Automatized self-supervised learning for skin lesion screening.

Melanoma, the deadliest form of skin cancer, has seen a steady increase in incidence rates worldwide, posing a significant challenge to dermatologists. Early detection is crucial for improving patient survival rates. However, performing total body screening (TBS), i.e., identifying suspicious lesions or ugly ducklings (UDs) by visual inspection, can be challenging and often requires sound expertise in pigmented lesions. To assist users of varying expertise levels, an artificial intelligence (AI) decision support tool was developed. Our solution identifies and characterizes UDs from real-world wide-field patient images. It employs a state-of-the-art object detection algorithm to locate and isolate all skin lesions present in a patient's total body images. These lesions are then sorted based on their level of suspiciousness using a self-supervised AI approach, tailored to the specific context of the patient under examination. A clinical validation study was conducted to evaluate the tool's performance. The results demonstrated an average sensitivity of 95% for the top-10 AI-identified UDs on skin lesions selected by the majority of experts in pigmented skin lesions. The study also found that the tool increased dermatologists' confidence when formulating a diagnosis, and the average majority agreement with the top-10 AI-identified UDs reached 100% when assisted by our tool. With the development of this AI-based decision support tool, we aim to address the shortage of specialists, enable faster consultation times for patients, and demonstrate the impact and usability of AI-assisted screening. Future developments will include expanding the dataset to include histologically confirmed melanoma and validating the tool for additional body regions.

International Skin Imaging Collaboration-Designated Diagnoses (ISIC-DX): Consensus terminology for lesion diagnostic labeling.

BACKGROUND: A common terminology for diagnosis is critically important for clinical communication, education, research and artificial intelligence. Prevailing lexicons are limited in fully representing skin neoplasms. OBJECTIVES: To achieve expert consensus on diagnostic terms for skin neoplasms and their hierarchical mapping. METHODS: Diagnostic terms were extracted from textbooks, publications and extant diagnostic codes. Terms were hierarchically mapped to super-categories (e.g. 'benign') and cellular/tissue-differentiation categories (e.g. 'melanocytic'), and appended with pertinent-modifiers and synonyms. These terms were evaluated using a modified-Delphi consensus approach. Experts from the International-Skin-Imaging-Collaboration (ISIC) were surveyed on agreement with terms and their hierarchical mapping; they could suggest modifying, deleting or adding terms. Consensus threshold was >75% for the initial rounds and >50% for the final round. RESULTS: Eighteen experts completed all Delphi rounds. Of 379 terms, 356 (94%) reached consensus in round one. Eleven of 226 (5%) benign-category terms, 6/140 (4%) malignant-category terms and 6/13 (46%) indeterminate-category terms did not reach initial agreement. Following three rounds, final consensus consisted of 362 terms mapped to 3 super-categories and 41 cellular/tissue-differentiation categories. CONCLUSIONS: We have created, agreed upon, and made public a taxonomy for skin neoplasms and their hierarchical mapping. Further study will be needed to evaluate the utility and completeness of the lexicon.

Expert Agreement on the Presence and Spatial Localization of Melanocytic Features in Dermoscopy.

Dermoscopy aids in melanoma detection; however, agreement on dermoscopic features, including those of high clinical relevance, remains poor. In this study, we attempted to evaluate agreement among experts on exemplar images not only for the presence of melanocytic-specific features but also for spatial localization. This was a cross-sectional, multicenter, observational study. Dermoscopy images exhibiting at least 1 of 31 melanocytic-specific features were submitted by 25 world experts as exemplars. Using a web-based platform that allows for image markup of specific contrast-defined regions (superpixels), 20 expert readers annotated 248 dermoscopic images in collections of 62 images. Each collection was reviewed by five independent readers. A total of 4,507 feature observations were performed. Good-to-excellent agreement was found for 14 of 31 features (45.2%), with eight achieving excellent agreement (Gwet's AC >0.75) and seven of them being melanoma-specific features. These features were peppering/granularity (0.91), shiny white streaks (0.89), typical pigment network (0.83), blotch irregular (0.82), negative network (0.81), irregular globules (0.78), dotted vessels (0.77), and blue-whitish veil (0.76). By utilizing an exemplar dataset, a good-to-excellent agreement was found for 14 features that have previously been shown useful in discriminating nevi from melanoma. All images are public (www.isic-archive.com) and can be used for education, scientific communication, and machine learning experiments.

Position statement of the EADV Artificial Intelligence (AI) Task Force on AI-assisted smartphone apps and web-based services for skin disease.

BACKGROUND: As the use of smartphones continues to surge globally, mobile applications (apps) have become a powerful tool for healthcare engagement. Prominent among these are dermatology apps powered by Artificial Intelligence (AI), which provide immediate diagnostic guidance and educational resources for skin diseases, including skin cancer. OBJECTIVE: This article, authored by the EADV AI Task Force, seeks to offer insights and recommendations for the present and future deployment of AI-assisted smartphone applications (apps) and web-based services for skin diseases with emphasis on skin cancer detection. METHODS: An initial position statement was drafted on a comprehensive literature review, which was subsequently refined through two rounds of digital discussions and meticulous feedback by the EADV AI Task Force, ensuring its accuracy, clarity and relevance. RESULTS: Eight key considerations were identified, including risks associated with inaccuracy and improper user education, a decline in professional skills, the influence of non-medical commercial interests, data security, direct and indirect costs, regulatory approval and the necessity of multidisciplinary implementation. Following these considerations, three main recommendations were formulated: (1) to ensure user trust, app developers should prioritize transparency in data quality, accuracy, intended use, privacy and costs; (2) Apps and web-based services should ensure a uniform user experience for diverse groups of patients; (3) European authorities should adopt a rigorous and consistent regulatory framework for dermatology apps to ensure their safety and accuracy for users. CONCLUSIONS: The utilisation of AI-assisted smartphone apps and web-based services in diagnosing and treating skin diseases has the potential to greatly benefit patients in their dermatology journeys. By prioritising innovation, fostering collaboration and implementing effective regulations, we can ensure the successful integration of these apps into clinical practice.

Saliency-Enhanced Content-Based Image Retrieval for Diagnosis Support in Dermatology Consultation: Reader Study.

BACKGROUND: Previous research studies have demonstrated that medical content image retrieval can play an important role by assisting dermatologists in skin lesion diagnosis. However, current state-of-the-art approaches have not been adopted in routine consultation, partly due to the lack of interpretability limiting trust by clinical users. OBJECTIVE: This study developed a new image retrieval architecture for polarized or dermoscopic imaging guided by interpretable saliency maps. This approach provides better feature extraction, leading to better quantitative retrieval performance as well as providing interpretability for an eventual real-world implementation. METHODS: Content-based image retrieval (CBIR) algorithms rely on the comparison of image features embedded by convolutional neural network (CNN) against a labeled data set. Saliency maps are computer vision-interpretable methods that highlight the most relevant regions for the prediction made by a neural network. By introducing a fine-tuning stage that includes saliency maps to guide feature extraction, the accuracy of image retrieval is optimized. We refer to this approach as saliency-enhanced CBIR (SE-CBIR). A reader study was designed at the University Hospital Zurich Dermatology Clinic to evaluate SE-CBIR's retrieval accuracy as well as the impact of the participant's confidence on the diagnosis. RESULTS: SE-CBIR improved the retrieval accuracy by 7% (77% vs 84%) when doing single-lesion retrieval against traditional CBIR. The reader study showed an overall increase in classification accuracy of 22% (62% vs 84%) when the participant is provided with SE-CBIR retrieved images. In addition, the overall confidence in the lesion's diagnosis increased by 24%. Finally, the use of SE-CBIR as a support tool helped the participants reduce the number of nonmelanoma lesions previously diagnosed as melanoma (overdiagnosis) by 53%. CONCLUSIONS: SE-CBIR presents better retrieval accuracy compared to traditional CBIR CNN-based approaches. Furthermore, we have shown how these support tools can help dermatologists and residents improve diagnosis accuracy and confidence. Additionally, by introducing interpretable methods, we should expect increased acceptance and use of these tools in routine consultation.

Delphi Consensus Among International Experts on the Diagnosis, Management, and Surveillance for Lentigo Maligna.

INTRODUCTION: Melanoma of the lentigo maligna (LM) type is challenging. There is lack of consensus on the optimal diagnosis, treatment, and follow-up. OBJECTIVES: To obtain general consensus on the diagnosis, treatment, and follow-up for LM. METHODS: A modified Delphi method was used. The invited participants were either members of the International Dermoscopy Society, academic experts, or authors of published articles relating to skin cancer and melanoma. Participants were required to respond across three rounds using a 4-point Likert scale). Consensus was defined as >75% of participants agreeing/strongly agreeing or disagreeing/strongly disagreeing. RESULTS: Of the 31 experts invited to participate in this Delphi study, 29 participants completed Round 1 (89.9% response rate), 25/31 completed Round 2 (77.5% response rate), and 25/31 completed Round 3 (77.5% response rate). Experts agreed that LM diagnosis should be based on a clinical and dermatoscopic approach (92%) followed by a biopsy. The most appropriate primary treatment of LM was deemed to be margin-controlled surgery (83.3%), although non-surgical modalities, especially imiquimod, were commonly used either as alternative off-label primary treatment in selected patients or as adjuvant therapy following surgery; 62% participants responded life-long clinical follow-up was needed for LM. CONCLUSIONS: Clinical and histological diagnosis of LM is challenging and should be based on macroscopic, dermatoscopic, and RCM examination followed by a biopsy. Different treatment modalities and follow-up should be carefully discussed with the patient.

Expert Consensus Statement on Proficiency Standards for Dermoscopy Education in Primary Care.

BACKGROUND: Primary care providers (PCPs) frequently address dermatologic concerns and perform skin examinations during clinical encounters. For PCPs who evaluate concerning skin lesions, dermoscopy (a noninvasive skin visualization technique) has been shown to increase the sensitivity for skin cancer diagnosis compared with unassisted clinical examinations. Because no formal consensus existed on the fundamental knowledge and skills that PCPs should have with respect to dermoscopy for skin cancer detection, the objective of this study was to develop an expert consensus statement on proficiency standards for PCPs learning or using dermoscopy. METHODS: A 2-phase modified Delphi method was used to develop 2 proficiency standards. In the study's first phase, a focus group of PCPs and dermatologists generated a list of dermoscopic diagnoses and associated features. In the second phase, a larger panel evaluated the proposed list and determined whether each diagnosis was reflective of a foundational or intermediate proficiency or neither. RESULTS: Of the 35 initial panelists, 5 PCPs were lost to follow-up or withdrew; 30 completed the fifth and last round. The final consensus-based list contained 39 dermoscopic diagnoses and associated features. CONCLUSIONS: This consensus statement will inform the development of PCP-targeted dermoscopy training initiatives designed to support early cancer detection.

Agreement Between Experts and an Untrained Crowd for Identifying Dermoscopic Features Using a Gamified App: Reader Feasibility Study.

BACKGROUND: Dermoscopy is commonly used for the evaluation of pigmented lesions, but agreement between experts for identification of dermoscopic structures is known to be relatively poor. Expert labeling of medical data is a bottleneck in the development of machine learning (ML) tools, and crowdsourcing has been demonstrated as a cost- and time-efficient method for the annotation of medical images. OBJECTIVE: The aim of this study is to demonstrate that crowdsourcing can be used to label basic dermoscopic structures from images of pigmented lesions with similar reliability to a group of experts. METHODS: First, we obtained labels of 248 images of melanocytic lesions with 31 dermoscopic "subfeatures" labeled by 20 dermoscopy experts. These were then collapsed into 6 dermoscopic "superfeatures" based on structural similarity, due to low interrater reliability (IRR): dots, globules, lines, network structures, regression structures, and vessels. These images were then used as the gold standard for the crowd study. The commercial platform DiagnosUs was used to obtain annotations from a nonexpert crowd for the presence or absence of the 6 superfeatures in each of the 248 images. We replicated this methodology with a group of 7 dermatologists to allow direct comparison with the nonexpert crowd. The Cohen κ value was used to measure agreement across raters. RESULTS: In total, we obtained 139,731 ratings of the 6 dermoscopic superfeatures from the crowd. There was relatively lower agreement for the identification of dots and globules (the median κ values were 0.526 and 0.395, respectively), whereas network structures and vessels showed the highest agreement (the median κ values were 0.581 and 0.798, respectively). This pattern was also seen among the expert raters, who had median κ values of 0.483 and 0.517 for dots and globules, respectively, and 0.758 and 0.790 for network structures and vessels. The median κ values between nonexperts and thresholded average-expert readers were 0.709 for dots, 0.719 for globules, 0.714 for lines, 0.838 for network structures, 0.818 for regression structures, and 0.728 for vessels. CONCLUSIONS: This study confirmed that IRR for different dermoscopic features varied among a group of experts; a similar pattern was observed in a nonexpert crowd. There was good or excellent agreement for each of the 6 superfeatures between the crowd and the experts, highlighting the similar reliability of the crowd for labeling dermoscopic images. This confirms the feasibility and dependability of using crowdsourcing as a scalable solution to annotate large sets of dermoscopic images, with several potential clinical and educational applications, including the development of novel, explainable ML tools.

Indications for Digital Monitoring of Patients With Multiple Nevi: Recommendations from the International Dermoscopy Society.

Introduction: In patients with multiple nevi, sequential imaging using total body skin photography (TBSP) coupled with digital dermoscopy (DD) documentation reduces unnecessary excisions and improves the early detection of melanoma. Correct patient selection is essential for optimizing the efficacy of this diagnostic approach. Objectives: The purpose of the study was to identify, via expert consensus, the best indications for TBSP and DD follow-up. Methods: This study was performed on behalf of the International Dermoscopy Society (IDS). We attained consensus by using an e-Delphi methodology. The panel of participants included international experts in dermoscopy. In each Delphi round, experts were asked to select from a list of indications for TBSP and DD. Results: Expert consensus was attained after 3 rounds of Delphi. Participants considered a total nevus count of 60 or more nevi or the presence of a CDKN2A mutation sufficient to refer the patient for digital monitoring. Patients with more than 40 nevi were only considered an indication in case of personal history of melanoma or red hair and/or a MC1R mutation or history of organ transplantation. Conclusions: Our recommendations support clinicians in choosing appropriate follow-up regimens for patients with multiple nevi and in applying the time-consuming procedure of sequential imaging more efficiently. Further studies and real-life data are needed to confirm the usefulness of this list of indications in clinical practice.

Dermoscopy Proficiency Expectations for US Dermatology Resident Physicians: Results of a Modified Delphi Survey of Pigmented Lesion Experts.

Importance: Dermoscopy education in US dermatology residency programs varies widely, and there is currently no existing expert consensus identifying what is most important for resident physicians to know. Objectives: To identify consensus-based learning constructs representing an appropriate foundational proficiency in dermoscopic image interpretation for dermatology resident physicians, including dermoscopic diagnoses, associated features, and representative teaching images. Defining these foundational proficiency learning constructs will facilitate further skill development in dermoscopic image interpretation to help residents achieve clinical proficiency. Design, Setting, and Participants: A 2-phase modified Delphi surveying technique was used to identify resident learning constructs in 3 sequential sets of surveys-diagnoses, features, and images. Expert panelists were recruited through an email distributed to the 32 members of the Pigmented Lesion Subcommittee of the Melanoma Prevention Working Group. Twenty-six (81%) opted to participate. Surveys were distributed using RedCAP software. Main Outcomes and Measures: Consensus on diagnoses, associated dermoscopic features, and representative teaching images reflective of a foundational proficiency in dermoscopic image interpretation for US dermatology resident physicians. Results: Twenty-six pigmented lesion and dermoscopy specialists completed 8 rounds of surveys, with 100% (26/26) response rate in all rounds. A final list of 32 diagnoses and 116 associated dermoscopic features was generated. Three hundred seventy-eight representative teaching images reached consensus with panelists. Conclusions and Relevance: Consensus achieved in this modified Delphi process identified common dermoscopic diagnoses, associated features, and representative teaching images reflective of a foundational proficiency in dermoscopic image interpretation for dermatology residency training. This list of validated objectives provides a consensus-based foundation of key learning points in dermoscopy to help resident physicians achieve clinical proficiency in dermoscopic image interpretation.

Inequalities in the patterns of dermoscopy use and training across Europe: conclusions of the Eurodermoscopy pan-European survey.

BACKGROUND: Dermoscopy is a widely used technique, recommended in clinical practice guidelines worldwide for the early diagnosis of skin cancers. Intra-European disparities are reported for early detection and prognosis of skin cancers, however, no information exists about regional variation in patterns of dermoscopy use across Europe. OBJECTIVE: To evaluate the regional differences in patterns of dermoscopy use and training among European dermatologists. MATERIALS & METHODS: An online survey of European-registered dermatologists regarding dermoscopy training, practice and attitudes was established. Answers from Eastern (EE) versus Western European (WE) countries were compared and their correlation with their respective countries' gross domestic product/capita (GDPc) and total and government health expenditure/capita (THEc and GHEc) was analysed. RESULTS: We received 4,049 responses from 14 WE countries and 3,431 from 18 EE countries. A higher proportion of WE respondents reported dermoscopy use (98% vs. 77%, p<0.001) and training during residency (43% vs. 32%) or anytime (96.5% vs. 87.6%) (p<0.001) compared to EE respondents. The main obstacles in dermoscopy use were poor access to dermoscopy equipment in EE and a lack of confidence in one's skills in WE. GDPc, THEc and GHEc correlated with rate of dermoscopy use and dermoscopy training during residency (Spearman rho: 0.5-0.7, p<0.05), and inversely with availability of dermoscopy equipment. CONCLUSION: The rates and patterns of dermoscopy use vary significantly between Western and Eastern Europe, on a background of economic inequality. Regionally adapted interventions to increase access to dermoscopy equipment and training might enhance the use of this technique towards improving the early detection of skin cancers.

Melanoma patients with additional primary cancers: a single-center retrospective analysis.

Background: Recent progress in the diagnosis and treatment of primary and metastatic cutaneous melanoma (CM) has led to a significant increase in the patients` expectancy of life. The development of additional primary tumors (APT) other than CM represents an important survival issue. Results: Of a total of 1764 CM patients, 80 (4.5%) patients developed APT. For tumors diagnosed after CM, there was a 2.7 fold excess risk for APT compared to the swiss german population. A significantly increased risk was noted for female breast (SIR, 2.46), male larynx (SIR, 76.92), male multiple myeloma (SIR, 11.2), male oesophagus (SIR, 10.8) and thyroid on males (SIR, 58.8) and females (SIR, 38.1). All thyroid cancer cases had a common papillary histological subtype and a high rate of BRAFV600E mutation. Melanoma was the primary cause of death in the vast majority of patients. Methods: We used the cancer registry from the Comprehensive Cancer Center Zurich (CCCZ) and retrospectively analyzed patients with CM and APT between 2008 and 2018. We calculated the risk of APT compared to the swiss german population using the standardized incidence ratio (SIR). Conclusions: Patients with CM have an increased risk for hematologic and solid APT. Long-term follow-up is indicated.

Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic study.

BACKGROUND: 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. METHODS: 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. FINDINGS: 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). INTERPRETATION: 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. FUNDING: None.

Total Body Skin Examination Practices: A Survey Study Amongst Dermatologists at High-Risk Skin Cancer Clinics.

BACKGROUND/OBJECTIVES: Although total body skin examination (TBSE) is the primary screening mechanism for melanoma, there is no consensus on which anatomic sites a screening TBSE should include. We sought to establish which anatomic sites are examined during routine (>90%) TBSEs of patients at high risk for skin cancer. METHODS: A Google survey was emailed to 173 international dermatologist skin cancer specialists. RESULTS: More than 75% of participants reported routinely examining the scalp, ears, face and neck, trunk, breasts, inframammary areas, axillae, extremities, palms and soles, nails, interdigital spaces, and buttocks. The least frequently inspected anatomic sites included genitalia, with male genitalia more frequently examined than female (penis n = 39; 52%; labia majora n = 21; 28%; P = 0.003), the perianal region (n = 26; 34.7%), and the ocular conjunctiva and oral mucosa (n = 35; 46.7%). Participants cited not screening these areas because of perceived patient discomfort, low prevalence of malignancy, and the expectation that other specialists examine the area. CONCLUSIONS: The role of routine surveillance of neglected anatomic sites is unclear and warrants further discussion weighing potential mortality benefit against the incidence of melanoma in obscure sites, morbidity of intervention in sensitive sites, cost-effectiveness, and potential for patient discomfort.

Dermoscopy and dermatopathology correlates of cutaneous neoplasms.

Dermoscopy is increasingly used by clinicians (dermatologists, family physicians, podiatrists, doctors of osteopathic medicine, etc) to inform clinical management decisions. Dermoscopic findings or images provided to pathologists offer important insight into the clinician's diagnostic and management thought process. However, with limited dermoscopic training in dermatopathology, dermoscopic descriptions and images provided in the requisition form provide little value to pathologists. Most dermoscopic structures have direct histopathologic correlates, and therefore dermoscopy can act as an excellent communication bridge between the clinician and the pathologist. In the first article in this continuing medical education series, we review dermoscopic features and their histopathologic correlates.

Usefulness of dermoscopy to improve the clinical and histopathologic diagnosis of skin cancers.

Multiple studies have shown that dermoscopy increases the sensitivity and specificity for the detection of skin cancers compared with examination by the naked eye. Dermoscopy can also lead to the detection of thinner and smaller cancers. In addition, dermoscopy leads to the more precise selection of lesions requiring excision. In essence, dermoscopy helps clinicians differentiate benign from malignant lesions through the presence or absence of specific dermoscopic structures. Therefore, because most dermoscopic structures have direct histopathologic correlates, dermoscopy can allow the prediction of certain histologic findings present in skin cancers, thus helping select management and treatment options for select types of skin cancers. Visualizing dermoscopic structures in the ex vivo specimens can also be beneficial. It can improve the histologic diagnostic accuracy by targeted step-sectioning in areas of concern, which can be marked by the clinician before sending the specimen to the pathologist, or by the pathologist on the excised specimen in the laboratory. In addition, ex vivo dermoscopy can also be used to select tumor areas with genetic importance because some dermoscopic structures have been related to mutations with theragnostic relevance. In the second article in this continuing medical education series, we review the impact of dermoscopy on the diagnostic accuracy of skin cancer, how dermoscopy can affect the histopathologic examination, and which dermoscopic features may be more relevant in terms of histologic and genetic prediction.

Expert-Level Diagnosis of Nonpigmented Skin Cancer by Combined Convolutional Neural Networks.

Importance: Convolutional neural networks (CNNs) achieve expert-level accuracy in the diagnosis of pigmented melanocytic lesions. However, the most common types of skin cancer are nonpigmented and nonmelanocytic, and are more difficult to diagnose. Objective: To compare the accuracy of a CNN-based classifier with that of physicians with different levels of experience. Design, Setting, and Participants: A CNN-based classification model was trained on 7895 dermoscopic and 5829 close-up images of lesions excised at a primary skin cancer clinic between January 1, 2008, and July 13, 2017, for a combined evaluation of both imaging methods. The combined CNN (cCNN) was tested on a set of 2072 unknown cases and compared with results from 95 human raters who were medical personnel, including 62 board-certified dermatologists, with different experience in dermoscopy. Main Outcomes and Measures: The proportions of correct specific diagnoses and the accuracy to differentiate between benign and malignant lesions measured as an area under the receiver operating characteristic curve served as main outcome measures. Results: Among 95 human raters (51.6% female; mean age, 43.4 years; 95% CI, 41.0-45.7 years), the participants were divided into 3 groups (according to years of experience with dermoscopy): beginner raters (<3 years), intermediate raters (3-10 years), or expert raters (>10 years). The area under the receiver operating characteristic curve of the trained cCNN was higher than human ratings (0.742; 95% CI, 0.729-0.755 vs 0.695; 95% CI, 0.676-0.713; P < .001). The specificity was fixed at the mean level of human raters (51.3%), and therefore the sensitivity of the cCNN (80.5%; 95% CI, 79.0%-82.1%) was higher than that of human raters (77.6%; 95% CI, 74.7%-80.5%). The cCNN achieved a higher percentage of correct specific diagnoses compared with human raters (37.6%; 95% CI, 36.6%-38.4% vs 33.5%; 95% CI, 31.5%-35.6%; P = .001) but not compared with experts (37.3%; 95% CI, 35.7%-38.8% vs 40.0%; 95% CI, 37.0%-43.0%; P = .18). Conclusions and Relevance: Neural networks are able to classify dermoscopic and close-up images of nonpigmented lesions as accurately as human experts in an experimental setting.

Cytokine Release Syndrome During Sequential Treatment With Immune Checkpoint Inhibitors and Kinase Inhibitors for Metastatic Melanoma.

Switching from immunotherapy to targeted therapy in metastasized melanoma can be complicated by a cytokine release syndrome (CRS). CRS is a serious complication, which is induced by high levels of circulating cytokines, associated with T-cell engagement and proliferation, and results in a constellation of symptoms with variable organ involvement. We report 2 patients with BRAF V600 mutant melanoma who were previously treated with anti-PD-1±anti-LAG-3 antibodies and were switched to BRAF/MEK-inhibitors because of progressive disease. Both cases depict the complexity of interactions occurring during sequential treatment with immune checkpoint inhibitors and kinase inhibitors. Early identification and management of CRS is crucial to decrease its toxicity and improve safety of further drugs to be given in a therapeutic ladder.