A multicentre study of naevus-associated melanoma vs. de novo melanoma, tumour thickness and body site differences

BACKGROUND

Whether melanoma in histological contiguity with a naevus [naevus-associated melanoma (NAM)] is distinctly different from melanoma arising de novo remains unclear.

OBJECTIVES

To determine whether the characteristics of de novo melanoma differ from NAM and are not due to naevus obliteration in thicker tumours.

METHODS

We conducted a multicentre retrospective study of de novo melanoma and NAM in seven referral centres in Europe, Australia and the USA between 2006 and 2015.

RESULTS

In a total of 9474 localized melanomas, de novo melanoma was associated with thicker tumours and body site differences compared with NAM. In the subset of T1 melanomas (n = 5307), similar body site differences were found in multivariate analysis by body site. When compared with NAM, de novo melanoma was more likely to affect older individuals (≥ 70 years) when located on the head/neck [odds ratio (OR) 4·65, 95% confidence interval (CI) 2·55-8·46], the trunk (OR 1·82, 95% CI 1·40-2·36) or the upper extremity (OR 1·69, 95% CI 1·14-2·50), was more likely to affect female patients when located on the lower extremities (OR 1·36, 95% CI 1·03-1·80), and was more likely to be of the nodular melanoma subtype (OR 2·23, 95% CI 1·14-4·35) when located on the trunk. De novo melanoma was less likely to have regression present compared with NAM.

CONCLUSIONS

Clinicopathological and body site differences between de novo melanoma and NAM support the divergent pathway model of development. These differences were also found in thin melanomas, suggesting that de novo melanomas are different from NAM and their differences are not due to the obliteration of naevus remnants in thicker tumours.

Commentary: Atypical melanocytic skin lesions - does the anatomical location have an impact on their clinical and dermoscopic appearance?

Linked article: L. Tognetti et al. J Eur Acad Dermatol Venereol 2021; 35: 650–657. https://doi.org/10.1111/jdv.16847.

Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditions

BACKGROUND

Convolutional neural networks (CNNs) efficiently differentiate skin lesions by image analysis. Studies comparing a market-approved CNN in a broad range of diagnoses to dermatologists working under less artificial conditions are lacking.

MATERIALS AND METHODS

One hundred cases of pigmented/non-pigmented skin cancers and benign lesions were used for a two-level reader study in 96 dermatologists (level I: dermoscopy only; level II: clinical close-up images, dermoscopy, and textual information). Additionally, dermoscopic images were classified by a CNN approved for the European market as a medical device (Moleanalyzer Pro, FotoFinder Systems, Bad Birnbach, Germany). Primary endpoints were the sensitivity and specificity of the CNN's dichotomous classification in comparison with the dermatologists' management decisions. Secondary endpoints included the dermatologists' diagnostic decisions, their performance according to their level of experience, and the CNN's area under the curve (AUC) of receiver operating characteristics (ROC).

RESULTS

The CNN revealed a sensitivity, specificity, and ROC AUC with corresponding 95% confidence intervals (CI) of 95.0% (95% CI 83.5% to 98.6%), 76.7% (95% CI 64.6% to 85.6%), and 0.918 (95% CI 0.866-0.970), respectively. In level I, the dermatologists' management decisions showed a mean sensitivity and specificity of 89.0% (95% CI 87.4% to 90.6%) and 80.7% (95% CI 78.8% to 82.6%). With level II information, the sensitivity significantly improved to 94.1% (95% CI 93.1% to 95.1%; P < 0.001), while the specificity remained unchanged at 80.4% (95% CI 78.4% to 82.4%; P = 0.97). When fixing the CNN's specificity at the mean specificity of the dermatologists' management decision in level II (80.4%), the CNN's sensitivity was almost equal to that of human raters, at 95% (95% CI 83.5% to 98.6%) versus 94.1% (95% CI 93.1% to 95.1%); P = 0.1. In contrast, dermatologists were outperformed by the CNN in their level I management decisions and level I and II diagnostic decisions. More experienced dermatologists frequently surpassed the CNN's performance.

CONCLUSIONS

Under less artificial conditions and in a broader spectrum of diagnoses, the CNN and most dermatologists performed on the same level. Dermatologists are trained to integrate information from a range of sources rendering comparative studies that are solely based on one single case image inadequate.

Sclerodermiform basal cell carcinomas vs. other histotypes: analysis of specific demographic, clinical and dermatoscopic features

BACKGROUND

Among the various types of basal cell carcinoma, the sclerodermiform variant has a high risk of recurrence and local invasiveness. A systematic description of the dermatoscopic features associated with specific body localization is lacking.

OBJECTIVES

To describe the clinical and dermoscopic features of sclerodermiform basal cell carcinoma (BCC) according to localization in the body confronting with superficial and nodular types.

METHODS

Clinical and dermoscopic images of sclerodermiform, nodular and superficial BCCs were retrospectively evaluated to study the location in the various body districts, maximum diameter, clinical appearance of the lesion, features of edges and presence or absence of specific dermatoscopic criteria of BCCs.

RESULTS

We examined 291 histopathologically proven BCCs showing that in nodular BCCs, classical arborizing vessels were more frequently found in the body macro-area (trunk and limbs; n = 46, 97.9%) than in the head/neck area (n = 43, 82.7%); within sclerodermiform BCCs, short arborizing vessels were found more frequently in the head/neck district (n = 35, 49.3%) than in the body (n = 6, 23.1%; P-value 0.02); within nodular BCCs, multiple blue-grey dots and globules were more frequently found on the trunk (n = 23, 48.9%) than in the head/neck district (n = 12, 23.1%; P-value 0.01). In sclerodermiform BCCs, ulceration was found more frequently in the head/neck district (n = 38, 53.5%) than in the body (n = 4, 15.4%; P-value > 0.01), and in superficial BCCs, ulceration was found more frequently in the head/neck district (n = 5, 38.5%) than in the body (n = 8, 9.8%; P-value 0.02).

CONCLUSION

Our study shows that superficial BCC are found frequently in the head/neck district dermoscopically characterized by ulceration and arborizing vessels; nodular BCCs are more frequently found in the body than in the head/neck district, and the dermoscopic pattern is characterized by the combination of three features: (i) classical arborizing vessels, (ii) multiple blue-grey dots and (iii) globules. Instead, sclerodermiform BCC is preferentially located in areas at high-moderate risk of recurrence; if pink-white areas and/or fine arborizing vessels are seen, clinicians should consider this diagnosis. Furthermore, location-specific dermatoscopic criteria have been described.

Dermatoskopie, sequenzielle Videodermatoskopie, Ganzkörperfotografie, künstliche Intelligenz – was bringt uns die Zukunft?

Die Dermatoskopie ist mittlerweile ein fester Bestandteil einer jeden dermatologischen Untersuchung. Mit dieser Technik konnten die Früherkennung von Malignomen der Haut und deren Vorstufen deutlich verbessert und unnötige Exzisionen benigner Hautläsionen reduziert werden. Der Einsatz der Dermatoskopie umfasst mittlerweile auch die Beurteilung von entzündlichen und parasitären Dermatosen sowie Haarerkrankungen. Bei definierten Risikogruppen für ein Melanom sollte der Zwei-Schritte-Algorithmus, bestehend aus Ganzkörperfotografie und Videodermatoskopie, in entsprechenden Zeitintervallen zur Anwendung kommen. Mit dieser Methode können Melanome meist in einem sehr frühen Stadium entdeckt werden, da Veränderungen bestehender Muttermale sowie neu entstandene Läsionen früher festgestellt werden. In den letzten Jahren konnten mehrere Studien nachweisen, dass speziell geschulte neuronale Netzwerke Malignome der Haut, insbesondere Melanome, mit einer sehr hohen Treffsicherheit diagnostizieren können. Wie diese Computer-gestützte Diagnostik mithilfe einer künstlichen Intelligenz in den klinischen Alltag integriert werden kann und welche Vorteile sich hiervon ableiten lassen, ist derzeit noch nicht geklärt.

Diagnostic performance of a deep learning convolutional neural network in the differentiation of combined naevi and melanomas

BACKGROUND

Deep learning convolutional neural networks (CNN) may assist physicians in the diagnosis of melanoma. The capacity of a CNN to differentiate melanomas from combined naevi, the latter representing well-known melanoma simulators, has not been investigated.

OBJECTIVE

To assess the diagnostic performance of a CNN when used to differentiate melanomas from combined naevi in comparison with dermatologists.

METHODS

In this study, a CNN with regulatory approval for the European market (Moleanalyzer-Pro, FotoFinder Systems GmbH, Bad Birnbach, Germany) was used. We attained a dichotomous classification (benign, malignant) in dermoscopic images of 36 combined naevi and 36 melanomas with a mean Breslow thickness of 1.3 mm. Primary outcome measures were the CNN's sensitivity, specificity and the diagnostic odds ratio (DOR) in comparison with 11 dermatologists with different levels of experience.

RESULTS

The CNN revealed a sensitivity, specificity and DOR of 97.1% (95% CI [82.7-99.6]), 78.8% (95% CI [62.8-89.1.3]) and 34 (95% CI [4.8-239]), respectively. Dermatologists showed a lower mean sensitivity, specificity and DOR of 90.6% (95% CI [84.1-94.7]; P = 0.092), 71.0% (95% CI [62.6-78.1]; P = 0.256) and 24 (95% CI [11.6-48.4]; P = 0.1114). Under the assumption that dermatologists use the CNN to verify their (initial) melanoma diagnosis, dermatologists achieve an increased specificity of 90.3% (95% CI [79.8-95.6]) at an almost unchanged sensitivity. The largest benefit was observed in 'beginners', who performed worst without CNN verification (DOR = 12) but best with CNN verification (DOR = 98).

CONCLUSION

The tested CNN more accurately classified combined naevi and melanomas in comparison with trained dermatologists. Their diagnostic performance could be improved if the CNN was used to confirm/overrule an initial melanoma diagnosis. Application of a CNN may therefore be of benefit to clinicians.

Clinical and dermoscopic clues to differentiate pigmented nail bands: an International Dermoscopy Society study

BACKGROUND

Longitudinal melanonychia might be difficult to differentiate and the use of dermoscopy can be useful for the preoperative evaluation and management decision.

OBJECTIVES

The aim of our study was to investigate clinical and dermoscopic criteria of acquired longitudinal melanonychia in adults to identify the best predictors of melanoma using a multivariate analysis and to explore eventual new dermoscopic criteria for nail melanoma diagnosis.

METHODS

In this retrospective observational study, 82 histopathologically diagnosed, acquired nail pigmented bands were collected and examined. All variables were included in the analysis and examined as possible predictors of nail melanoma. Both univariate and multivariable analyses have been performed.

RESULTS

Among 82 cases, 25 were diagnosed as nail melanoma and 57 as benign lesions (including 32 melanocytic nevi and 25 benign melanocytic hyperplasia). Melanoma cases were significantly associated with a width of the pigmented band higher than 2/3 of the nail plate, grey and black colours, irregularly pigmented lines, Hutchinson and micro-Hutchinson signs, and nail dystrophy. Granular pigmentation, a newly defined dermoscopic criterion, was found in 40% of melanomas and only in 3.51% of benign lesions.

CONCLUSIONS

Dermoscopic examination of longitudinal melanonychia provides useful information that could help clinicians to improve melanoma recognition.