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

• Verfasst von: Kommoss, Katharina [VerfasserIn]
• Verfasst von: Winkler, Julia K. [VerfasserIn]
• Verfasst von: Müller-Christmann, Christine [VerfasserIn]
• Verfasst von: Niedermair, Felicitas [VerfasserIn]
• Verfasst von: Toberer, Ferdinand [VerfasserIn]
• Verfasst von: Stolz, Wilhelm [VerfasserIn]
• Verfasst von: Kraenke, Teresa [VerfasserIn]
• Verfasst von: Hofmann-Wellenhof, Rainer [VerfasserIn]
• Verfasst von: Blum, Andreas [VerfasserIn]
• Verfasst von: Enk, Alexander [VerfasserIn]
• Verfasst von: Rosenberger, Albert [VerfasserIn]
• Verfasst von: Hänßle, Holger [VerfasserIn]
• Titel: Observational study investigating the level of support from a convolutional neural network in face and scalp lesions deemed diagnostically ‘unclear’ by dermatologists
• Verf.angabe: Katharina S. Kommoss, Julia K. Winkler, Christine Mueller-Christmann, Felicitas Bardehle, Ferdinand Toberer, Wilhelm Stolz, Teresa Kraenke, Rainer Hofmann-Wellenhof, Andreas Blum, Alexander Enk, Albert Rosenberger, Holger A. Haenssle
• E-Jahr: 2023
• Jahr: May 2023
• Umfang: 8 S.
• Fussnoten: Gesehen am 26.05.2023
• Titel Quelle: Enthalten in: European journal of cancer
• Ort Quelle: Amsterdam [u.a.] : Elsevier, 1992
• Jahr Quelle: 2023
• Band/Heft Quelle: 185(2023) vom: Mai, Seite 53-60
• ISSN Quelle: 1879-0852
• DOI: doi:10.1016/j.ejca.2023.02.025
• Datenträger: Online-Ressource
• Sprache: eng
• Bibliogr. Hinweis: Ergänzung: Kommoss, Katharina: Response to letter
• Sach-SW: Actinic keratosis
• Sach-SW: Basal cell carcinoma
• Sach-SW: Deep learning
• Sach-SW: Dermoscopy
• Sach-SW: Lentigo maligna
• Sach-SW: Melanoma
• Sach-SW: Neural network
• Sach-SW: Seborrhoeic keratosis
• Sach-SW: Skin cancer
• Sach-SW: Solar lentigo
• K10plus-PPN: 1846277469

Abstract

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.