Abstract
Background: Deep learning convolutional neural networks (CNNs) show great potential for melanoma diagnosis. Melanoma thickness at diagnosis among others depends on melanoma localisation and subtype (e.g. advanced thickness in acrolentiginous or nodular melanomas). The question whether CNN may counterbalance physicians' diagnostic difficulties in these melanomas has not been addressed. We aimed to investigate the diagnostic performance of a CNN with approval for the European market across different melanoma localisations and subtypes.
Methods: The current market version of a CNN (Moleanalyzer-Pro®, FotoFinder Systems GmbH, Bad Birnbach, Germany) was used for classifications (malignant/benign) in six dermoscopic image sets. Each set included 30 melanomas and 100 benign lesions of related localisations and morphology (set-SSM: superficial spreading melanomas and macular nevi; set-LMM: lentigo maligna melanomas and facial solar lentigines/seborrhoeic keratoses/nevi; set-NM: nodular melanomas and papillomatous/dermal/blue nevi; set-Mucosa: mucosal melanomas and mucosal melanoses/macules/nevi; set-AMskin: acrolentiginous melanomas and acral (congenital) nevi; set-AMnail: subungual melanomas and subungual (congenital) nevi/lentigines/ethnical type pigmentations).
Results: The CNN showed a high-level performance in set-SSM, set-NM and set-LMM (sensitivities >93.3%, specificities >65%, receiver operating characteristics-area under the curve [ROC-AUC] >0.926). In set-AMskin, the sensitivity was lower (83.3%) at a high specificity (91.0%) and ROC-AUC (0.928). A limited performance was found in set-mucosa (sensitivity 93.3%, specificity 38.0%, ROC-AUC 0.754) and set-AMnail (sensitivity 53.3%, specificity 68.0%, ROC-AUC 0.621).
Conclusions: The CNN may help to partly counterbalance reduced human accuracies. However, physicians need to be aware of the CNN's limited diagnostic performance in mucosal and subungual lesions. Improvements may be expected from additional training images of mucosal and subungual sites.
Keywords: Convolutional neural network; Deep learning; Dermoscopy; Melanoma; Nevi.
Copyright © 2019 Elsevier Ltd. All rights reserved.
Conflict of interest statement
Conflict of interest statement FotoFinder Systems GmbH had no role in the study design or interpretation of the data. T Fuchs is an employed software developer at the research and development department of FotoFinder Systems GmbH and was responsible for technical support and for writing parts of the supplement method section covering details on the CNN architecture and training. HA Haenssle received honoraria and/or travel expenses from companies involved in the development of devices for skin cancer screening: Scibase AB, FotoFinder Systems GmbH, Heine Optotechnik GmbH, Magnosco GmbH. A Blum received honoraria and/or travel expenses from companies involved in the development of devices for skin cancer screening: Scibase AB, FotoFinder Systems GmbH, Heine Optotechnik GmbH. All other authors indicated no conflict of interest.
