to treatment-limiting toxicities (TLTs) were selected. Relapse rates (RRs) post cessation, time to PD, rechallenge and disease control rate (DCR) after 2 course were the main outcomes. Random-effects models were preferred, and subgroup and sensitivity analyses were conducted to investigate possible sources of heterogeneity. 38 and 35 studies were included in qualitative and quantitative synthesis, respectively. From 2542 patients discontinued treatment with ICIs electively or due to TLTs, 495 experienced progression [number of studies (n)=34, RR 20.9%, 95%CI 17.1 - 24.7%, I 85%) and higher rates were detected in patients with TLTs compared to elective discontinuation. Mean time to PD was 14.26 months (n=18, mean time 14.26, 95%CI 11.54 - 16.98, I 93%) and was numerically higher in patients who ceased for CR compared to patients with TLTs. Treatment duration before cessation was not associated with risk and time to relapse, while mucosal melanomas and non-CR as BOR during treatment led to increased risk for relapse and shorter time to PD compared to other histologic subtypes or CR. Rechallenge with ICI resulted in 57.3% DCR and 28.6% pooled CR rates (n=22, CR rate 28.6%, 95%CI 17.1 - 40.2, I 68%). Heterogeneity among studies was high, but subgroup analysis based on type of ICI used (anti-CTL4 and anti-PD1 inhibitor or anti-PD1 monotherapy) and type of study (RCTs or observational studies), along with sensitivity analyses did not reveal significant alterations in results. Discontinuation of ICIs in patients without progression is possible. Outcomes to rechallenge with ICIs may differ depending on the reason for discontinuation, but remains a considerable option. https://www.crd.york.ac.uk/prospero/, identifier CRD42024547792.

Background and Objectives: Dermoscopy is a non-invasive clinical tool that allows for the in vivo visualization of pigmented and non-pigmented structures in the epidermis and the papillary dermis. The standard handheld dermoscopy offers a magnification of 10×, whereas the videodermatoscopes can obtain a magnification of up to 140×. Recently, a new method called magnified dermoscopy was introduced, in which a magnification of 400× can be achieved. Materials and Methods: This review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting guidelines. Comprehensive research was conducted using the PubMed database on 9 June 2025, using the following keywords: “high magnification” or “super high magnification” or “optical super high magnification” or “400×”, and “dermoscopy” or “dermatoscopy”. Results: From a total of 237 records retrieved, 25 were found to be suitable for this review, and consisted of: four prospective studies, three retrospective studies, six case series, ten case reports and two image letters. Conclusions: This review summarizes the current knowledge on magnified dermoscopy, compiling existing data and exploring future perspectives for this emerging non-invasive diagnostic method.

The diagnosis of basal cell carcinoma (BCC) in dark phototypes can be a challenging task due to the lack of relevant clues and its variable presentation. In this regard, there is growing evidence that dermoscopy may benefit the recognition of BCC even for skin of color (SoC). The objective of this review is to provide an up-to-date overview on clinical and dermoscopic patterns of BCC in SoC, also comparing such findings with those of the main clinical mimickers reported in the literature. A comprehensive search of the literature through the PubMed electronic database was carried out in order to identify papers describing the clinical and dermoscopic features of BCC in dark phototypes (IV–VI). By finding macroscopic clinical presentations of BCCs in SoC patients and any possible clinical mimickers considered in the retrieved papers, we built a differential diagnosis list and analyzed the dermoscopic findings of such conditions to facilitate the diagnosis of BCC. BCC in darker skin may present as pigmented nodular lesions, pigmented patches or plaques, ulcers, erythematous nodular lesions, erythematous plaques or patches, or scar-like lesions, depending on its subtype and body site. The differential diagnosis for BCC in patients with SoC includes squamous cell carcinoma, melanoma, nevi, adnexal tumors and sebaceous keratosis. Additionally, it differs from that of Caucasians, as it also includes lesions less common in fair skin, such as dermatosis papulosa nigra, melanotrichoblastoma, and pigmented dermatofibrosarcoma protuberans, and excludes conditions like actinic keratosis and keratoacanthoma, which rarely appear in darker skin. The resulting differences also include infectious diseases such as deep cutaneous mycosis and inflammatory dermatoses. The most prevalent differentiating dermoscopic feature for BCC includes blue, black and gray dots, though arborizing vessels still remain the predominant BCC feature, even in dark phototypes. Diagnostic approach to BCC in dark-skinned patients varies due to the prevalence of dermoscopy findings associated with hyperpigmented structures. Clinicians should be aware of such points of differentiation for a proper management of this tumor in SoC.

Current melanoma prognostic tools have limited clinical use at the bedside, highlighting the need for more effective biomarkers. Dermatoscopy correlates with established prognostic markers obtained through invasive procedures. However, its direct predictive value for metastasis remains unexplored. In this multinational study, 30 dermatologists evaluated 776 dermatoscopic images of melanomas (stage IB and above) for predefined criteria including structures, colors and vessels. Extensive dermatoscopic ulceration and blue-white veil are associated with increased risk of metastasis in the total cohort and reduced recurrence-free survival in early-stage melanomas, while extensive regression is associated with reduced metastasis risk and improved recurrence-free survival. Three predictive models of metastasis: (1) dermatoscopic features only, (2) histopathologic features only, and (3) a combination of both demonstrate comparable prognostic accuracy. Here, we show that dermatoscopy may offer valuable prognostic insights into melanoma’s biological behavior before excision and help guide therapeutic decisions. Prospective validation in future trials is essential. Dermatoscopy is a common method to aid in diagnosis of melanoma, however, its utility in predicting metastasis is not fully known. Here, the authors leverage a cohort of 30 dermatologists to develop models to predict prognosis from dermatoscopic images.

Acquired perforating dermatoses (APD) represent a group of papulonodular skin disorders characterized by transepidermal elimination of dermal components, most frequently arising in patients with poorly controlled chronic systemic conditions such as diabetes mellitus (DM) and chronic renal failure (CRF). The four classical subtypes include acquired reactive perforating collagenosis (RPC), Kyrle’s disease (KD), elastosis perforans serpiginosa (EPS), and perforating folliculitis (PF). Owing to their rarity and the often-complex comorbidities of affected individuals, accurate diagnosis of APD may be challenging. In this context, dermoscopy has emerged as a valuable noninvasive tool that enhances diagnostic accuracy and supports clinical decision-making. This study aimed to characterize the dermoscopic features of APD through a case series and subsequent literature review. We present clinical and dermoscopic findings from a case series of 10 patients with APD followed by a literature review of 17 published case reports and 2 case series. The predominant dermoscopic pattern comprised a central yellow-to-brown structureless area, a surrounding white rim or a broader white structureless area with or without scaling, and an outer erythematous area containing dotted or hairpin vessels. Variations in these features appeared to reflect different stages of lesion evolution. The findings reinforce dermoscopy as a useful adjunct for the recognition, characterization, and monitoring of APD, providing additional insights into disease progression and contributing to improved diagnostic accuracy and clinical management.

Background and Objectives: Artificial intelligence (AI) has transitioned to an integral part of dermatology in only few years, yet perceptions of its use vary widely, reflecting diverse hopes, concerns, and perceived clinical utility. Materials and Methods: In this study, 300 dermatologists from 13 countries, representing a range of experience levels and AI usage statuses, were surveyed regarding the characteristics and applications of AI in dermatology. Results: Among respondents, 61.33% reported having used AI tools in clinical practice. Adoption of AI was observed across all age groups, countries, and experience levels. Analysis of the types of AI tools used revealed a strong reliance on general-purpose large language models (LLMs), with chatbots being the most frequently cited category, utilized by 58.15% of users. Younger clinicians demonstrated a significant preference for chatbots (p < 0.05). Country-specific patterns in AI adoption were also noted. The most highly rated expected benefit of AI in dermatology was improved diagnostic accuracy, while the primary concern centered on regulatory and ethical limitations, suggesting that the “AI revolution” in dermatology is currently constrained less by technical barriers and more by regulation considerations. Use of consent forms when AI use takes place was more frequently reported as mandatory by dermatologists who had never used AI, reflecting heightened caution among non-users (p = 0.03). Additionally, 75% of respondents agreed that formal training in AI is necessary, highlighting a significant gap in traditional medical education regarding emerging technologies.