Seven-point checklist of dermoscopy revisited

Self-supervised multi-modality learning for multi-label skin lesion classification

BACKGROUND

The clinical diagnosis of skin lesions involves the analysis of dermoscopic and clinical modalities. Dermoscopic images provide detailed views of surface structures, while clinical images offer complementary macroscopic information. Clinicians frequently use the seven-point checklist as an auxiliary tool for melanoma diagnosis and identifying lesion attributes. Supervised deep learning approaches, such as convolutional neural networks, have performed well using dermoscopic and clinical modalities (multi-modality) and further enhanced classification by predicting seven skin lesion attributes (multi-label). However, the performance of these approaches is reliant on the availability of large-scale labeled data, which are costly and time-consuming to obtain, more so with annotating multi-attributes METHODS:: To reduce the dependency on large labeled datasets, we propose a self-supervised learning (SSL) algorithm for multi-modality multi-label skin lesion classification. Compared with single-modality SSL, our algorithm enables multi-modality SSL by maximizing the similarities between paired dermoscopic and clinical images from different views. We introduce a novel multi-modal and multi-label SSL strategy that generates surrogate pseudo-multi-labels for seven skin lesion attributes through clustering analysis. A label-relation-aware module is proposed to refine each pseudo-label embedding, capturing the interrelationships between pseudo-multi-labels. We further illustrate the interrelationships of skin lesion attributes and their relationships with clinical diagnoses using an attention visualization technique.

RESULTS

The proposed algorithm was validated using the well-benchmarked seven-point skin lesion dataset. Our results demonstrate that our method outperforms the state-of-the-art SSL counterparts. Improvements in the area under receiver operating characteristic curve, precision, sensitivity, and specificity were observed across various lesion attributes and melanoma diagnoses.

CONCLUSIONS

Our self-supervised learning algorithm offers a robust and efficient solution for multi-modality multi-label skin lesion classification, reducing the reliance on large-scale labeled data. By effectively capturing and leveraging the complementary information between the dermoscopic and clinical images and interrelationships between lesion attributes, our approach holds the potential for improving clinical diagnosis accuracy in dermatology.

A multi-stage multi-modal learning algorithm with adaptive multimodal fusion for improving multi-label skin lesion classification

Skin cancer is frequently occurring and has become a major contributor to both cancer incidence and mortality. Accurate and timely diagnosis of skin cancer holds the potential to save lives. Deep learning-based methods have demonstrated significant advancements in the screening of skin cancers. However, most current approaches rely on a single modality input for diagnosis, thereby missing out on valuable complementary information that could enhance accuracy. Although some multimodal-based methods exist, they often lack adaptability and fail to fully leverage multimodal information. In this paper, we introduce a novel uncertainty-based hybrid fusion strategy for a multi-modal learning algorithm aimed at skin cancer diagnosis. Our approach specifically combines three different modalities: clinical images, dermoscopy images, and metadata, to make the final classification. For the fusion of two image modalities, we employ an intermediate fusion strategy that considers the similarity between clinical and dermoscopy images to extract features containing both complementary and correlated information. To capture the correlated information, we utilize cosine similarity, and we employ concatenation as the means for integrating complementary information. In the fusion of image and metadata modalities, we leverage uncertainty to obtain confident late fusion results, allowing our method to adaptively combine the information from different modalities. We conducted comprehensive experiments using a popular publicly available skin disease diagnosis dataset, and the results of these experiments demonstrate the effectiveness of our proposed method. Our proposed fusion algorithm could enhance the clinical applicability of automated skin lesion classification, offering a more robust and adaptive way to make automatic diagnoses with the help of uncertainty mechanism. Code is available at https://github.com/Zuo-Lihan/CosCatNet-Adaptive_Fusion_Algorithm.

Dermoscopy of External Ear Melanocytic Lesions: Performance of Selected Dermoscopic Screening Algorithms and Proposal of a New Predictive Model for Malignancy (AuriCheck Dermoscopic Algorithm)

Dermoscopy is a non-invasive imaging technique that significantly enhances diagnostic accuracy in diagnosing skin disorders [...].

Zoom-in Dermoscopy for Facial Tumors

Background/Objectives: Facial lesions, including lentigo maligna and lentigo maligna melanoma (LM/LMM), both malignant, present significant diagnostic challenges due to their clinical similarity to benign conditions. Although standard dermoscopy is a well-established tool for diagnosis, its inability to reveal cellular-level details highlights the necessity of new magnified techniques. This study aimed to assess the role of standard dermoscopy, high-magnification dermoscopy, and fluorescence-advanced videodermatoscopy (FAV) in diagnosing LM/LMM and differentiating them from benign facial lesions. Methods: This retrospective, observational, multicenter study evaluated 85 patients with facial skin lesions (including LM, LMM, basal-cell carcinoma, solar lentigo, seborrheic keratosis, actinic keratosis, and nevi) who underwent dermatological examination for skin tumor screening. Standard dermoscopy at 30× magnification (D30), high-magnification dermoscopy at 150× magnification (D150), and FAV examination were performed. Dermoscopic images were retrospectively evaluated for the presence of fifteen 30× and twenty-one 150× dermoscopic features, and their frequency was calculated. To compare D30 with D150 and D150 with FAV, the Gwet AC1 concordance index and the correct classification rate (CCR) were estimated. Results: Among 85 facial lesions analyzed, LM/LMM exhibited distinctive dermoscopic features at D30, including a blue-white veil (38.9% vs. 1.7%, p < 0.001), regression structures (55.6% vs. 21.7%, p = 0.013), irregular dots or globules (50.0% vs. 10%, p = 0.001), angulated lines (72.2% vs. 6.7%, p < 0.001), an annular granular pattern (61.1% vs. 20%, p = 0.002), asymmetrical pigmented follicular openings (100.0% vs. 21.7%; p < 0.001), and follicular obliteration (27.8% vs. 3.3%). At D150, roundish melanocytes (87.5% vs. 18.2%, p < 0.001) and melanophages (43.8% vs. 14.5%, p = 0.019) were predominant. FAV examination identified large dendritic cells, isolated melanocytes, and free melanin in LM/LMM (all p < 0.001) with high concordance to D150. Conclusions: Integrating D30, D150, and FAV into clinical practice may enhance diagnostic precision for facial lesions by combining macroscopic and cellular insights, thereby reducing unnecessary biopsies. However, future studies are essential to confirm these results.

Atypical naevi in dermoscopy and reflectance confocal microscopy: correlation between immunohistochemistry and diagnostic patterns of atypia

Equivocal cutaneous melanocytic lesions can sometimes be diagnosed as naevi at histopathology, despite positive melanoma-associated features being observed at dermoscopy and/or reflectance confocal microscopy (RCM). We prospectively identified equivocal lesions with histopathological diagnosis of naevus and at least one criterion of melanoma on dermoscopy and/or RCM (Prot.# 289\13).

Melanoma clinicopathological groups characterized and compared with dermoscopy and reflectance confocal microscopy

BACKGROUND

Dermoscopic and reflectance confocal microscopy (RCM) correlations between morphologic groups of melanoma have not yet been described.

OBJECTIVE

Describe and compare dermoscopic and RCM features of cutaneous melanomas with histopathological confirmation.

METHODS

Single center, retrospective analysis of consecutive melanomas evaluated with RCM (2015-2019). Lesions were clinically classified as typical, nevus-like, amelanotic/nonmelanoma skin cancer (NMSC)-like, seborrheic keratosis (SK)-like and lentigo/lentigo maligna (LM)-like. Presence or absence of common facial and nonfacial melanoma dermoscopic and RCM patterns were recorded. Clusters were compared with typical lesions by multivariate logistic regression.

RESULTS

Among 583 melanoma lesions, significant differences between clusters were evident (compared to typical lesions). Observation of dermoscopic features (>50% of lesions) in amelanotic/NMSC-like lesions consistently displayed 3 patterns (atypical network, atypical vascular pattern + regression structures), and nevus-like and SK-like lesions and lentigo/LM-like lesions consistently displayed 2 patterns (atypical network + regression structures, and nonevident follicles + heavy pigmentation intensity). Differences were less evident with RCM, as almost all lesions were consistent with melanoma diagnosis.

LIMITATIONS

Small SK-like lesions sample, single RCM analyses (no reproduction of outcome).

CONCLUSION

RCM has the potential to augment our ability to consistently and accurately diagnose melanoma independently of clinical and dermoscopic features.

A Narrative Review of Current Knowledge on Cutaneous Melanoma

Cutaneous melanoma is a public health problem. Efforts to reduce its incidence have failed, as it continues to increase. In recent years, many risk factors have been identified. Numerous diagnostic systems exist that greatly assist in early clinical diagnosis. The histopathological aspect illustrates the grim nature of these cancers. Currently, pathogenic pathways and the tumor microclimate are key to the development of therapeutic methods. Revolutionary therapies like targeted therapy and immune checkpoint inhibitors are starting to replace traditional therapeutic methods. Targeted therapy aims at a specific molecule in the pathogenic chain to block it, stopping cell growth and dissemination. The main function of immune checkpoint inhibitors is to boost cellular immunity in order to combat cancer cells. Unfortunately, these therapies have different rates of effectiveness and side effects, and cannot be applied to all patients. These shortcomings are the basis of increased incidence and mortality rates. This study covers all stages of the evolutionary sequence of melanoma. With all these data in front of us, we see the need for new research efforts directed at therapies that will bring greater benefits in terms of patient survival and prognosis, with fewer adverse effects.

Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma

Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists' decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists' diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists' confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists' willingness to adopt such XAI systems, promoting future use in the clinic.

Differentiating between early melanomas and melanocytic nevi: A state-of-the-art review

Clinicians and dermatologists are challenged by accurate diagnosis of melanocytic lesions, due to melanoma's resemblance to benign skin conditions. Several methodologies have been proposed to diagnose melanoma, and to differentiate between a cancerous and a benign skin condition. First, the ABCD rule and Menzies method use skin lesion characteristics to interpret the condition. The 7-point checklist, 3-point checklist, and CASH algorithm are score-based methods. Each of these methods attributes a score point to the features found on the skin lesion. Furthermore, reflectance confocal microscopy (RCM), an integrated clinical and dermoscopic risk scoring system (iDscore), and a deep convoluted neural network (DCNN) also aids in diagnosis. RCM optically sections live tissues to reveal morphological and cellular structures. The skin lesion's clinical parameters determine iDscore's score point system. The DCNN model is based on a detailed learning algorithm. Therefore, we discuss the conventional and new methodologies for the identification of skin diseases. Moreover, our review attempts to provide clinicians with a comprehensible summary of the wide range of techniques that can help differentiate between early melanomas and melanocytic nevi.

Dermoscopy of melanoma according to different body sites: Head and neck, trunk, limbs, nail, mucosal and acral

Effective cancer screening detects early-stage tumours, leading to a lower incidence of late-stage disease over time. Dermoscopy is the gold standard for skin cancer diagnosis as diagnostic accuracy is improved compared to naked eye examinations. As melanoma dermoscopic features are often body site specific, awareness of common features according to their location is imperative for improved melanoma diagnostic accuracy. Several criteria have been identified according to the anatomical location of the melanoma. This review provides a comprehensive and contemporary review of dermoscopic melanoma criteria according to specific body sites, including frequently observed melanoma of the head/neck, trunk and limbs and special site melanomas, located on the nail, mucosal and acral region.

Machine Learning Methods in Skin Disease Recognition: A Systematic Review

Skin lesions affect millions of people worldwide. They can be easily recognized based on their typically abnormal texture and color but are difficult to diagnose due to similar symptoms among certain types of lesions. The motivation for this study is to collate and analyze machine learning (ML) applications in skin lesion research, with the goal of encouraging the development of automated systems for skin disease diagnosis. To assist dermatologists in their clinical diagnosis, several skin image datasets have been developed and published online. Such efforts have motivated researchers and medical staff to develop automatic skin diagnosis systems using image segmentation and classification processes. This paper summarizes the fundamental steps in skin lesion diagnosis based on papers mainly published since 2013. The applications of ML methods (including traditional ML and deep learning (DL)) in skin disease recognition are reviewed based on their contributions, methods, and achieved results. Such technical analysis is beneficial to the continuing development of reliable and effective computer-aided skin disease diagnosis systems. We believe that more research efforts will lead to the current automatic skin diagnosis studies being used in real clinical settings in the near future.

Clinicopathologic and Dermoscopic Features of 20 Cases of Spark's Nevus, a Dermoscopic Simulator of Melanoma

ABSTRACT

Spark's nevus is a particular type of melanocytic nevus, with histology that shows features of both Spitz and Clark nevus. Detailed dermoscopic features in a series of Spark nevi have not been described yet. We performed a monocentric retrospective observational study on 20 lesions of Spark nevus excised from 19 patients (M:F = 10:9; mean age: 37,6 years), reviewed by 5 experts in dermoscopy and 2 dermatopathologists. A histologic review confirmed that Spark nevi were mostly symmetric (80%), well circumscribed (100%), mainly compound (65%) melanocytic lesions with either epithelioid (55%) or spitzoid (45%) cell morphology and bridging of the nests (100%). Spark nevi were more frequently found on the trunk (85%) in patients with a history of sunburns in childhood (84%), with skin phototype III (79%), and with high nevus count (>100 nevi, 7 patients (36%)). On dermoscopy, we observed different general patterns: multicomponent (40%), reticular-globular-homogeneous (15%), globular homogeneous (15%), reticular (15%), reticular-globular (5%), homogeneous (5%), and globular (5%). Spark nevi showed frequently dermoscopic asymmetry (63%), brown color (90%) with areas of central hyperpigmentation (41%) and peripheral hypopigmentation (28%), atypical pigment network (48%), irregular globules (42%), irregular dots (31%), irregular blotches (16%), blue-whitish veil (13%), peripheral island (25%), irregular hyperpigmented areas (12%), and regression (33%). BRAF mutation was present in 7 of the 10 analyzed cases (70%); all these cases presented a history of evolution. In conclusion, Spark nevi occur on the trunk of young adults with high nevus count and history of sunburns; dermoscopic features are protean, often atypical and suspicious of melanoma.

[Artificial intelligence-based classification for the diagnostics of skin cancer]

Convolutional neural networks (CNN) achieve a level of performance comparable or even superior to dermatologists in the assessment of pigmented and nonpigmented skin lesions. In the analysis of images by artificial neural networks, images on a pixel level pass through various layers of the network with different graphic filters. Based on excellent study results, a first deep learning network (Moleanalyzer pro, Fotofinder Systems GmBH, Bad Birnbach, Germany) received market approval in Europe. However, such neural networks also reveal relevant limitations, whereby rare entities with insufficient training images are classified less adequately and image artifacts can lead to false diagnoses. Best results can ultimately be achieved in a cooperation of "man with machine". For future skin cancer screening, automated total body mapping is evaluated, which combines total body photography, automated data extraction and assessment of all relevant skin lesions.

"Red Spitz Tumor" on the Ear: Case Report and Review of the Literature

Spitz nevus (SN) is a benign melanocytic lesion with cytologic and architectural atypia. It is sometimes difficult to distinguish SNs from atypical Spitz tumor (AST), Spitz melanoma, or conventional melanoma. SNs frequently develop in Caucasians and appear on the skin of the head and lower extremities. Lesions on the ear in Asian populations are rare. Here, we report a “red Spitz tumor” on the ear of a Chinese 18-year-old boy. Dermoscopic examination revealed possibly malignant features presented as polymorphous vessels along with central white area, pseudo-network depigmentation and atypical peripheral globular pattern. The results of histopathological examination strongly suggested that the neoplasm was a compound SN and no recurrences or metastases occurred during 1-year follow-up post-surgery. Further, we review the literature on 4 previously reported cases of SN on the ear and summarize the main points of SN diagnosis and differential diagnosis with atypical Spitz tumors and melanoma.

Unusual Dermoscopic Patterns of Basal Cell Carcinoma Mimicking Melanoma

Background

Basal cell carcinoma can simulate melanoma and specific dermoscopic criteria have not yet been defined in a large cohort.

Objective

To identify dermoscopic “trump” characteristics for differential diagnosis, identify cluster groups and assess the clinical impact of this study's findings.

Methods

Retrospective, multicentric comparative study of atypical, non‐facial basal cell carcinoma (≥1 seven‐point checklist criteria) and melanoma (with at least one BCC criteria) at dermoscopy. Observed dermoscopic features were used to develop a proposed score. Lesion clusters were defined with hierarchical analysis. Clinical impact was assessed with a blinded reader study following this study's results.

Results

A total of 146 basal cell carcinoma and 76 melanoma were included. Atypical vascular pattern was common to most lesions (74.5%). Twelve trump features were included in the proposed score (sensitivity 94.1% and specificity 79.5%). Cluster analysis identified 3 basal cell carcinoma and 3 melanoma clusters. Findings improved overall diagnostic accuracy and confidence (26.8% and 13.8%, respectively; p < 0.001).

Conclusions

These findings support the notion that atypical vascular pattern should be considered a shared feature of both melanoma and atypical basal cell carcinoma. Our proposed score improves diagnostic accuracy and confidence. Absence of pigmented features was associated with lower diagnostic accuracy and confidence.

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer

Simple Summary

Malignant melanomas (MMs) with aypical clinical presentation constitute a diagnostic pitfall, and false negatives carry the risk of a diagnostic delay and improper disease management. Among the most common, challenging presentation forms of MMs are those that clinically resemble seborrheic keratosis (SK). On the other hand, SK may mimic melanoma, producing ‘false positive overdiagnosis’ and leading to needless excisions. The evolving efficiency of deep learning algorithms in image recognition and the availability of large image databases have accelerated the development of advanced computer-aided systems for melanoma detection. In the present study, we used image data from the International Skin Image Collaboration archive to explore the capacity of deep knowledge transfer in the challenging diagnostic task of the atypical skin tumors of MM and SK.

Abstract

Malignant melanomas resembling seborrheic keratosis (SK-like MMs) are atypical, challenging to diagnose melanoma cases that carry the risk of delayed diagnosis and inadequate treatment. On the other hand, SK may mimic melanoma, producing a ‘false positive’ with unnecessary lesion excisions. The present study proposes a computer-based approach using dermoscopy images for the characterization of SΚ-like MMs. Dermoscopic images were retrieved from the International Skin Imaging Collaboration archive. Exploiting image embeddings from pretrained convolutional network VGG16, we trained a support vector machine (SVM) classification model on a data set of 667 images. SVM optimal hyperparameter selection was carried out using the Bayesian optimization method. The classifier was tested on an independent data set of 311 images with atypical appearance: MMs had an absence of pigmented network and had an existence of milia-like cysts. SK lacked milia-like cysts and had a pigmented network. Atypical MMs were characterized with a sensitivity and specificity of 78.6% and 84.5%, respectively. The advent of deep learning in image recognition has attracted the interest of computer science towards improved skin lesion diagnosis. Open-source, public access archives of skin images empower further the implementation and validation of computer-based systems that might contribute significantly to complex clinical diagnostic problems such as the characterization of SK-like MMs.

FusionM4Net: A multi-stage multi-modal learning algorithm for multi-label skin lesion classification

Skin disease is one of the most common diseases in the world. Deep learning-based methods have achieved excellent skin lesion recognition performance, most of which are based on only dermoscopy images. In recent works that use multi-modality data (patient's meta-data, clinical images, and dermoscopy images), the methods adopt a one-stage fusion approach and only optimize the information fusion at the feature level. These methods do not use information fusion at the decision level and thus cannot fully use the data of all modalities. This work proposes a novel two-stage multi-modal learning algorithm (FusionM4Net) for multi-label skin diseases classification. At the first stage, we construct a FusionNet, which exploits and integrates the representation of clinical and dermoscopy images at the feature level, and then uses a Fusion Scheme 1 to conduct the information fusion at the decision level. At the second stage, to further incorporate the patient's meta-data, we propose a Fusion Scheme 2, which integrates the multi-label predictive information from the first stage and patient's meta-data information to train an SVM cluster. The final diagnosis is formed by the fusion of the predictions from the first and second stages. Our algorithm was evaluated on the seven-point checklist dataset, a well-established multi-modality multi-label skin disease dataset. Without using the patient's meta-data, the proposed FusionM4Net's first stage (FusionM4Net-FS) achieved an average accuracy of 75.7% for multi-classification tasks and 74.9% for diagnostic tasks, which is more accurate than other state-of-the-art methods. By further fusing the patient's meta-data at FusionM4Net's second stage (FusionM4Net-SS), the entire FusionM4Net finally boosts the average accuracy to 77.0% and the diagnostic accuracy to 78.5%, which indicates its robust and excellent classification performance on the label-imbalanced dataset. The corresponding code is available at: https://github.com/pixixiaonaogou/MLSDR.

Usefulness of Dermoscopy to Provide Accurate Assessment of Skin Cancers

Seborrheic keratosis (SK) is the most common benign tumour of epidermal origin. In most cases, it is simple to recognize in the clinical examination. However, sometimes SK can be a problematic lesion. We present the cases of two patients with seborrheic keratosis in whom we diagnosed the skin cancer through dermoscopic and histopathological examinations. The article aims to draw attention to the need for dermoscopic examinations to be included for an accurate assessment of the nevi not only by dermatologists but also not-specialized doctors. We would like to underline that many skin cancers share the similar features of malignancy, and competence and capability to interpret the dermoscopic pictures correctly are important for early recognition of malignant lesion. Very often malignant skin cancers can be hidden among benign lesions like seborrheic keratosis or they can be imitators of benign lesions. Amongst all cases of imposing SK, basal cell carcinoma, squamous cell carcinoma, melanoma is the most important differential diagnosis, of which their dermoscopic features will be discussed in this article.

Dynamic dermoscopic and reflectance confocal microscopic changes of melanocytic lesions excised during follow up

BACKGROUND

Digital dermoscopy follow up (DDF) is useful in improving the recognition of melanoma, catching early changes over time, although benign nevi can also show changes. Reflectance confocal microscopy (RCM) improves accuracy in diagnosing melanoma and decreases the number of unnecessary resections.

OBJECTIVE

To evaluate dynamic dermoscopic and RCM changes during follow up of equivocal melanocytic lesions and assess the impact of adjunctive RCM to DDF for melanoma diagnosis.

METHODS

A retrospective, multicenter study of extrafacial atypical melanocytic lesions excised during follow up was performed. Morphologic changes were evaluated, comparing dermoscopy and RCM baseline and follow-up images.

RESULTS

One hundred thirty-seven atypical melanocytic lesions were studied, including 14 melanomas and 123 benign nevi. Significantly greater changes in DDF of atypical network, regression, atypical streaks, and asymmetrical growth as well as in dynamic RCM of atypical cells and dermal-epidermal junction disarray were noted in melanomas. With adjunctive dynamic RCM and major changes at DDF, sensitivity reached 100%, with 40.6% specificity.

LIMITATIONS

Selected series of difficult to recognize lesions, with both DDF and dynamic RCM images.

CONCLUSION

Adjunctive dynamic RCM improves early melanoma recognition sensitivity.

Cancer diagnostic tools to aid decision-making in primary care: mixed-methods systematic reviews and cost-effectiveness analysis

BACKGROUND

Tools based on diagnostic prediction models are available to help general practitioners diagnose cancer. It is unclear whether or not tools expedite diagnosis or affect patient quality of life and/or survival.

OBJECTIVES

The objectives were to evaluate the evidence on the validation, clinical effectiveness, cost-effectiveness, and availability and use of cancer diagnostic tools in primary care.

METHODS

Two systematic reviews were conducted to examine the clinical effectiveness (review 1) and the development, validation and accuracy (review 2) of diagnostic prediction models for aiding general practitioners in cancer diagnosis. Bibliographic searches were conducted on MEDLINE, MEDLINE In-Process, EMBASE, Cochrane Library and Web of Science) in May 2017, with updated searches conducted in November 2018. A decision-analytic model explored the tools' clinical effectiveness and cost-effectiveness in colorectal cancer. The model compared patient outcomes and costs between strategies that included the use of the tools and those that did not, using the NHS perspective. We surveyed 4600 general practitioners in randomly selected UK practices to determine the proportions of general practices and general practitioners with access to, and using, cancer decision support tools. Association between access to these tools and practice-level cancer diagnostic indicators was explored.

RESULTS

Systematic review 1 - five studies, of different design and quality, reporting on three diagnostic tools, were included. We found no evidence that using the tools was associated with better outcomes. Systematic review 2 - 43 studies were included, reporting on prediction models, in various stages of development, for 14 cancer sites (including multiple cancers). Most studies relate to QCancer® (ClinRisk Ltd, Leeds, UK) and risk assessment tools.

DECISION MODEL

In the absence of studies reporting their clinical outcomes, QCancer and risk assessment tools were evaluated against faecal immunochemical testing. A linked data approach was used, which translates diagnostic accuracy into time to diagnosis and treatment, and stage at diagnosis. Given the current lack of evidence, the model showed that the cost-effectiveness of diagnostic tools in colorectal cancer relies on demonstrating patient survival benefits. Sensitivity of faecal immunochemical testing and specificity of QCancer and risk assessment tools in a low-risk population were the key uncertain parameters.

SURVEY

Practitioner- and practice-level response rates were 10.3% (476/4600) and 23.3% (227/975), respectively. Cancer decision support tools were available in 83 out of 227 practices (36.6%, 95% confidence interval 30.3% to 43.1%), and were likely to be used in 38 out of 227 practices (16.7%, 95% confidence interval 12.1% to 22.2%). The mean 2-week-wait referral rate did not differ between practices that do and practices that do not have access to QCancer or risk assessment tools (mean difference of 1.8 referrals per 100,000 referrals, 95% confidence interval -6.7 to 10.3 referrals per 100,000 referrals).

LIMITATIONS

There is little good-quality evidence on the clinical effectiveness and cost-effectiveness of diagnostic tools. Many diagnostic prediction models are limited by a lack of external validation. There are limited data on current UK practice and clinical outcomes of diagnostic strategies, and there is no evidence on the quality-of-life outcomes of diagnostic results. The survey was limited by low response rates.

CONCLUSION

The evidence base on the tools is limited. Research on how general practitioners interact with the tools may help to identify barriers to implementation and uptake, and the potential for clinical effectiveness.

FUTURE WORK

Continued model validation is recommended, especially for risk assessment tools. Assessment of the tools' impact on time to diagnosis and treatment, stage at diagnosis, and health outcomes is also recommended, as is further work to understand how tools are used in general practitioner consultations.

STUDY REGISTRATION

This study is registered as PROSPERO CRD42017068373 and CRD42017068375.

FUNDING

This project was funded by the National Institute for Health Research (NIHR) Health Technology programme and will be published in full in Health Technology Assessment; Vol. 24, No. 66. See the NIHR Journals Library website for further project information.

Gray-edged line sign of scabies burrow

A scabies burrow is created by a mature female mite laying eggs through the stratum corneum, representing a kind of scabies eruption. We have noticed that the edges of the scabies burrow sometime appear as blackish-gray lines. We named these lines the "gray-edged line" sign, as a new feature of scabies burrows. The gray-edged line sign has the following two tendencies: (i) it is rarely seen on the palm or sole; and (ii) when the burrow follows a curved course, the gray-edged line often forms on the outer wall. Explaining the formation of this sign from clinical findings was difficult, so the aim of the present study was to elucidate the mechanisms underlying the gray-edged line sign. This retrospective study involved collection of data from electronic medical records of patients treated for scabies in our department between April 2015 and February 2020. We treated 32 scabies patients, including 4 patients with the gray-edged line sign. We analyzed clinical features, dermoscopy, histopathology and special stains. Fontana-Masson staining showed melanin staining in three parts: feces; some keratinocytes around the scabies burrows; and the mouth and legs of the scabies mite. The gray-edged line sign appears to represent mite feces containing melanin.

Dark pigmented lesions: Diagnostic accuracy of dermoscopy and reflectance confocal microscopy in a tertiary referral center for skin cancer diagnosis

BACKGROUND

There is lack of studies on the diagnostic accuracy of dermoscopy and reflectance confocal microscopy (RCM) for dark pigmented lesions.

OBJECTIVE

To assess the diagnostic accuracy of dermoscopy plus confocal microscopy for melanoma diagnosis of dark pigmented lesions in real life.

METHODS

Prospective analysis of difficult dark lesions with clinical/dermoscopic suspicion of melanoma referred for RCM for further analysis. The outcome could be excision or dermoscopic digital follow-up.

RESULTS

We included 370 clinically dark lesions from 350 patients (median age, 45 y). Because of the clinical/dermoscopic/RCM approach, we saved 129 of 213 unnecessary biopsies (specificity of 60.6%), with a sensitivity of 98.1% (154/157). The number needed to excise with the addition of RCM was 1.5 for melanoma diagnosis.

LIMITATIONS

Single institution based; Italian population only.

CONCLUSIONS

This study showed that RCM coupled with dermoscopy increases the specificity for diagnosing melanoma, and it helps correctly identify benign lesions. Our findings provide the basis for subsequent prospective studies on melanocytic neoplasms belonging to patients in different countries.

Real-Time Mobile-Phone-Aided Melanoma Skin Lesion Detection Using Triangulation Technique

Melanoma is a harmful disease among all types of skin cancer. Genetic factors and the exposure of UV rays causes melanoma skin lesions. Early diagnosis is important to identify malignant melanomas to improve the patient prognosis. A biopsy is a traditional method which is painful and invasive when used for skin cancer detection. This method requires laboratory testing which is not very efficient and time-consuming to detect skin lesions. To solve the above issue, a computer aided diagnosis (CAD) for skin lesion detection is needed. In this article, we have developed a mobile application with the capabilities to segment skin lesions in dermoscopy images using a triangulation method and categorize them into malignant or bengin lesions through a supervised method which is convolution neural network (CNN). This mobile application will make the skin cancer detection non-invasive which does not require any laboratory testing, making the detection less time consuming and inexpensive with a detection accuracy of 81%.

The presence of eccentric hyperpigmentation should raise the suspicion of melanoma

BACKGROUND

Melanocytic lesions with eccentric hyperpigmentation (EH), even though without other dermatoscopic features of melanoma, are often excised.

OBJECTIVE

Aiming to understand whether the EH in a pigmented lesion is an accurate criterion of malignancy, we evaluated the capability of two evaluators, with different expertise, to correctly diagnose a melanoma when analysing a given lesion in toto versus a partial analysis, with only the EH or the non-hyperpigmented portion (non-EH) visible.

METHODS

Dermatoscopic images of 240 lesions (107 melanomas and 133 nevi) typified by EH were selected. Facial, acral, mucosal lesions and lesions showing clear-cut features of melanoma (except for atypical network) were excluded. Clinical and dermoscopic features (main pattern and numbers of colours) were described for all cases. Each image was split in two through a software so that only the EH or the non-EH was visible. Two blinded evaluators examined three sets of images, two with customized images and one with the non-modified ones: they were asked to give a dichotomous diagnosis (melanoma or nevus) for each image.

RESULTS

Melanomas were significantly more frequently typified by colour variegation (3 colours in 44.8% and 4 colours in 41.1% of cases) and atypical network (88.1% in the EH). No significant differences in diagnostic accuracy emerged between the two evaluators. Sensitivity improved in the evaluation of the whole lesions (mean sensitivity 89.7%) in comparison with the evaluation of EH or non-EH alone (72.7-62.6%). Specificity increased when evaluating the EH (54.1%). Positive predictive value (PPV) and likelihood ratio (LR+) of EH resulted 52.3% and 1.4, meaning that in one case out of two with EH is a melanoma.

CONCLUSIONS

Lesions with EH are challenging, regardless of dermoscopic experience. The EH is a robust criterion for malignancy, since the evaluation of the whole lesion, through an intralesional comparative approach, increases sensitivity.

Digital dermoscopic changes during follow-up of de-novo and nevus-associated melanoma: a cohort study

BACKGROUND

Nevus-associated melanoma (NAM) has been regarded as a distinct biological entity from de-novo melanoma (DNM); however, static dermoscopy often fails in differentiating these entities. Digital dermoscopic monitoring allows to identify dynamic changes occurring during follow-up; this may improve diagnostic accuracy and potentially our knowledge on NAM biology. We aimed to define main independent factors associated with NAM diagnosis and those influencing follow-up time in a population of melanomas excised at follow-up.

METHODS

A cohort of melanomas excised at follow-up was retrospectively and consecutively selected. NAMs and DNMs were compared according to baseline features and main dermoscopic changes occurring during follow-up. Univariate and multivariable logistic and Cox's regression analysis were performed to respectively define factors associated with NAM diagnosis and those influencing the risk for excision.

RESULTS

Eighty-six melanomas were enrolled, of which 21 (24.4%) were nevus-associated. During follow-up NAMs mainly underwent atypical network modifications (47.6%), followed by inverse network (28.6%) and dermoscopic island (23.8%) worsening or appearance. DNMs were also mainly characterized by atypical network modifications (47.7%), however, a significant proportion of cases underwent irregular pigmentation/dots/globules or regression changes (29.2%), which were rarely seen among NAMs. Furthermore, both multivariable logistic and Cox's regression analysis demonstrated a significant association between NAM and a longer follow-up.

CONCLUSIONS

We demonstrated that among melanomas excised at follow-up, different patterns of dermoscopic changes may be found between NAMs and DNMs. This finding, together with the association of NAM with a longer follow-up time, supports the hypothesis of different biological behavior of these two entities.

Clinical and dermoscopic features of surgically treated melanocytic nevi: a retrospective study of 1046 cases

Background:

Compared with Caucasians, unique demographic and clinical features have been reported in Chinese patients with malignant melanoma, but similar comparative studies of melanocytic nevi (MN) are lacking. This study examined the clinical and dermoscopic features of MN in surgically treated Chinese cases.

Methods:

Clinical data and dermoscopic findings from 1046 cases of MN were collected and analyzed. Cases were treated from January 1 to December 31, 2014 at the Department of Dermatology and Venerology, Peking University First Hospital. The association between nevi location and histologic subtypes was examined with Chi-squared test and univariate logistic regression. Chi-squared test was also used to analyze the proportion of globular patterns across different body sites, and proportion of parallel furrow patterns across different histologic subtypes.

Results:

The majority of the nevi were from female patients, irrespective of location. The range of age at the time of nevi onset was from 0 (birth) to 79 years. There were 381 (36.4%, 381/1046) congenital nevi; of these 81.6% (311/381) were present at birth. Nevi appeared before 30 years of age in 83.2% (870/1046) of the cases. Median values of length growth rate in congenital and acquired MN were 2.0 and 1.6, respectively. Median values of length growth rates in four age groups (0–9, 10–19, 20–29, and ≥30 years) of congenital nevi were 2.2, 2.0, 2.4, and 2.0, respectively. In acral nevi, which often need to be differentiated from acral lentiginous melanoma, 50.2% (109/217) were junctional (odds ratio [OR]; 95% confidence interval [CI]: 91.572 [52.210–160.959], P < 0.05). Acral location was also associated with a higher likelihood of compound nevi subtype (OR [95% CI]: 14.468 [8.981–23.306], P < 0.05). The globular (59.4%, 354/596) and pseudonetwork (48.8%, 291/596) dermoscopic patterns were often seen in the head and neck region. In areas other than head and neck and acral regions, the globular pattern was the commonest pattern (34.8%, 71/204) regardless of age. Parallel furrow pattern occurred in 46.0% (87/189) of acral MN, followed by fibrillar pattern (21.7%, 41/189).

Conclusion:

Unique clinical and dermoscopic features exist in Chinese patients with MN compared with observations reported in other population.

Melanoma Detection by Means of Multiple Instance Learning

We present an application to melanoma detection of a multiple instance learning (MIL) approach, whose objective, in the binary case, is to discriminate between positive and negative sets of items. In the MIL terminology these sets are called bags and the items inside the bags are called instances. Under the hypothesis that a bag is positive if at least one of its instances is positive and it is negative if all its instances are negative, the MIL paradigm fits very well with images classification, since an image (bag) is in general classified on the basis of some its subregions (instances). In this work we have applied a MIL algorithm on some clinical data constituted by color dermoscopic images, with the aim to discriminate between melanomas (positive images) and common nevi (negative images). In comparison with standard classification approaches, such as the well known support vector machine, our method performs very well in terms both of accuracy and sensitivity. In particular, using a leave-one-out validation on a data set constituted by 80 melanomas and 80 common nevi, we have obtained the following results: accuracy = 92.50%, sensitivity = 97.50% and specificity = 87.50%. Since the results appear promising, we conclude that a MIL technique could be at the basis of more sophisticated tools useful to physicians in melanoma detection.

The prevalent dermoscopic criterion to distinguish between benign and suspicious pink tumours

BACKGROUND

Pink skin tumours are difficult to differentiate, clinically and dermoscopically. In previous studies, mainly focused on pigmented lesions, pattern analysis provided the best sensitivity and specificity values, as compared to other algorithms. These findings suggest that the global dermoscopic appearance, based on the evaluation of prevalent features, could represent a valuable and practical approach even when dealing with pink lesions.

OBJECTIVE

In this study, we aimed to evaluate the diagnostic accuracy of a new dermoscopic approach for pink tumours based on the prevalent criterion, as compared to a standard diagnostic method (Menzies algorithm).

METHODS

The databases of two referral centres were retrospectively evaluated to retrieve dermoscopic images of amelanotic/hypomelanotic skin lesions. Two experts in dermoscopy, blinded for the final diagnosis and for clinical and demographic information, evaluated separately dermoscopic pictures of 1000 lesions according to the Menzies score and to the prevalent criterion method.

RESULTS

According to the high sensitivity model of the Menzies score, 129 (12.9%) lesions were considered as non-suspicious (of which 16 were false negative) and 871 (87.1%) as suspicious (of which 212 were false positive), with 97.6% sensitivity and 34.8% specificity. According to the high specificity model, 370 (37%) lesions were evaluated as non-suspicious (of which 105 were false negative) and 630 (63%) as suspicious (of which 60 were false positive), with 84.4% sensitivity and 81.5% specificity. Concerning the prevalent criterion method, 316 (31.6%) lesions were evaluated as non-suspicious (of which 46 were false negative) and 684 (68.4) as suspicious (of which 55 were false positive), with 93.2% sensitivity and 83.1% specificity.

CONCLUSIONS

This study demonstrated that focusing on the prevalent dermoscopic features could allow to detect malignant pink tumours with similar sensitivity but higher specificity than using the conventional Menzies scoring system.

Accuracy of Dermoscopic Criteria for the Diagnosis of Melanoma In Situ

Importance

The accuracy of melanoma-specific dermoscopic criteria has been tested mainly in studies including invasive tumors. Scarce evidence exists on the usefulness of these criteria for the diagnosis of melanoma in situ (MIS).

Objective

To investigate the diagnostic accuracy of dermoscopic criteria for the diagnosis of MIS.

Design, Setting, and Participants

A diagnostic accuracy study with retrospective patient enrollment was conducted in 3 centers specializing in skin cancer diagnosis and management. A total of 1285 individuals with histopathologically diagnosed MIS or other flat, pigmented skin tumors that were histopathologically diagnosed or monitored for at least 1 year were included. Dermoscopic images of MIS and other flat, pigmented skin tumors were evaluated by 3 independent investigators for the presence of predefined criteria. Evaluators were blinded to the clinic dermoscopic and histopathologic diagnosis.

Main Outcomes and Measures

Frequencies of dermoscopic criteria per diagnosis were calculated. Crude odds ratios, adjusted odds ratios, and corresponding 95% CIs were calculated by univariate and multivariate logistic regression, respectively.

Results

A total of 1285 patients were included in the study (642 [50%] male); mean age was 45.9 years (range, 9-91 years). Of a total of 1285 lesions obtained from these patients, 325 (25.3%) were MIS; 574 (44.7%) were nevi (312 [24.3%] excised and 262 [20.4%] not excised); 67 (5.2%) were seborrheic keratoses, solar lentigines, or lichen planus-like keratoses; 91 (7.1%) were pigmented superficial basal cell carcinomas; 26 (2.0%) were pigmented intraepithelial carcinomas; 100 (7.8%) were Reed nevi; and 102 (7.9%) were invasive melanomas with a Breslow thickness less than 0.75 mm. The most frequent dermoscopic criteria for MIS were regression (302 [92.9%]), atypical network (278 [85.5%]), and irregular dots and/or globules (163 [50.2%]). The multivariate analysis revealed 5 main positive dermoscopic indicators of MIS: atypical network (3.7-fold; 95% CI, 2.5-5.4), regression (4.7-fold; 95% CI, 2.8-8.1), irregular hyperpigmented areas (5.4-fold; 95% CI, 3.7-8.0), prominent skin markings (3.4-fold; 95% CI, 1.9-6.1), and angulated lines (2.2-fold; 95% CI, 1.2-4.1). When compared only with excised nevi, 2 of these criteria remained potent MIS indicators, namely, irregular hyperpigmented areas (4.3-fold; 95% CI, 2.7-6.8) and prominent skin markings (2.7-fold; 95% CI, 1.3-5.7).

Conclusions and Relevance

Clinicians should take into consideration the aforementioned dermoscopic indicators for the diagnosis of MIS.

External validation and comparison of four confocal microscopic scores for melanoma diagnosis on a retrospective series of highly suspicious melanocytic lesions

BACKGROUND

In vivo reflectance confocal microscopy significantly improves melanoma diagnosis as compared to clinical/dermoscopic examination alone. Several confocal criteria have been described allowing to differentiate melanoma from nevi; by combining different criteria, three pure confocal scores (Pellacani 2005, Segura 2009 and Pellacani 2012) and one mixed dermoscopic/confocal score (Borsari 2018) were constructed.

OBJECTIVE

Our aim was to externally validate and compare the performance of these confocal scores.

METHODS

We retrospectively enrolled excised melanocytic lesions which underwent confocal examination in a 2-year period. Lesions located on the face and acral sites were excluded. Both dermoscopic and confocal criteria considered in the four scores were evaluated by experts. Subsequently, specificity and sensitivity levels for each score were calculated, together with the positive and negative predictive values and likelihood ratios; also, receiver operating characteristic curves were constructed.

RESULTS

A total of 389 patients with 422 lesions were retrospectively enrolled, of which 162 (38.4%) were melanomas and 260 (61.6%) were nevi (189 common and 71 Spitz/Reed nevi). The highest sensitivity levels were recorded for Segura 2009 with cut-off ≥-1 (92.0%), while Pellacani 2005 with cut-off ≥5 achieved the highest specificity (69.6%). The score by Borsari et al. showed the highest levels of positive and negative predictive values (59.8% and 91.5%) and likelihood ratios (2.4 and 0.1) as well as the highest area under the curve values (0.76; 95% CI 0.72-0.81; P < 0.001).

CONCLUSIONS

High levels of accuracy were found for each of the four considered scores. No differences were found among scores in confirming melanoma diagnosis when positive; however, the score by Borsari 2018 was the best in excluding melanoma diagnosis when negative.

Visual inspection and dermoscopy, alone or in combination, for diagnosing keratinocyte skin cancers in adults

BACKGROUND

Early accurate detection of all skin cancer types is important to guide appropriate management, to reduce morbidity and to improve survival. Basal cell carcinoma (BCC) is almost always a localised skin cancer with potential to infiltrate and damage surrounding tissue, whereas a minority of cutaneous squamous cell carcinomas (cSCCs) and invasive melanomas are higher-risk skin cancers with the potential to metastasise and cause death. Dermoscopy has become an important tool to assist specialist clinicians in the diagnosis of melanoma, and is increasingly used in primary-care settings. Dermoscopy is a precision-built handheld illuminated magnifier that allows more detailed examination of the skin down to the level of the superficial dermis. Establishing the value of dermoscopy over and above visual inspection for the diagnosis of BCC or cSCC in primary- and secondary-care settings is critical to understanding its potential contribution to appropriate skin cancer triage, including referral of higher-risk cancers to secondary care, the identification of low-risk skin cancers that might be treated in primary care and to provide reassurance to those with benign skin lesions who can be safely discharged.

OBJECTIVES

To determine the diagnostic accuracy of visual inspection and dermoscopy, alone or in combination, for the detection of (a) BCC and (b) cSCC, in adults. We separated studies according to whether the diagnosis was recorded face-to-face (in person) or based on remote (image-based) assessment.

SEARCH METHODS

We undertook a comprehensive search of the following databases from inception up to August 2016: Cochrane Central Register of Controlled Trials; MEDLINE; Embase; CINAHL; CPCI; Zetoc; Science Citation Index; US National Institutes of Health Ongoing Trials Register; NIHR Clinical Research Network Portfolio Database; and the World Health Organization International Clinical Trials Registry Platform. We studied reference lists and published systematic review articles.

SELECTION CRITERIA

Studies of any design that evaluated visual inspection or dermoscopy or both in adults with lesions suspicious for skin cancer, compared with a reference standard of either histological confirmation or clinical follow-up.

DATA COLLECTION AND ANALYSIS

Two review authors independently extracted all data using a standardised data extraction and quality assessment form (based on QUADAS-2). We contacted authors of included studies where information related to the target condition or diagnostic thresholds were missing. We estimated accuracy using hierarchical summary ROC methods. We undertook analysis of studies allowing direct comparison between tests. To facilitate interpretation of results, we computed values of sensitivity at the point on the SROC curve with 80% fixed specificity and values of specificity with 80% fixed sensitivity. We investigated the impact of in-person test interpretation; use of a purposely-developed algorithm to assist diagnosis; and observer expertise.

MAIN RESULTS

We included 24 publications reporting on 24 study cohorts, providing 27 visual inspection datasets (8805 lesions; 2579 malignancies) and 33 dermoscopy datasets (6855 lesions; 1444 malignancies). The risk of bias was mainly low for the index test (for dermoscopy evaluations) and reference standard domains, particularly for in-person evaluations, and high or unclear for participant selection, application of the index test for visual inspection and for participant flow and timing. We scored concerns about the applicability of study findings as of 'high' or 'unclear' concern for almost all studies across all domains assessed. Selective participant recruitment, lack of reproducibility of diagnostic thresholds and lack of detail on observer expertise were particularly problematic.The detection of BCC was reported in 28 datasets; 15 on an in-person basis and 13 image-based. Analysis of studies by prior testing of participants and according to observer expertise was not possible due to lack of data. Studies were primarily conducted in participants referred for specialist assessment of lesions with available histological classification. We found no clear differences in accuracy between dermoscopy studies undertaken in person and those which evaluated images. The lack of effect observed may be due to other sources of heterogeneity, including variations in the types of skin lesion studied, in dermatoscopes used, or in the use of algorithms and varying thresholds for deciding on a positive test result.Meta-analysis found in-person evaluations of dermoscopy (7 evaluations; 4683 lesions and 363 BCCs) to be more accurate than visual inspection alone for the detection of BCC (8 evaluations; 7017 lesions and 1586 BCCs), with a relative diagnostic odds ratio (RDOR) of 8.2 (95% confidence interval (CI) 3.5 to 19.3; P < 0.001). This corresponds to predicted differences in sensitivity of 14% (93% versus 79%) at a fixed specificity of 80% and predicted differences in specificity of 22% (99% versus 77%) at a fixed sensitivity of 80%. We observed very similar results for the image-based evaluations.When applied to a hypothetical population of 1000 lesions, of which 170 are BCC (based on median BCC prevalence across studies), an increased sensitivity of 14% from dermoscopy would lead to 24 fewer BCCs missed, assuming 166 false positive results from both tests. A 22% increase in specificity from dermoscopy with sensitivity fixed at 80% would result in 183 fewer unnecessary excisions, assuming 34 BCCs missed for both tests. There was not enough evidence to assess the use of algorithms or structured checklists for either visual inspection or dermoscopy.Insufficient data were available to draw conclusions on the accuracy of either test for the detection of cSCCs.

AUTHORS' CONCLUSIONS

Dermoscopy may be a valuable tool for the diagnosis of BCC as an adjunct to visual inspection of a suspicious skin lesion following a thorough history-taking including assessment of risk factors for keratinocyte cancer. The evidence primarily comes from secondary-care (referred) populations and populations with pigmented lesions or mixed lesion types. There is no clear evidence supporting the use of currently-available formal algorithms to assist dermoscopy diagnosis.

Dermoscopy, with and without visual inspection, for diagnosing melanoma in adults

BACKGROUND

Melanoma has one of the fastest rising incidence rates of any cancer. It accounts for a small percentage of skin cancer cases but is responsible for the majority of skin cancer deaths. Although history-taking and visual inspection of a suspicious lesion by a clinician are usually the first in a series of 'tests' to diagnose skin cancer, dermoscopy has become an important tool to assist diagnosis by specialist clinicians and is increasingly used in primary care settings. Dermoscopy is a magnification technique using visible light that allows more detailed examination of the skin compared to examination by the naked eye alone. Establishing the additive value of dermoscopy over and above visual inspection alone across a range of observers and settings is critical to understanding its contribution for the diagnosis of melanoma and to future understanding of the potential role of the growing number of other high-resolution image analysis techniques.

OBJECTIVES

To determine the diagnostic accuracy of dermoscopy alone, or when added to visual inspection of a skin lesion, for the detection of cutaneous invasive melanoma and atypical intraepidermal melanocytic variants in adults. We separated studies according to whether the diagnosis was recorded face-to-face (in-person), or based on remote (image-based), assessment.

SEARCH METHODS

We undertook a comprehensive search of the following databases from inception up to August 2016: CENTRAL; MEDLINE; Embase; CINAHL; CPCI; Zetoc; Science Citation Index; US National Institutes of Health Ongoing Trials Register; NIHR Clinical Research Network Portfolio Database; and the World Health Organization International Clinical Trials Registry Platform. We studied reference lists and published systematic review articles.

SELECTION CRITERIA

Studies of any design that evaluated dermoscopy in adults with lesions suspicious for melanoma, compared with a reference standard of either histological confirmation or clinical follow-up. Data on the accuracy of visual inspection, to allow comparisons of tests, was included only if reported in the included studies of dermoscopy.

DATA COLLECTION AND ANALYSIS

Two review authors independently extracted all data using a standardised data extraction and quality assessment form (based on QUADAS-2). We contacted authors of included studies where information related to the target condition or diagnostic threshold were missing. We estimated accuracy using hierarchical summary receiver operating characteristic (SROC),methods. Analysis of studies allowing direct comparison between tests was undertaken. To facilitate interpretation of results, we computed values of sensitivity at the point on the SROC curve with 80% fixed specificity and values of specificity with 80% fixed sensitivity. We investigated the impact of in-person test interpretation; use of a purposely developed algorithm to assist diagnosis; observer expertise; and dermoscopy training.

MAIN RESULTS

We included a total of 104 study publications reporting on 103 study cohorts with 42,788 lesions (including 5700 cases), providing 354 datasets for dermoscopy. The risk of bias was mainly low for the index test and reference standard domains and mainly high or unclear for participant selection and participant flow. Concerns regarding the applicability of study findings were largely scored as 'high' concern in three of four domains assessed. Selective participant recruitment, lack of reproducibility of diagnostic thresholds and lack of detail on observer expertise were particularly problematic.The accuracy of dermoscopy for the detection of invasive melanoma or atypical intraepidermal melanocytic variants was reported in 86 datasets; 26 for evaluations conducted in person (dermoscopy added to visual inspection), and 60 for image-based evaluations (diagnosis based on interpretation of dermoscopic images). Analyses of studies by prior testing revealed no obvious effect on accuracy; analyses were hampered by the lack of studies in primary care, lack of relevant information and the restricted inclusion of lesions selected for biopsy or excision. Accuracy was higher for in-person diagnosis compared to image-based evaluations (relative diagnostic odds ratio (RDOR) 4.6, 95% confidence interval (CI) 2.4 to 9.0; P < 0.001).We compared accuracy for (a), in-person evaluations of dermoscopy (26 evaluations; 23,169 lesions and 1664 melanomas),versus visual inspection alone (13 evaluations; 6740 lesions and 459 melanomas), and for (b), image-based evaluations of dermoscopy (60 evaluations; 13,475 lesions and 2851 melanomas),versus image-based visual inspection (11 evaluations; 1740 lesions and 305 melanomas). For both comparisons, meta-analysis found dermoscopy to be more accurate than visual inspection alone, with RDORs of (a), 4.7 (95% CI 3.0 to 7.5; P < 0.001), and (b), 5.6 (95% CI 3.7 to 8.5; P < 0.001). For a), the predicted difference in sensitivity at a fixed specificity of 80% was 16% (95% CI 8% to 23%; 92% for dermoscopy + visual inspection versus 76% for visual inspection), and predicted difference in specificity at a fixed sensitivity of 80% was 20% (95% CI 7% to 33%; 95% for dermoscopy + visual inspection versus 75% for visual inspection). For b) the predicted differences in sensitivity was 34% (95% CI 24% to 46%; 81% for dermoscopy versus 47% for visual inspection), at a fixed specificity of 80%, and predicted difference in specificity was 40% (95% CI 27% to 57%; 82% for dermoscopy versus 42% for visual inspection), at a fixed sensitivity of 80%.Using the median prevalence of disease in each set of studies ((a), 12% for in-person and (b), 24% for image-based), for a hypothetical population of 1000 lesions, an increase in sensitivity of (a), 16% (in-person), and (b), 34% (image-based), from using dermoscopy at a fixed specificity of 80% equates to a reduction in the number of melanomas missed of (a), 19 and (b), 81 with (a), 176 and (b), 152 false positive results. An increase in specificity of (a), 20% (in-person), and (b), 40% (image-based), at a fixed sensitivity of 80% equates to a reduction in the number of unnecessary excisions from using dermoscopy of (a), 176 and (b), 304 with (a), 24 and (b), 48 melanomas missed.The use of a named or published algorithm to assist dermoscopy interpretation (as opposed to no reported algorithm or reported use of pattern analysis), had no significant impact on accuracy either for in-person (RDOR 1.4, 95% CI 0.34 to 5.6; P = 0.17), or image-based (RDOR 1.4, 95% CI 0.60 to 3.3; P = 0.22), evaluations. This result was supported by subgroup analysis according to algorithm used. We observed higher accuracy for observers reported as having high experience and for those classed as 'expert consultants' in comparison to those considered to have less experience in dermoscopy, particularly for image-based evaluations. Evidence for the effect of dermoscopy training on test accuracy was very limited but suggested associated improvements in sensitivity.

AUTHORS' CONCLUSIONS

Despite the observed limitations in the evidence base, dermoscopy is a valuable tool to support the visual inspection of a suspicious skin lesion for the detection of melanoma and atypical intraepidermal melanocytic variants, particularly in referred populations and in the hands of experienced users. Data to support its use in primary care are limited, however, it may assist in triaging suspicious lesions for urgent referral when employed by suitably trained clinicians. Formal algorithms may be of most use for dermoscopy training purposes and for less expert observers, however reliable data comparing approaches using dermoscopy in person are lacking.

Lesions Mimicking Melanoma at Dermoscopy Confirmed Basal Cell Carcinoma: Evaluation with Reflectance Confocal Microscopy

Background: Atypical basal cell carcinoma (BCC), characterized by equivocal dermoscopic features typical of malignant melanoma (MM), can be difficult to diagnose. Reflectance confocal microscopy (RCM) enables in vivo imaging at nearly histological resolution. Objectives: To evaluate with RCM atypical melanocytic lesions identified in dermoscopy, according to common RCM criteria for the differential diagnosis of BCC, and to identify representative RCM parameters for superficial (sBCCs) and nonsuperficial (nsBCCs) basal cell carcinomas (BCCs). Methods: A retrospective analysis of consecutive patients evaluated with RCM, selecting excised lesions classified at dermoscopy with ≥1 score from the re visited 7-point checklist, mimicking melanoma, registered between 2010 and 2016. Cluster analysis identified BCC subclassifications. Results: Of 178 atypical lesions, 34 lesions were diagnosed as BCCs with RCM. Lesions were confirmed BCCs with histopathology. Dermoscopic features included atypical network (55.9%) and regression structures (35.5%) associated with sBCCs, and an atypical vascular pattern (58.8%) and irregular blotches (58.8%) with nsBCCs. Hierarchical cluster analysis identified 2 clusters: cluster 1 (100% sBCCs) was characterized by the presence of cords connected to the epidermis (90%, p < 0.001), tumor islands located in the epidermis (100%, p < 0.001), smaller vascular diameter (100%, p < 0.001) and solar elastosis (90%, p = 0.017), and cluster 2 (nsBCCs 85%) was defined by the dermic location of tumor islands (87.5%, p < 0.001) with branch-like structures (70.8%, p = 0.007) and surrounding collagen (83.3%, p = 0.012), peripheral palisading (83.3%, p = 0.012) and coiled vascular morphology (79.2%, p < 0.001) with a larger vascular diameter (50%, p < 0.001). Conclusions: RCM is able to diagnose BCCs mimicking melanoma at dermoscopy and seems able to identify sBCCs and nsBCCs.

Acral lentiginous melanoma in the Turkish population and a new dermoscopic clue for the diagnosis

Background

The incidence of acral lentiginous melanoma (ALM) in the white population is low. Dermoscopy enhances diagnosis of ALM; however, diagnostic accuracy may sometimes be poor due to the considerable proportion of amelanotic ALM variants.

Objectives

To calculate the proportion of ALM among all melanoma subtypes and to determine the frequency of dermoscopic features of ALM in the Turkish population.

Methods

Out of 612 melanomas, there were 70 cases of ALM, of which 46 showed sufficient image quality for retrospective study of dermoscopic features. Data from patients and their lesions was classified according to clinical features and histopathologic parameters. The dermoscopic variables evaluated were based on pertinent literature on dermoscopy of acral melanocytic neoplasms.

Results

The prevalence of ALM among all melanoma subtypes was 11.4%. Parallel-ridge pattern (PRP) was detected in 60.8% of cases and irregular diffuse pigmentation (IDP) in 28.3%. The ALMs were amelanotic in 24%, showing an atypical vascular pattern in all cases; a new dermoscopic pattern, named “vascularized parallel-ridge pattern” (VPRP), was detected in 13% of ALMs. Irregular lines were observed in 81.8% of subungual melanomas and were often associated with a multicolored background.

Conclusions

ALM has site-specific dermoscopic patterns, with PRP being the most prevalent pattern. The newly described VPRP pattern may be an additional clue for ALM diagnosis, especially in thin amelanotic melanomas.

Dermoscopy of a Spark's nevus

Spark’s nevus is a particular type of melanocytic nevus that on histology shows features of both Spitz’s and Clark’s nevus. Clinically, it is an asymmetric, irregular, multicolored, pigmented lesion that is not clearly distinguishable from melanoma or dysplastic (Clark’s) nevus. Dermoscopic features have not been described yet, and one could speculate that they are similar to those of Clark’s nevi because the histopathologic architecture of Spark’s nevus is similar to that of a Clark’s nevus, resembling Spitz’s nevi in the epithelioid morphology of melanocytes. We present a 32-year-old woman with a Spark’s nevus, who upon dermoscopy showed a pronounced atypical network with accentuation of the blue veil and mostly peripheral dots.

7-Point Checklist and Skin Lesion Classification using Multi-Task Multi-Modal Neural Nets

We propose a multi-task deep convolutional neural network, trained on multi-modal data (clinical and dermoscopic images, and patient meta-data), to classify the 7-point melanoma checklist criteria and perform skin lesion diagnosis. Our neural network is trained using several multi-task loss functions, where each loss considers different combinations of the input modalities, which allows our model to be robust to missing data at inference time. Our final model classifies the 7-point checklist and skin condition diagnosis, produces multi-modal feature vectors suitable for image retrieval, and localizes clinically discriminant regions. We benchmark our approach using 1011 lesion cases, and report comprehensive results over all 7-point criteria and diagnosis. We also make our dataset (images and metadata) publicly available online at http://derm.cs.sfu.ca.

Dermoscopy pathology correlation in melanoma

Dermoscopy is a widely used technique whose role in the clinical (and preoperative) diagnosis of melanocytic and non-melanocytic skin lesions has been well established in recent years. The aim of this paper is to clarify the correlations between the "local" dermoscopic findings in melanoma and the underlying histology, in order to help clinicians in routine practice.