Dermatoscopic patterns of cutaneous metastases: A multicentre cross-sectional study of the International Dermoscopy Society.

BACKGROUND: The detection of cutaneous metastases (CMs) from various primary tumours represents a diagnostic challenge. OBJECTIVES: Our aim was to evaluate the general characteristics and dermatoscopic features of CMs from different primary tumours. METHODS: Retrospective, multicentre, descriptive, cross-sectional study of biopsy-proven CMs. RESULTS: We included 583 patients (247 females, median age: 64 years, 25%-75% percentiles: 54-74 years) with 632 CMs, of which 52.2% (n = 330) were local, and 26.7% (n = 169) were distant. The most common primary tumours were melanomas (n = 474) and breast cancer (n = 59). Most non-melanoma CMs were non-pigmented (n = 151, 95.6%). Of 169 distant metastases, 54 (32.0%) appeared on the head and neck region. On dermatoscopy, pigmented melanoma metastases were frequently structureless blue (63.6%, n = 201), while amelanotic metastases were typified by linear serpentine vessels and a white structureless pattern. No significant difference was found between amelanotic melanoma metastases and CMs of other primary tumours. CONCLUSIONS: The head and neck area is a common site for distant CMs. Our study confirms that most pigmented melanoma metastasis are structureless blue on dermatoscopy and may mimic blue nevi. Amelanotic metastases are typified by linear serpentine vessels and a white structureless pattern, regardless of the primary tumour.

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.

Observational study investigating the level of support from a convolutional neural network in face and scalp lesions deemed diagnostically 'unclear' by dermatologists.

BACKGROUND: The clinical diagnosis of face and scalp lesions (FSL) is challenging due to overlapping features. Dermatologists encountering diagnostically 'unclear' lesions may benefit from artificial intelligence support via convolutional neural networks (CNN). METHODS: In a web-based classification task, dermatologists (n = 64) diagnosed a convenience sample of 100 FSL as 'benign', 'malignant', or 'unclear' and indicated their management decisions ('no action', 'follow-up', 'treatment/excision'). A market-approved CNN (Moleanalyzer-Pro®, FotoFinder Systems, Germany) was applied for binary classifications (benign/malignant) of dermoscopic images. RESULTS: After reviewing one dermoscopic image per case, dermatologists labelled 562 of 6400 diagnoses (8.8%) as 'unclear' and mostly managed these by follow-up examinations (57.3%, n = 322) or excisions (42.5%, n = 239). Management was incorrect in 58.8% of 291 truly malignant cases (171 'follow-up' or 'no action') and 43.9% of 271 truly benign cases (119 'excision'). Accepting CNN classifications in unclear cases would have reduced false management decisions to 4.1% in truly malignant and 31.7% in truly benign lesions (both p < 0.01). After receiving full case information 239 diagnoses (3.7%) remained 'unclear' to dermatologists, now triggering more excisions (72.0%) than follow-up examinations (28.0%). These management decisions were incorrect in 32.8% of 116 truly malignant cases and 76.4% of 123 truly benign cases. Accepting CNN classifications would have reduced false management decisions to 6.9% in truly malignant lesions and to 38.2% in truly benign cases (both p < 0.01). CONCLUSIONS: Dermatologists mostly managed diagnostically 'unclear' FSL by treatment/excision or follow-up examination. Following CNN classifications as guidance in unclear cases seems suitable to significantly reduce incorrect decisions.

New AI-algorithms on smartphones to detect skin cancer in a clinical setting-A validation study.

BACKGROUND AND OBJECTIVES: The incidence of skin cancer is rising worldwide and there is medical need to optimize its early detection. This study was conducted to determine the diagnostic and risk-assessment accuracy of two new diagnosis-based neural networks (analyze and detect), which comply with the CE-criteria, in evaluating the malignant potential of various skin lesions on a smartphone. Of note, the intention of our study was to evaluate the performance of these medical products in a clinical setting for the first time. METHODS: This was a prospective, single-center clinical study at one tertiary referral center in Graz, Austria. Patients, who were either scheduled for preventive skin examination or removal of at least one skin lesion were eligible for participation. Patients were assessed by at least two dermatologists and by the integrated algorithms on different mobile phones. The lesions to be recorded were randomly selected by the dermatologists. The diagnosis of the algorithm was stated as correct if it matched the diagnosis of the two dermatologists or the histology (if available). The histology was the reference standard, however, if both clinicians considered a lesion as being benign no histology was performed and the dermatologists were stated as reference standard. RESULTS: A total of 238 patients with 1171 lesions (86 female; 36.13%) with an average age of 66.19 (SD = 17.05) was included. Sensitivity and specificity of the detect algorithm were 96.4% (CI 93.94-98.85) and 94.85% (CI 92.46-97.23); for the analyze algorithm a sensitivity of 95.35% (CI 93.45-97.25) and a specificity of 90.32% (CI 88.1-92.54) were achieved. DISCUSSION: The studied neural networks succeeded analyzing the risk of skin lesions with a high diagnostic accuracy showing that they are sufficient tools in calculating the probability of a skin lesion being malignant. In conjunction with the wide spread use of smartphones this new AI approach opens the opportunity for a higher early detection rate of skin cancer with consecutive lower epidemiological burden of metastatic cancer and reducing health care costs. This neural network moreover facilitates the empowerment of patients, especially in regions with a low density of medical doctors. REGISTRATION: Approved and registered at the ethics committee of the Medical University of Graz, Austria (Approval number: 30-199 ex 17/18).

Common Benign Melanocytic and Non-Melanocytic Skin Tumors among the Elderly: Results of the Graz Study on Health and Aging.

BACKGROUND AND OBJECTIVES: Benign skin tumors are the most common skin findings and contribute to the major reasons for consulting a dermatologist. However, the frequency of benign skin tumors concerning different body areas and their relationship with sun-related behavior have not been sufficiently characterized. We aimed to improve knowledge about the anatomic distribution of the most frequently occurring benign skin tumors among a healthy predominant elderly population. Furthermore, we investigated associations with sun-related habits. METHODS: In total, 100 participants, 37 men, and 63 women (mean age: 67.2 years; range: 46-86 years) were enrolled in the Graz Study on Health and Aging (GSHA) cohort. Full body images were investigated for melanocytic nevi, seborrheic keratoses, hemangiomas, dermatofibromas, and lentigines. Information on the phenotypic trait, sun exposure, use of sun-protective measures, and history of sunburns was collected in a questionnaire. RESULTS: Common melanocytic nevi were the most frequently encountered skin lesions. Male sex was associated with multiple common nevi on the abdomen and the presence of atypical nevi. High sun exposure in central European latitudes during adolescence was positively associated with multiple common nevi on the total body. Multiple common nevi and atypical nevi on the back correlated with frequent use of sunscreens with SPF during young adulthood and adolescence, respectively. CONCLUSION: Our study adds new knowledge about the most frequently occurring benign skin tumors, considering all visible body areas. This research may serve as a reference basis for following epidemiological studies.

Vascular Diameter as Clue for the Diagnosis of Clinically and/or Dermoscopically Equivocal Pigmented and Non-Pigmented Basal Cell Carcinomas and Nodular Melanomas.

Background and objectives: Dermoscopy is a useful tool for the early and non-invasive diagnosis of skin malignancies. Besides many progresses, heavily pigmented and amelanotic skin tumors remain still a challenge. We aimed to investigate by dermoscopy if distinctive morphologic characteristics of vessels may help the diagnosis of equivocal nodular lesions. Materials and Methods: A collage of 16 challenging clinical and dermoscopic images of 8 amelanotic and 8 heavily pigmented nodular melanomas and basal cell carcinomas was sent via e-mail to 8 expert dermoscopists. Results: Dermoscopy improved diagnostic accuracy in 40 cases. Vessels were considered the best clue in 71 cases. Focusing on the diameter of vessels improved diagnosis in 5 cases. Conclusions: vascular diameter in addition to morphology and arrangement may be a useful dermoscopic clue for the differential diagnosis of clinically equivocal nodular malignant tumors.

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.

Reproducible Naevus Counts Using 3D Total Body Photography and Convolutional Neural Networks.

BACKGROUND: The number of naevi on a person is the strongest risk factor for melanoma; however, naevus counting is highly variable due to lack of consistent methodology and lack of inter-rater agreement. Machine learning has been shown to be a valuable tool for image classification in dermatology. OBJECTIVES: To test whether automated, reproducible naevus counts are possible through the combination of convolutional neural networks (CNN) and three-dimensional (3D) total body imaging. METHODS: Total body images from a study of naevi in the general population were used for the training (82 subjects, 57,742 lesions) and testing (10 subjects; 4,868 lesions) datasets for the development of a CNN. Lesions were labelled as naevi, or not ("non-naevi"), by a senior dermatologist as the gold standard. Performance of the CNN was assessed using sensitivity, specificity, and Cohen's kappa, and evaluated at the lesion level and person level. RESULTS: Lesion-level analysis comparing the automated counts to the gold standard showed a sensitivity and specificity of 79% (76-83%) and 91% (90-92%), respectively, for lesions ≥2 mm, and 84% (75-91%) and 91% (88-94%) for lesions ≥5 mm. Cohen's kappa was 0.56 (0.53-0.59) indicating moderate agreement for naevi ≥2 mm, and substantial agreement (0.72, 0.63-0.80) for naevi ≥5 mm. For the 10 individuals in the test set, person-level agreement was assessed as categories with 70% agreement between the automated and gold standard counts. Agreement was lower in subjects with numerous seborrhoeic keratoses. CONCLUSION: Automated naevus counts with reasonable agreement to those of an expert clinician are possible through the combination of 3D total body photography and CNNs. Such an algorithm may provide a faster, reproducible method over the traditional in person total body naevus counts.

In Vivo Reflectance Confocal Microscopy as a Response Monitoring Tool for Actinic Keratoses Undergoing Cryotherapy and Photodynamic Therapy.

Reflectance confocal microscopy (RCM) presents a non-invasive method to image actinic keratosis (AK) at a cellular level. However, RCM criteria for AK response monitoring vary across studies and a universal, standardized approach is lacking. We aimed to identify reliable AK response criteria and to compare the clinical and RCM evaluation of responses across AK severity grades. Twenty patients were included and randomized to receive either cryotherapy (n = 10) or PDT (n = 10). Clinical assessment and RCM evaluation of 12 criteria were performed in AK lesions and photodamaged skin at baseline, 3 and 6 months. We identified the RCM criteria that reliably characterize AK at baseline and display significant reduction following treatment. Those with the highest baseline odds ratio (OR), good interobserver agreement, and most significant change over time were atypical honeycomb pattern (OR: 12.7, CI: 5.7-28.1), hyperkeratosis (OR: 13.6, CI: 5.3-34.9), stratum corneum disruption (OR: 7.8, CI: 3.5-17.3), and disarranged epidermal pattern (OR: 6.5, CI: 2.9-14.8). Clinical evaluation demonstrated a significant treatment response without relapse. However, in grade 2 AK, 10/12 RCM parameters increased from 3 to 6 months, which suggested early subclinical recurrence detection by RCM. Incorporating standardized RCM protocols for the assessment of AK may enable a more meaningful comparison across clinical trials, while allowing for the early detection of relapses and evaluation of biological responses to therapy over time.

Clinical and Dermoscopic Features of Melanocytic Lesions on the Face Versus the External Ear.

INTRODUCTION: Melanoma of the external ear is a rare condition accounting for 7-20% of all melanomas of the head and neck region. They present classical features of extra-facial melanomas clinically and dermoscopically. In contrast, facial melanomas show peculiar patterns in dermoscopy. OBJECTIVES: To evaluate whether there are clinical and/or dermoscopic differences in melanocytic lesions located either at the external ear or on the face. METHODS: In this retrospective study we reviewed an image database for clinical and dermoscopic images of melanomas and nevi located either on the face or at the level of the external ear. RESULTS: 65 patients (37 men; 63.8%) with 65 lesions were included. We found no significant differences in comparing face melanomas with melanomas at the level of the external ear, neither clinically nor dermoscopically. However, we provided evidence for differences in some clinical and dermoscopic features of melanomas and nevi of the external ear. CONCLUSIONS: In this study, we reported no significant differences in comparing melanomas on the face with melanomas of the external ear, both clinically and dermoscopically. Furthermore, we provided data on clinical and dermoscopic differences comparing nevi and melanoma of the external ear.

Skin lesions of face and scalp - Classification by a market-approved convolutional neural network in comparison with 64 dermatologists.

BACKGROUND: The clinical differentiation of face and scalp lesions (FSLs) is challenging even for trained dermatologists. Studies comparing the diagnostic performance of a convolutional neural network (CNN) with dermatologists in FSL are lacking. METHODS: A market-approved CNN (Moleanalyzer-Pro, FotoFinder Systems) was used for binary classifications of 100 dermoscopic images of FSL. The same lesions were used in a two-level reader study including 64 dermatologists (level I: dermoscopy only; level II: dermoscopy, clinical close-up images, textual information). Primary endpoints were the CNN's sensitivity and specificity in comparison with the dermatologists' management decisions in level II. Generalizability of the CNN results was tested by using four additional external data sets. RESULTS: The CNN's sensitivity, specificity and ROC AUC were 96.2% [87.0%-98.9%], 68.8% [54.7%-80.1%] and 0.929 [0.880-0.978], respectively. In level II, the dermatologists' management decisions showed a mean sensitivity of 84.2% [82.2%-86.2%] and specificity of 69.4% [66.0%-72.8%]. When fixing the CNN's specificity at the dermatologists' mean specificity (69.4%), the CNN's sensitivity (96.2% [87.0%-98.9%]) was significantly higher than that of dermatologists (84.2% [82.2%-86.2%]; p < 0.001). Dermatologists of all training levels were outperformed by the CNN (all p < 0.001). In confirmation, the CNN's accuracy (83.0%) was significantly higher than dermatologists' accuracies in level II management decisions (all p < 0.001). The CNN's performance was largely confirmed in three additional external data sets but particularly showed a reduced specificity in one Australian data set including FSL on severely sun-damaged skin. CONCLUSIONS: When applied as an assistant system, the CNN's higher sensitivity at an equivalent specificity may result in an improved early detection of face and scalp skin cancers.

Accuracy of mobile digital teledermoscopy for skin self-examinations in adults at high risk of skin cancer: an open-label, randomised controlled trial.

BACKGROUND: Skin self-examinations supplemented with mobile teledermoscopy might improve early detection of skin cancers compared with naked-eye skin self-examinations. We aimed to assess whether mobile teledermoscopy-enhanced skin self-examination can improve sensitivity and specificity of self-detection of skin cancers when compared with naked-eye skin self-examination. METHODS: This randomised, controlled trial was done in Brisbane (QLD, Australia). Eligible participants (aged ≥18 years) had at least two skin cancer risk factors as self-reported in the eligibility survey and had to own or have access to an iPhone compatible with a dermatoscope attachment (iPhone versions 5-8). Participants were randomly assigned (1:1), via a computer-generated randomisation procedure, to the intervention group (mobile dermoscopy-enhanced self-skin examination) or the control group (naked-eye skin self-examination). Control group and intervention group participants received web-based instructions on how to complete a whole body skin self-examination. All participants completed skin examinations at baseline, 1 month, and 2 months; intervention group participants submitted photographs of suspicious lesions to a dermatologist for telediagnosis after each skin examination and control group participants noted lesions on a body chart that was sent to the research team after each skin examination. All participants had an in-person whole-body clinical skin examination within 3 months of their last skin self-examination. Primary outcomes were sensitivity and specificity of skin self-examination, patient selection of clinically atypical lesions suspicious for melanoma or keratinocyte skin cancers (body sites examined, number of lesions photographed, types of lesions, and lesions missed), and diagnostic concordance of telediagnosis versus in-person whole-body clinical skin examination diagnosis. All primary outcomes were analysed in the modified intention-to-treat population, which included all patients who had a clinical skin examination within 3 months of their last skin self-examination. This trial was registered with the Australian and New Zealand Clinical Trials Registry, ACTRN12616000989448. FINDINGS: Between March 6, 2017, and June 7, 2018, 234 participants consented to enrol in the study, of whom 116 (50%) were assigned to the intervention group and 118 (50%) were assigned to the control group. 199 participants (98 participants in the intervention group and 101 participants in the control group) attended the clinical skin examination and thus were eligible for analyses. Participants in the intervention group submitted 615 lesions (median 6·0 per person; range 1-24) for telediagnosis and participants in the control group identified and recorded 673 lesions (median 6·0 per person; range 1-16). At the lesion level, sensitivity for lesions clinically suspicious for skin cancer was 75% (95% CI 63-84) in the intervention group and 88% (95% CI 80-91) in the control group (p=0·04). Specificity was 87% (95% CI 85-90) in the intervention group and 89% (95% CI 87-91) in the control group (p=0·42). At the individual level, the intervention group had a sensitivity of 87% (95% CI 76-99) compared with 97% (95% CI 91-100) in the control group (p=0·26), and a specificity of 95% (95% CI 90-100) compared with 96% (95% CI 91-100) in the control group. The overall diagnostic concordance between the telediagnosis and in-person clinical skin examination was 88%. INTERPRETATION: The use of mobile teledermoscopy did not increase sensitivity for the detection of skin cancers compared with naked-eye skin self-examination; thus, further evidence is necessary for inclusion of skin self-examination technology for public health benefit. FUNDING: National Health and Medical Research Council (Australia).

The importance of total-body photography and sequential digital dermatoscopy for monitoring patients at increased melanoma risk.

BACKGROUND AND OBJECTIVES: The incidence of melanoma is rising and prevention plays an important role. Multiple nevi as well as a medical history of melanoma are important risk factors. In affected patients, a two-step algorithm consisting of total-body photography (TBP) and sequential digital dermatoscopy (SDD) is a helpful diagnostic tool. PATIENTS AND METHODS: This was a retrospective observational study that lasted six years in order to evaluate the significance of the two-step algorithm. Cases were evaluated based on distinct dermoscopic patterns and statistical analyses were performed with the latest version of SPSS. RESULTS: 6020 dermoscopic images of 214 patients were included. TBP was performed at a mean interval of 16.9 months (SD ± 1.43 months), while SDD was performed every 9.9 months (SD ± 1.68 months). The number needed to excise was 4.6 and the number needed to monitor was 548. Excisions were mostly performed because dynamic changes were observed. A total of eleven melanomas were detected and had a mean tumor thickness of 0.44 mm (SD ± 0.15 mm; range 0.2-0.6 mm). CONCLUSIONS: Invasive melanomas had a tumor thickness of less than 0.6 mm, thus providing evidence of an effective strategy for early melanoma detection. Excisions of benign nevi were minimized as indicated by a low number needed to excise.