Using multiple real-world dermoscopic photographs of one lesion improves melanoma classification via deep learning - 11/04/24

Doi : 10.1016/j.jaad.2023.11.065

Achim Hekler, MSc ^a, Roman C. Maron, MSc ^a, Sarah Haggenmüller, MSc ^a, Max Schmitt, MSc ^a, Christoph Wies, MSc ^a,^b, Jochen S. Utikal, MD ^c,^d,^e, Friedegund Meier, MD ^f, Sarah Hobelsberger, MD ^f, Frank F. Gellrich, MD ^f, Mildred Sergon, MD ^f, Axel Hauschild, MD ^g, Lars E. French, MD ^h,ⁱ, Lucie Heinzerling, MD ^h,^j, Justin G. Schlager, MD ^h, Kamran Ghoreschi, MD ^k, Max Schlaak, MD ^k, Franz J. Hilke, PhD ^k, Gabriela Poch, MD ^k, Sören Korsing, MD ^k, Carola Berking, MD ^j, Markus V. Heppt, MD ^j, Michael Erdmann, MD ^j, Sebastian Haferkamp, MD ^l, Konstantin Drexler, MD ^l, Dirk Schadendorf, MD ^m, Wiebke Sondermann, MD ^m, Matthias Goebeler, MD ⁿ, Bastian Schilling, MD ⁿ, Jakob N. Kather, MD ^o, Eva Krieghoff-Henning, PhD ^a, Titus J. Brinker, MD ^a,^⁎
^a Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Heidelberg, Germany
^b Medical Faculty, University Heidelberg, Heidelberg, Germany
^c Department of Dermatology, Venereology and Allergology, University Medical Center Mannheim, Ruprecht-Karl University of Heidelberg, Mannheim, Germany
^d Skin Cancer Unit, German Cancer Research Center (DKFZ), Heidelberg, Germany
^e DKFZ Hector Cancer Institute at the University Medical Center Mannheim, Mannheim, Germany
^f Department of Dermatology, Skin Cancer Center at the University Cancer Center and National Center for Tumor Diseases Dresden, University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
^g Department of Dermatology, University Hospital (UKSH), Kiel, Germany
^h Department of Dermatology and Allergy, University Hospital, LMU Munich, Munich, Germany
ⁱ Dr. Phillip Frost Department of Dermatology and Cutaneous Surgery, University of Miami, Miller School of Medicine, Miami, Florida
^j Department of Dermatology, University Hospital Erlangen, Comprehensive Cancer Center Erlangen – European Metropolitan Region Nürnberg, CCC Alliance WERA, Erlangen, Germany
^k Department of Dermatology, Venereology and Allergology, Charité – Universitätsmedizin Berlin, Corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
^l Department of Dermatology, University Hospital Regensburg, Regensburg, Germany
^m Department of Dermatology, Venereology and Allergology, University Hospital Essen, Essen, Germany
ⁿ Department of Dermatology, Venereology and Allergology, University Hospital Würzburg and National Center for Tumor Diseases (NCT) WERA Würzburg, Würzburg, Germany
^o Else Kroener Fresenius Center for Digital Health, Technical University Dresden, Dresden, Germany

^∗Correspondence to: Titus J. Brinker, MD, Digital Biomarkers for Oncology Group, German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, Heidelberg, 69120, GermanyDigital Biomarkers for Oncology GroupGerman Cancer Research Center (DKFZ)Im Neuenheimer Feld 280Heidelberg69120Germany

Key words : artificial intelligence, deep learning, dermatology, dermoscopy, diagnosis, diagnostic accuracy, melanoma, robustness, uncertainty estimation

	Drs Hekler and Maron, contributed equally to this work.
	Funding sources: This study was funded by the Federal Ministry of Health, Berlin, Germany (grant: Skin Classification Project 2; grant holder: Titus J. Brinker, German Cancer Research Center, Heidelberg, Germany). The sponsor had no role in the design and conduct of the study; collection, management, analysis and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication.
	Patient consent: All patients provided written informed consent for their participation in the study.
	IRB approval status: This study was approved by the respective Institutional Review Boards of the participating hospitals/centers (Berlin, Dresden, Erlangen, Essen, Mannheim, Munich, Regensburg, Wuerzburg) and adhered to the established guidelines outlined in the Declaration of Helsinki.

Esportazione

Vol 90 - N° 5

P. 1028-1031 - maggio 2024 Ritorno al numero

Articolo precedente

Analysis of general payments from industry to dermatology nonphysician clinicians in the United States, 2021-2022
Nicole J. Hardy, Christian Gronbeck, Hao Feng

| Articolo seguente

Clinical outcomes and management of JAK inhibitor-associated acne in patients with moderate-to-severe atopic dermatitis undergoing upadacitinib: A multicenter retrospective study
Gianluca Avallone, Luca Mastorino, Gianluca Tavoletti, Nicole Macagno, Francesca Barei, Donatella Schena, Mariateresa Rossi, Elisabetta Magnaterra, Flaminia Antonelli, Graziella Babino, Riccardo Viola, Luigi Gargiulo, Claudio Conforti, Luca Rapparini, Enzo Errichetti, Cataldo Patruno, Pasqualina Ruggiero, Gabriele Roccuzzo, Carlo A. Maronese, Giampiero Girolomoni, Massimo Gola, Andrea Chiricozzi, Anna Balato, Francesca Ambrogio, Alessandra Narcisi, Iris Zalaudek, Carlotta Gurioli, Maddalena Napolitano, Angelo V. Marzano, Caterina Foti, Antonio Costanzo, Bianca M. Piraccini, Silvia M. Ferrucci, Michela Ortoncelli, Pietro Quaglino, Simone Ribero

Benvenuto su EM|consulte, il riferimento dei professionisti della salute.
L'accesso al testo integrale di questo articolo richiede un abbonamento.

Già abbonato a @@106933@@ rivista ?

connettersi o creare un account

Using multiple real-world dermoscopic photographs of one lesion improves melanoma classification via deep learning - 11/04/24

Citazioni Export

File

Contenuto

Il mio account

Aide & support

Dichiarazione CNIL