Discrimination Between Invasive and In Situ Melanomas Using Clinical Close-Up Images and a De Novo Convolutional Neural Network.

Autor:	Polesie S; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.; Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden., Gillstedt M; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.; Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden., Ahlgren G; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden., Ceder H; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.; Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden., Dahlén Gyllencreutz J; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden., Fougelberg J; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.; Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden., Johansson Backman E; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.; Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden., Pakka J; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.; Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden., Zaar O; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.; Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden., Paoli J; Department of Dermatology and Venereology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.; Department of Dermatology and Venereology, Region Västra Götaland, Sahlgrenska University Hospital, Gothenburg, Sweden.
Jazyk:	angličtina
Zdroj:	Frontiers in medicine [Front Med (Lausanne)] 2021 Sep 14; Vol. 8, pp. 723914. Date of Electronic Publication: 2021 Sep 14 (Print Publication: 2021).
DOI:	10.3389/fmed.2021.723914
Abstrakt:	Background: Melanomas are often easy to recognize clinically but determining whether a melanoma is in situ (MIS) or invasive is often more challenging even with the aid of dermoscopy. Recently, convolutional neural networks (CNNs) have made significant and rapid advances within dermatology image analysis. The aims of this investigation were to create a de novo CNN for differentiating between MIS and invasive melanomas based on clinical close-up images and to compare its performance on a test set to seven dermatologists. Methods: A retrospective study including clinical images of MIS and invasive melanomas obtained from our department during a five-year time period (2016-2020) was conducted. Overall, 1,551 images [819 MIS (52.8%) and 732 invasive melanomas (47.2%)] were available. The images were randomized into three groups: training set ( n = 1,051), validation set ( n = 200), and test set ( n = 300). A de novo CNN model with seven convolutional layers and a single dense layer was developed. Results: The area under the curve was 0.72 for the CNN (95% CI 0.66-0.78) and 0.81 for dermatologists (95% CI 0.76-0.86) ( P < 0.001). The CNN correctly classified 208 out of 300 lesions (69.3%) whereas the corresponding number for dermatologists was 216 (72.0%). When comparing the CNN performance to each individual reader, three dermatologists significantly outperformed the CNN. Conclusions: For this classification problem, the CNN was outperformed by the dermatologist. However, since the algorithm was only trained and validated on 1,251 images, future refinement and development could make it useful for dermatologists in a real-world setting. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2021 Polesie, Gillstedt, Ahlgren, Ceder, Dahlén Gyllencreutz, Fougelberg, Johansson Backman, Pakka, Zaar and Paoli.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu