Haggenmueller, Sarah and Maron, Roman C. and Hekler, Achim and Utikal, Jochen S. and Barata, Catarina and Barnhill, Raymond L. and Beltraminelli, Helmut and Berking, Carola and Betz-Stablein, Brigid and Blum, Andreas and Braun, Stephan A. and Carr, Richard and Combalia, Marc and Fernandez-Figueras, Maria-Teresa and Ferrara, Gerardo and Fraitag, Sylvie and French, Lars E. and Gellrich, Frank F. and Ghoreschi, Kamran and Goebeler, Matthias and Guitera, Pascale and Haenssle, Holger A. and Haferkamp, Sebastian and Heinzerling, Lucie and V. Heppt, Markus and Hilke, Franz J. and Hobelsberger, Sarah and Krahl, Dieter and Kutzner, Heinz and Lallas, Aimilios and Liopyris, Konstantinos and Llamas-Velasco, Mar and Malvehy, Josep and Meier, Friedegund and Mueller, Cornelia S. L. and Navarini, Alexander A. and Navarrete-Dechent, Cristian and Perasole, Antonio and Poch, Gabriela and Podlipnik, Sebastian and Requena, Luis and Rotemberg, Veronica M. and Saggini, Andrea and Sangueza, Omar P. and Santonja, Carlos and Schadendorf, Dirk and Schilling, Bastian and Schlaak, Max and Schlager, Justin G. and Sergon, Mildred and Sondermann, Wiebke and Soyer, H. Peter and Starz, Hans and Stolz, Wilhelm and Vale, Esmeralda and Weyers, Wolfgang and Zink, Alexander and Krieghoff-Henning, Eva and Kather, Jakob N. and von Kalle, Christof and Lipka, Daniel B. and Froehling, Stefan and Hauschild, Axel and Kittler, Harald and Brinker, Titus J. (2021) Original Research Skin cancer classification via convolutional neural networks: systematic review of studies involving human experts. EUROPEAN JOURNAL OF CANCER, 156. pp. 202-216. ISSN 0959-8049, 1879-0852
Full text not available from this repository. (Request a copy)Abstract
Background: Multiple studies have compared the performance of artificial intelligence (AI) -based models for automated skin cancer classification to human experts, thus setting the cornerstone for a successful translation of AI-based tools into clinicopathological practice. Objective: The objective of the study was to systematically analyse the current state of research on reader studies involving melanoma and to assess their potential clinical relevance by evaluating three main aspects: test set characteristics (holdout/out-of-distribution data set, composition), test setting (experimental/clinical, inclusion of metadata) and representativeness of participating clini-cians. Methods: PubMed, Medline and ScienceDirect were screened for peer-reviewed studies published between 2017 and 2021 and dealing with AI-based skin cancer classification involving melanoma. The search terms skin cancer classification, deep learning, convolutional neural network (CNN), melanoma (detection), digital biomarkers, histopathology and whole slide imaging were com-bined. Based on the search results, only studies that considered direct comparison of AI results with clinicians and had a diagnostic classification as their main objective were included. Results: A total of 19 reader studies fulfilled the inclusion criteria. Of these, 11 CNN-based ap-proaches addressed the classification of dermoscopic images; 6 concentrated on the classification of clinical images, whereas 2 dermatopathological studies utilised digitised histopathological whole slide images. Conclusions: All 19 included studies demonstrated superior or at least equivalent performance of CNN-based classifiers compared with clinicians. However, almost all studies were conducted in highly artificial settings based exclusively on single images of the suspicious lesions. Moreover, test sets mainly consisted of holdout images and did not represent the full range of patient populations and melanoma subtypes encountered in clinical practice. (c) 2021 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | IMAGE CLASSIFICATION; HISTOPATHOLOGIC DIAGNOSIS; LEVEL CLASSIFICATION; MELANOMA; DERMATOLOGISTS; LESIONS; METAANALYSIS; SUPERIOR; Skin cancer classification; Digital biomarkers; Convolutional neural network(s); Artificial intelligence; Machine learning; Deep learning; Dermatology; Malignant melanoma |
| Subjects: | 600 Technology > 610 Medical sciences Medicine |
| Divisions: | Medicine > Lehrstuhl für Dermatologie und Venerologie |
| Depositing User: | Petra Gürster |
| Date Deposited: | 18 Jan 2023 09:08 |
| Last Modified: | 29 Feb 2024 14:17 |
| URI: | https://pred.uni-regensburg.de/id/eprint/48220 |
Actions (login required)
 |
View Item |
