Melanoma recognition by a deep learning convolutional neural network

• Verfasst von: Winkler, Julia K. [VerfasserIn]
• Verfasst von: Kommoss, Katharina [VerfasserIn]
• Verfasst von: Müller-Christmann, Christine [VerfasserIn]
• Verfasst von: Toberer, Ferdinand [VerfasserIn]
• Verfasst von: Enk, Alexander [VerfasserIn]
• Verfasst von: Deinlein, Teresa [VerfasserIn]
• Verfasst von: Hofmann-Wellenhof, Rainer [VerfasserIn]
• Verfasst von: Thomas, Luc [VerfasserIn]
• Verfasst von: Lallas, Aimilios [VerfasserIn]
• Verfasst von: Blum, Andreas [VerfasserIn]
• Verfasst von: Stolz, Wilhelm [VerfasserIn]
• Verfasst von: Abassi, Mohamed S. [VerfasserIn]
• Verfasst von: Fuchs, Tobias [VerfasserIn]
• Verfasst von: Rosenberger, Albert [VerfasserIn]
• Verfasst von: Hänßle, Holger [VerfasserIn]
• Titel: Melanoma recognition by a deep learning convolutional neural network
• Titelzusatz: performance in different melanoma subtypes and localisations
• Verf.angabe: Julia K. Winkler, Katharina Sies, Christine Fink, Ferdinand Toberer, Alexander Enk, Teresa Deinlein, Rainer Hofmann-Wellenhof, Luc Thomas, Aimilios Lallas, Andreas Blum, Wilhelm Stolz, Mohamed S. Abassi, Tobias Fuchs, Albert Rosenberger, Holger A. Haenssle
• E-Jahr: 2020
• Jahr: 20 January 2020
• Umfang: 9 S.
• Fussnoten: Gesehen am 27.10.2020
• Titel Quelle: Enthalten in: European journal of cancer
• Ort Quelle: Amsterdam [u.a.] : Elsevier, 1992
• Jahr Quelle: 2020
• Band/Heft Quelle: 127(2020), Seite 21-29
• ISSN Quelle: 1879-0852
• DOI: doi:10.1016/j.ejca.2019.11.020
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Convolutional neural network
• Sach-SW: Deep learning
• Sach-SW: Dermoscopy
• Sach-SW: Melanoma
• Sach-SW: Nevi
• K10plus-PPN: 1736690108

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.