Melanoma 2.0. Skin cancer as a paradigm for emerging diagnostic technologies, computational modelling and artificial intelligence.

We live in an unprecedented time in oncology. We have accumulated samples and cases in cohorts larger and more complex than ever before. New technologies are available for quantifying solid or liquid samples at the molecular level. At the same time, we are now equipped with the computational power necessary to handle this enormous amount of quantitative data. Computational models are widely used helping us to substantiate and interpret data. Under the label of systems and precision medicine, we are putting all these developments together to improve and personalize the therapy of cancer. In this review, we use melanoma as a paradigm to present the successful application of these technologies but also to discuss possible future developments in patient care linked to them. Melanoma is a paradigmatic case for disruptive improvements in therapies, with a considerable number of metastatic melanoma patients benefiting from novel therapies. Nevertheless, a large proportion of patients does not respond to therapy or suffers from adverse events. Melanoma is an ideal case study to deploy advanced technologies not only due to the medical need but also to some intrinsic features of melanoma as a disease and the skin as an organ. From the perspective of data acquisition, the skin is the ideal organ due to its accessibility and suitability for many kinds of advanced imaging techniques. We put special emphasis on the necessity of computational strategies to integrate multiple sources of quantitative data describing the tumour at different scales and levels.

European consensus-based interdisciplinary guideline for diagnosis, treatment and prevention of actinic keratoses, epithelial UV-induced dysplasia and field cancerization on behalf of European Association of Dermato-Oncology, European Dermatology Forum, European Academy of Dermatology and Venereology and Union of Medical Specialists (Union Européenne des Médecins Spécialistes).

A collaboration of multidisciplinary experts from the European Association of Dermato-Oncology, the European Dermatology Forum, the European Academy of Dermatology and Venereology, and the European Union of Medical Specialists was formed to develop European recommendations on AK diagnosis and treatment, based on current literature and expert consensus. This guideline addresses the epidemiology, diagnostics, risk stratification and treatments in immunocompetent as well as immunosuppressed patients. Actinic keratoses (AK) are potential precursors of cutaneous squamous cell carcinoma (cSCC) and display typical histopathologic and immunohistochemical features of this malignancy in an early stage. They can develop into cSSC in situ and become invasive in a low percentage of cases. AK is the most frequent neoplasia in white populations, frequently occurring within a cancerous field induced by ultraviolet radiation. Since it cannot be predicted, which lesion will progress to cSCC and when treatment is usually recommended. The diagnosis of AK and field cancerization is made by clinical examination. Dermatoscopy, confocal microscopy, optical coherence tomography or line-field confocal-OCT can help in the differential diagnosis of AK and other skin neoplasms. A biopsy is indicated in clinically and/or dermatoscopically suspicious and/or treatment-refractory lesions. The choice of treatment depends on patients' and lesion characteristics. For single non-hyperkeratotic lesions, the treatment can be started upon patient's request with destructive treatments or topical treatments. For multiple lesions, field cancerization treatment is advised with topical treatments and photodynamic therapy. Preventive measures such as sun protection, self-examination and repeated field cancerization treatments of previously affected skin areas in high-risk patients are advised.

Identifying biomarkers and novel therapeutic targets in uveal melanoma.

Uveal melanoma (UM) is an orphan cancer despite being the most common eye tumor in adults. Patients often present to skin cancer centers for treatment of metastatic disease although there are significant genetic, biological, and clinical differences from cutaneous melanoma. The treatments most commonly used for metastatic UM are tebentafusp and combined immune checkpoint blockade, both of which yield low response rates and may be accompanied by high treatment costs and significant immune-related toxicities. Thus, it is of paramount importance to identify biomarkers and clinical profiles predictive of treatment response and to find novel therapeutic targets. The use of immune checkpoint blockade showed more favorable outcomes in patients with extrahepatic disease and normal levels of serum lactate dehydrogenase in a panel of retrospective studies, making its use more reasonable in this subgroup. To identify novel drug targets, we will analyze the expression and relevance of neural crest transcription factors in patient bio-specimens using next-generation nanopore sequencing. Computer algorithms and network-based analysis will facilitate the identification of druggable targets which will subsequently be validated in patient-derived short-term cell cultures. This approach will help to find novel and personalized treatments for UM.

Evaluating the Efficacy and Safety of 4% 5-Fluorouracil Cream in Patients with Actinic Keratosis: An Expert Opinion.

Actinic keratosis is a lesion that develops in sun-exposed areas of the skin and is considered to be a precancerous condition or an early in situ squamous cell carcinoma. Treatment of actinic keratosis is important for reducing skin cancer risk, with treatment choice based on patient-, lesion- and treatment-related considerations. Of the topical treatments used for field-directed therapy, those containing 5-fluorouracil are among the most effective and widely prescribed. The most recently developed topical 5-fluorouracil preparation (Tolak®; Pierre Fabre, France) contains 4% 5-fluorouracil in an aqueous cream. This narrative review discusses data on 4% 5-fluorouracil cream to treat actinic keratosis, and provides the authors' expert opinion on issues associated with it use. The effect of the cream has been evaluated in phase 2 and 3 trials of adult patients with actinic keratosis on the face, ears or scalp. These trials included patients with severe baseline disease, defined by high lesion counts and large-size treatment fields, which possibly affected the proportion of patients who were able to achieve complete clearance. Other efficacy parameters (e.g. percentage change in lesion count, ≥ 75% clearance of lesions or clinically significant changes in validated severity scales) should also be assessed to fully evaluate 4% 5-fluorouracil treatment efficacy in these patients. Nevertheless, 4% 5-fluorouracil is associated with high efficacy, a low level of recurrence and a satisfactory safety profile.

Immune checkpoint inhibition and targeted therapy for melanoma: A patient-oriented cross-sectional comparative multicentre study.

BACKGROUND: Choosing the adequate systemic treatment for melanoma is driven by clinical parameters and personal preferences. OBJECTIVE: Evaluation of the impact of disease and treatment on the daily life of patients receiving systemic therapy for melanoma. METHODS: A German-wide, cross-sectional comparative study was conducted at 13 specialized skin cancer centres from 08/2020 to 03/2021. A questionnaire was distributed to assess patients' perception of disease and symptoms, the impact of their current treatment on quality of life (QOL) and activities, adverse events (AEs), therapeutic visits, as well as believe in and satisfaction with their current systemic melanoma treatment. Patient-reported outcomes (PROs) were rated on a continuous numerical rating scale or selected from a given list. RESULTS: Four hundred and fourteen patients with systemic melanoma therapy were included. 359 (87%) received immune checkpoint inhibition (ICI) and 55 (13%) targeted therapy (TT). About 1/3 of patients were adjuvantly treated, the remaining because of unresectable/metastatic melanoma. In subgroup analyses, only in the adjuvant setting, TT patients reported a significant decrease in their treatment associated QOL compared to patients with ICI (p = 0.02). Patients with TT were 1.9 times more likely to report AEs than patients with ICI, a difference being significant just for the adjuvant setting (p = 0.01). ICI treatment intervals differed significantly between adjuvant and unresectable/metastatic setting (p = 0.04), though all patients, regardless of their specific ICI drug, evaluated their treatment frequency as adequate. TT patients with dabrafenib/trametinib (n = 37) or encorafenib/binimetinib (n = 15) did not differ regarding the strain of daily pill intake. Patients older than 63 years rated various PROs better than younger patients. CONCLUSIONS: Patients evaluated their treatment mainly positively. ICI might be preferred over TT regarding QOL and patient-reported AEs in the adjuvant setting. Older melanoma patients appeared to be less impacted by their disease and more satisfied with their treatment.

Standardized Computer-Assisted Analysis of PRAME Immunoreactivity in Dysplastic Nevi and Superficial Spreading Melanomas.

PRAME (PReferentially expressed Antigen in MElanoma) is a cancer testis antigen that is frequently expressed in melanoma compared to benign melanocytic proliferations and nevi. However, the interpretation of the intensity and distribution of PRAME immunostaining is not standardized a lot, which makes interpretation difficult. PRAME-stained histological slides of superficial spreading melanomas (SSM) and dysplastic nevi (DN) were digitized and analyzed using the digital pathology and image platform QuPath. t-tests and ROC AUCs were performed with SPSS. A p-value of <0.05 was used for statistical significance, and a ROC AUC score of >0.8 was considered a good result. A cut-off score was defined in an evaluation cohort and subsequently analyzed in an independent validation cohort. In total, 81 PRAME-stained specimens were included. The evaluation cohort included 32 (50%) SSM and 32 (50%) DN, and the mean of PRAME-positive cells/mm2 for the entire lesion was 455.3 (SD 428.2) in SSM and 60.5 (SD 130.1; p < 0.001) in DN. The ROC AUC of PRAME-positive cells of the entire lesion was 0.866, and in the epidermis it was 0.901. The defined cut-off score to distinguish between DN and SSM was 97.67 cells/mm2. In the validation cohort, 16 out of 17 cases (94.1%) were correctly classified by the cut-off score. The computer-aided assessment of PRAME immunostaining is a useful tool in dermatopathology to distinguish between DN and SSM. Lesions with a moderate expression and indifferent morphologic features will remain a challenge for dermatopathologists.

Standardized Computer-Assisted Analysis of 5-hmC Immunoreactivity in Dysplastic Nevi and Superficial Spreading Melanomas.

5-Hydroxymethylcytosine (5-hmC) is an important intermediate of DNA demethylation. Hypomethylation of DNA is frequent in cancer, resulting in deregulation of 5-hmC levels in melanoma. However, the interpretation of the intensity and distribution of 5-hmC immunoreactivity is not very standardized, which makes its interpretation difficult. In this study, 5-hmC-stained histological slides of superficial spreading melanomas (SSM) and dysplastic compound nevi (DN) were digitized and analyzed using the digital pathology and image platform QuPath. Receiver operating characteristic/area under the curve (ROCAUC) and t-tests were performed. A p-value of <0.05 was used for statistical significance, and a ROCAUC score of >0.8 was considered a "good" result. In total, 92 5-hmC-stained specimens were analyzed, including 42 SSM (45.7%) and 50 DN (54.3%). The mean of 5-hmC-positive cells/mm2 for the epidermis and dermo-epidermal junction and the entire lesion differed significantly between DN and SSM (p = 0.002 and p = 0.006, respectively) and showed a trend towards higher immunoreactivity in the dermal component (p = 0.069). The ROCAUC of 5-hmC-positive cells of the epidermis and dermo-epidermal junction was 0.79, for the dermis 0.74, and for the entire lesion 0.76. These results show that the assessment of the epidermal with junctional expression of 5-hmC is slightly superior to dermal immunoreactivity in distinguishing between DN and SSM.

One Website to Gather them All: Usability Testing of the New German SKin Cancer INFOrmation (SKINFO) Website-A Mixed-methods Approach.

Skin cancer patients increasingly search the internet to acquire disease-related information. However, information on the internet may be misleading. Recently, SKINFO has been launched, a website exclusively created for German-speaking skin cancer patients providing information as well as additional resources of verified quality. Here, we describe the results of the first usability test of SKINFO using a mixed-methods approach. Ten adult patients with skin cancer were recruited for usability testing in the skin cancer units of the University Hospitals of Erlangen and Dresden, Germany. Testing consisted of three different scenarios where patients were asked to find specific information on the SKINFO website guided by the think-aloud method. Descriptive analysis and content analyses were performed. All patients would recommend SKINFO and appreciated its content, design, and structure. Think-aloud analysis identified the topics layout, navigation, and content and structure which would benefit from refinement. Major criticism included the navigation through the website, and the desire for more specific information addressing patients' relatives and the latest, up-to-date information. Overall, usability testing showed that the unique web-based information platform has the potential to support patients coping with skin cancer and thus strengthen informed decision-making.

Cutaneous squamous cell carcinoma: state of the art, perspectives and unmet needs.

Squamous cell carcinoma of the skin (cSCC) is one of the most common cancers of the Caucasian population and accounts for 20% of all cutaneous tumors. An S3 guideline from the German Guideline Program in Oncology has been available since 2019 and was updated in 2022. The diagnosis of cSCC is based on clinical examination. Excision and histological confirmation are required for clinically suspicious lesions to allow for prognostic assessment and correct treatment. The treatment of first choice is excision with complete histological assessment of the surgical margins. Adjuvant radiation therapy may be considered if there is a high risk of recurrence. The immune checkpoint inhibitor cemiplimab is approved and recommended as the treatment of first choice for locally advanced or metastatic cSCC in Europe. If contraindications are present, chemotherapy, EGFR inhibitors, or palliative radiation therapy may be used. Surveillance should be performed in a risk-stratified manner and includes a dermatological control supplemented by sonography examinations in high-risk patients. Much research is still needed for solid organ transplant patients, concomitant hematologic diseases, and cSCC showing primary or acquired resistance to immunotherapies. Current developments include new drug combinations, intralesional therapies alone or in combination with immune checkpoint inhibitors, and neoadjuvant approaches.

S3 guideline "actinic keratosis and cutaneous squamous cell carcinoma" - update 2023, part 2: epidemiology and etiology, diagnostics, surgical and systemic treatment of cutaneous squamous cell carcinoma (cSCC), surveillance and prevention.

Actinic keratosis (AK) are common lesions in light-skinned individuals that can potentially progress to cutaneous squamous cell carcinoma (cSCC). Both conditions may be associated with significant morbidity and constitute a major disease burden, especially among the elderly. To establish an evidence-based framework for clinical decision making, the guideline "actinic keratosis and cutaneous squamous cell carcinoma" was updated and expanded by the topics cutaneous squamous cell carcinoma in situ (Bowen's disease) and actinic cheilitis. The guideline is aimed at dermatologists, general practitioners, ear nose and throat specialists, surgeons, oncologists, radiologists and radiation oncologists in hospitals and office-based settings, as well as other medical specialties, policy makers and insurance funds involved in the diagnosis and treatment of patients with AK and cSCC. A separate guideline exists for patients and their relatives. In this part, we will address aspects relating to epidemiology and etiology, diagnostics, surgical and systemic treatment of cutaneous squamous cell carcinoma (cSCC), surveillance and prevention.

A disease network-based deep learning approach for characterizing melanoma.

Multiple types of genomic variations are present in cutaneous melanoma and some of the genomic features may have an impact on the prognosis of the disease. The access to genomics data via public repositories such as The Cancer Genome Atlas (TCGA) allows for a better understanding of melanoma at the molecular level, therefore making characterization of substantial heterogeneity in melanoma patients possible. Here, we proposed an approach that integrates genomics data, a disease network, and a deep learning model to classify melanoma patients for prognosis, assess the impact of genomic features on the classification and provide interpretation to the impactful features. We integrated genomics data into a melanoma network and applied an autoencoder model to identify subgroups in TCGA melanoma patients. The model utilizes communities identified in the network to effectively reduce the dimensionality of genomics data into a patient score profile. Based on the score profile, we identified three patient subtypes that show different survival times. Furthermore, we quantified and ranked the impact of genomic features on the patient score profile using a machine-learning technique. Follow-up analysis of the top-ranking features provided us with the biological interpretation of them at both pathway and molecular levels, such as their mutation and interactome profiles in melanoma and their involvement in pathways associated with signaling transduction, immune system and cell cycle. Taken together, we demonstrated the ability of the approach to identify disease subgroups using a deep learning model that captures the most relevant information of genomics data in the melanoma network.

Clinical determinants of long-term survival in metastatic uveal melanoma.

This study aimed to identify prognostic factors in patients with metastatic uveal melanoma (UM) that were associated with long-term survival in a real-world setting. A total of 94 patients with metastatic UM were included from German skin cancer centers and the German national skin cancer registry (ADOReg). Data were analyzed for the response to treatment, progression-free survival, and overall survival (OS). Prognostic factors were explored with univariate Cox regression, log-rank, and χ2-tests. Identified factors were subsequently validated after the population was divided into two cohorts of short-term survival (< 2 years OS, cohort A, n = 50) and long-term survival (> 2 years OS, cohort B, n = 44). A poor ECOG performance status (hazard ratio [HR] 2.0, 95% confidence interval [CI] 1.0-3.9) and elevated serum LDH (HR 2.0, 95% CI 1.0-3.8) were associated with a poor OS, whereas a good response to immune checkpoint blockade (ICB, p < 0.001), radiation therapy (p < 0.001), or liver-directed treatments (p = 0.01) were associated with a prolonged OS. Long-term survivors (cohort B) showed a higher median number of organs affected by metastasis (p < 0.001), while patients with liver metastases only were more common in cohort A (40% vs. 9%; p = 0.002). A partial response to ICB was observed in 16% (12/73), being 21% (8/38) for combined ICB, 17% (1/6) for single CTLA4 inhibition, and 10% (3/29) for single PD1 inhibition. One complete response occurred in cohort B with combined ICB. We conclude that the response to ICB and the presence of extrahepatic disease were favorable prognostic factors for long-term survival.

HDAC2 Is Involved in the Regulation of BRN3A in Melanocytes and Melanoma.

The neural crest transcription factor BRN3A is essential for the proliferation and survival of melanoma cells. It is frequently expressed in melanoma but not in normal melanocytes or benign nevi. The mechanisms underlying the aberrant expression of BRN3A are unknown. Here, we investigated the epigenetic regulation of BRN3A in melanocytes and melanoma cell lines treated with DNA methyltransferase (DNMT), histone acetyltransferase (HAT), and histone deacetylase (HDAC) inhibitors. DNMT and HAT inhibition did not significantly alter BRN3A expression levels, whereas panHDAC inhibition by trichostatin A led to increased expression. Treatment with the isoform-specific HDAC inhibitor mocetinostat, but not with PCI-34051, also increased BRN3A expression levels, suggesting that class I HDACs HDAC1, HDAC2, and HDAC3, and class IV HDAC11, were involved in the regulation of BRN3A expression. Transient silencing of HDACs 1, 2, 3, and 11 by siRNAs revealed that, specifically, HDAC2 inhibition was able to increase BRN3A expression. ChIP-Seq analysis uncovered that HDAC2 inhibition specifically increased H3K27ac levels at a distal enhancer region of the BRN3A gene. Altogether, our data suggest that HDAC2 is a key epigenetic regulator of BRN3A in melanocytes and melanoma cells. These results highlight the importance of epigenetic mechanisms in regulating melanoma oncogenes.

"I Feel I'm in Best Hands with You!": A Survey of Patient Satisfac-tion in a German University Skin Cancer Centre.

An important measure of hospital quality is the satisfaction of patients. The aim of this cross-sectional study, performed in the dermato-oncology unit of the university hospital in Erlangen, Germany, was to assess skin cancer patients' degree of satisfaction with healthcare services. Self-administered questionnaires on patient satisfaction regarding contact with staff, need for information, and recommendation of the skin cancer centre were distributed in the day-care unit and the outpatient department to patients between April and June 2017. Results were reported descriptively and subgroup differences were explored using the Mann-Whitney U test, binary logistic regression, or χ2 test. Overall, 496 of 571 questionnaires were returned (86.9%). The median of all satisfaction items ranged between 1 (very good) and 2 (good). The majority of patients wanted more detailed information about skin cancer (46.7%, 142/304). Long waiting times were often criticized (22.8%; 80/351). Particular attention in addressing specific needs and fears may further increase patient satisfaction.

Integrating Patient Data Into Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review.

BACKGROUND: Recent years have been witnessing a substantial improvement in the accuracy of skin cancer classification using convolutional neural networks (CNNs). CNNs perform on par with or better than dermatologists with respect to the classification tasks of single images. However, in clinical practice, dermatologists also use other patient data beyond the visual aspects present in a digitized image, further increasing their diagnostic accuracy. Several pilot studies have recently investigated the effects of integrating different subtypes of patient data into CNN-based skin cancer classifiers. OBJECTIVE: This systematic review focuses on the current research investigating the impact of merging information from image features and patient data on the performance of CNN-based skin cancer image classification. This study aims to explore the potential in this field of research by evaluating the types of patient data used, the ways in which the nonimage data are encoded and merged with the image features, and the impact of the integration on the classifier performance. METHODS: Google Scholar, PubMed, MEDLINE, and ScienceDirect were screened for peer-reviewed studies published in English that dealt with the integration of patient data within a CNN-based skin cancer classification. The search terms skin cancer classification, convolutional neural network(s), deep learning, lesions, melanoma, metadata, clinical information, and patient data were combined. RESULTS: A total of 11 publications fulfilled the inclusion criteria. All of them reported an overall improvement in different skin lesion classification tasks with patient data integration. The most commonly used patient data were age, sex, and lesion location. The patient data were mostly one-hot encoded. There were differences in the complexity that the encoded patient data were processed with regarding deep learning methods before and after fusing them with the image features for a combined classifier. CONCLUSIONS: This study indicates the potential benefits of integrating patient data into CNN-based diagnostic algorithms. However, how exactly the individual patient data enhance classification performance, especially in the case of multiclass classification problems, is still unclear. Moreover, a substantial fraction of patient data used by dermatologists remains to be analyzed in the context of CNN-based skin cancer classification. Further exploratory analyses in this promising field may optimize patient data integration into CNN-based skin cancer diagnostics for patients' benefits.

How Neural Crest Transcription Factors Contribute to Melanoma Heterogeneity, Cellular Plasticity, and Treatment Resistance.

Cutaneous melanoma represents one of the deadliest types of skin cancer. The prognosis strongly depends on the disease stage, thus early detection is crucial. New therapies, including BRAF and MEK inhibitors and immunotherapies, have significantly improved the survival of patients in the last decade. However, intrinsic and acquired resistance is still a challenge. In this review, we discuss two major aspects that contribute to the aggressiveness of melanoma, namely, the embryonic origin of melanocytes and melanoma cells and cellular plasticity. First, we summarize the physiological function of epidermal melanocytes and their development from precursor cells that originate from the neural crest (NC). Next, we discuss the concepts of intratumoral heterogeneity, cellular plasticity, and phenotype switching that enable melanoma to adapt to changes in the tumor microenvironment and promote disease progression and drug resistance. Finally, we further dissect the connection of these two aspects by focusing on the transcriptional regulators MSX1, MITF, SOX10, PAX3, and FOXD3. These factors play a key role in NC initiation, NC cell migration, and melanocyte formation, and we discuss how they contribute to cellular plasticity and drug resistance in melanoma.

Comparative analysis of the phototoxicity induced by BRAF inhibitors and alleviation through antioxidants.

BACKGROUND: Small molecules tackling mutated BRAF (BRAFi) are an important mainstay of targeted therapy in a variety of cancers including melanoma. Albeit commonly reported as side effect, the phototoxic potential of many BRAFi is poorly characterized. In this study, we evaluated the phototoxicity of 17 distinct agents and investigated whether BRAFi-induced phototoxicity can be alleviated by antioxidants. METHODS: The ultraviolet (UV) light absorbance of 17 BRAFi was determined. Their phototoxic potential was investigated independently with a reactive oxygen species (ROS) and the 3T3 neutral red uptake (NRU) assay in vitro. To test for a possible phototoxicity alleviation by antioxidants, vitamin C, vitamin E phosphate, trolox, and glutathione (GSH) were added to the 3T3 assay of selected inhibitors. RESULTS: The highest cumulative absorbance for both UVA and UVB was detected for vemurafenib. The formation of ROS was more pronounced for all compounds after irradiation with UVA than with UVB. In the 3T3 NRU assay, 8 agents were classified as phototoxic, including vemurafenib, dabrafenib, and encorafenib. There was a significant correlation between the formation of singlet oxygen (P = .026) and superoxide anion (P < .001) and the phototoxicity observed in the 3T3 NRU assay. The phototoxicity of vemurafenib was fully rescued in the 3T3 NRU assay after GSH was added at different concentrations. CONCLUSION: Our study confirms that most of the BRAF inhibitors exhibited a considerable phototoxic potential, predominantly after exposure to UVA. GSH may help treat and prevent the phototoxicity induced by vemurafenib.

Implications of the COVID-19 Pandemic for the Development and Update of Clinical Practice Guidelines: Viewpoint.

Following the rapid spread of a new type of coronavirus (SARS-CoV-2), nearly all countries have introduced temporary restrictions affecting daily life, with "social distancing" as a key intervention for slowing the spread of the virus. Despite the pandemic, the development or actualization of medical guidelines, especially in the rapidly changing field of oncology, needs to be continued to provide up-to-date evidence- and consensus-based recommendations for shared decision making and maintaining the treatment quality for patients. In this viewpoint, we describe the potential strengths and limitations of online conferences for medical guideline development. This viewpoint will assist guideline developers in evaluating whether online conferences are an appropriate tool for their guideline conference and audience.

Artificial Intelligence and Its Effect on Dermatologists' Accuracy in Dermoscopic Melanoma Image Classification: Web-Based Survey Study.

BACKGROUND: Early detection of melanoma can be lifesaving but this remains a challenge. Recent diagnostic studies have revealed the superiority of artificial intelligence (AI) in classifying dermoscopic images of melanoma and nevi, concluding that these algorithms should assist a dermatologist's diagnoses. OBJECTIVE: The aim of this study was to investigate whether AI support improves the accuracy and overall diagnostic performance of dermatologists in the dichotomous image-based discrimination between melanoma and nevus. METHODS: Twelve board-certified dermatologists were presented disjoint sets of 100 unique dermoscopic images of melanomas and nevi (total of 1200 unique images), and they had to classify the images based on personal experience alone (part I) and with the support of a trained convolutional neural network (CNN, part II). Additionally, dermatologists were asked to rate their confidence in their final decision for each image. RESULTS: While the mean specificity of the dermatologists based on personal experience alone remained almost unchanged (70.6% vs 72.4%; P=.54) with AI support, the mean sensitivity and mean accuracy increased significantly (59.4% vs 74.6%; P=.003 and 65.0% vs 73.6%; P=.002, respectively) with AI support. Out of the 10% (10/94; 95% CI 8.4%-11.8%) of cases where dermatologists were correct and AI was incorrect, dermatologists on average changed to the incorrect answer for 39% (4/10; 95% CI 23.2%-55.6%) of cases. When dermatologists were incorrect and AI was correct (25/94, 27%; 95% CI 24.0%-30.1%), dermatologists changed their answers to the correct answer for 46% (11/25; 95% CI 33.1%-58.4%) of cases. Additionally, the dermatologists' average confidence in their decisions increased when the CNN confirmed their decision and decreased when the CNN disagreed, even when the dermatologists were correct. Reported values are based on the mean of all participants. Whenever absolute values are shown, the denominator and numerator are approximations as every dermatologist ended up rating a varying number of images due to a quality control step. CONCLUSIONS: The findings of our study show that AI support can improve the overall accuracy of the dermatologists in the dichotomous image-based discrimination between melanoma and nevus. This supports the argument for AI-based tools to aid clinicians in skin lesion classification and provides a rationale for studies of such classifiers in real-life settings, wherein clinicians can integrate additional information such as patient age and medical history into their decisions.

Merkel Cell Carcinoma of the Head and Neck Compared to Other Anatomical Sites in a Real-World Setting: Importance of Surgical Therapy for Facial Tumors.

Merkel cell carcinoma (MCC) is a rare and aggressive neuroendocrine skin tumor with a high propensity for nodal involvement, local recurrence, and distant metastases. Up to 50% of MCC arises on head and neck (HN), which may impede oncological treatment due to insufficiently wide excisions and a lower rate of sentinel lymph node detection due to more complicated lymph drainage. Several studies have compared the clinical outcome of HN-MCC with those of non-head and neck (NHN) MCC yielding inconsistent results. This single-center, retrospective analysis compared the clinical outcome of 26 HN-MCC patients with 30 NHN-MCC patients. Overall survival (OS) and disease-free survival (DFS) were calculated with the Kaplan-Meier method assuming proportional hazards. The mean resection margins were 1.6 and 2.0 cm for the HN and NHN cohort, respectively. Local relapses were more frequently observed in patients with HN-MCC (19 vs. 10%). Patients with HN-MCC had a median OS of 4.3 years compared with 7.5 years in patients with NHN-MCC (p = 0.277). The median OS by tumor stage was 11, 3, 2, and 3 years in stage I, II, III, and IV disease, respectively (p = 0.009). The median DFS in HN-MCC was 10 years and not reached in the cohort with NHN-MCC patients (p = 0.939). Our data suggest a trend toward poorer outcomes of HN-MCC compared with NHN-MCC. Patients with MCC on the head and neck carry a higher risk for local relapse, requiring resolute surgical treatment also in facial localizations at early stages.