Navigation überspringen
Universitätsbibliothek Heidelberg
Status: Bibliographieeintrag

Verfügbarkeit
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Maron, Roman C. [VerfasserIn]   i
 Hekler, Achim [VerfasserIn]   i
 Haggenmüller, Sarah [VerfasserIn]   i
 Kalle, Christof von [VerfasserIn]   i
 Utikal, Jochen [VerfasserIn]   i
 Müller, Verena [VerfasserIn]   i
 Gaiser, Maria [VerfasserIn]   i
 Meier, Friedegund [VerfasserIn]   i
 Hobelsberger, Sarah [VerfasserIn]   i
 Gellrich, Frank F. [VerfasserIn]   i
 Sergon, Mildred [VerfasserIn]   i
 Hauschild, Axel [VerfasserIn]   i
 French, Lars E. [VerfasserIn]   i
 Heinzerling, Lucie [VerfasserIn]   i
 Schlager, Justin Gabriel [VerfasserIn]   i
 Ghoreschi, Kamran [VerfasserIn]   i
 Schlaak, Max [VerfasserIn]   i
 Hilke, Franz [VerfasserIn]   i
 Poch, Gabriela [VerfasserIn]   i
 Korsing, Sören [VerfasserIn]   i
 Berking, Carola [VerfasserIn]   i
 Heppt, Markus V. [VerfasserIn]   i
 Erdmann, Michael [VerfasserIn]   i
 Haferkamp, Sebastian [VerfasserIn]   i
 Schadendorf, Dirk [VerfasserIn]   i
 Sondermann, Wiebke [VerfasserIn]   i
 Goebeler, Matthias [VerfasserIn]   i
 Schilling, Bastian [VerfasserIn]   i
 Kather, Jakob Nikolas [VerfasserIn]   i
 Fröhling, Stefan [VerfasserIn]   i
 Lipka, Daniel [VerfasserIn]   i
 Krieghoff-Henning, Eva [VerfasserIn]   i
 Brinker, Titus Josef [VerfasserIn]   i
Titel:Model soups improve performance of dermoscopic skin cancer classifiers
Verf.angabe:Roman C. Maron, Achim Hekler, Sarah Haggenmüller, Christof von Kalle, Jochen S. Utikal, Verena Müller, Maria Gaiser, Friedegund Meier, Sarah Hobelsberger, Frank F. Gellrich, Mildred Sergon, Axel Hauschild, Lars E. French, Lucie Heinzerling, Justin G. Schlager, Kamran Ghoreschi, Max Schlaak, Franz J. Hilke, Gabriela Poch, Sören Korsing, Carola Berking, Markus V. Heppt, Michael Erdmann, Sebastian Haferkamp, Dirk Schadendorf, Wiebke Sondermann, Matthias Goebeler, Bastian Schilling, Jakob N. Kather, Stefan Fröhling, Daniel B. Lipka, Eva Krieghoff-Henning, Titus J. Brinker
E-Jahr:2022
Jahr:September 2022
Umfang:10 S.
Fussnoten:Gesehen am 17.05.2023
Titel Quelle:Enthalten in: European journal of cancer
Ort Quelle:Amsterdam [u.a.] : Elsevier, 1992
Jahr Quelle:2022
Band/Heft Quelle:173(2022), Seite 307-316
ISSN Quelle:1879-0852
Abstract:Background - Image-based cancer classifiers suffer from a variety of problems which negatively affect their performance. For example, variation in image brightness or different cameras can already suffice to diminish performance. Ensemble solutions, where multiple model predictions are combined into one, can improve these problems. However, ensembles are computationally intensive and less transparent to practitioners than single model solutions. Constructing model soups, by averaging the weights of multiple models into a single model, could circumvent these limitations while still improving performance. - Objective - To investigate the performance of model soups for a dermoscopic melanoma-nevus skin cancer classification task with respect to (1) generalisation to images from other clinics, (2) robustness against small image changes and (3) calibration such that the confidences correspond closely to the actual predictive uncertainties. - Methods - We construct model soups by fine-tuning pre-trained models on seven different image resolutions and subsequently averaging their weights. Performance is evaluated on a multi-source dataset including holdout and external components. - Results - We find that model soups improve generalisation and calibration on the external component while maintaining performance on the holdout component. For robustness, we observe performance improvements for pertubated test images, while the performance on corrupted test images remains on par. - Conclusions - Overall, souping for skin cancer classifiers has a positive effect on generalisation, robustness and calibration. It is easy for practitioners to implement and by combining multiple models into a single model, complexity is reduced. This could be an important factor in achieving clinical applicability, as less complexity generally means more transparency.
DOI:doi:10.1016/j.ejca.2022.07.002
URL:Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.

Volltext: https://doi.org/10.1016/j.ejca.2022.07.002
 Volltext: https://www.sciencedirect.com/science/article/pii/S0959804922004129
 DOI: https://doi.org/10.1016/j.ejca.2022.07.002
Datenträger:Online-Ressource
Sprache:eng
Sach-SW:Artificial intelligence
 Calibration
 Deep learning
 Dermatology
 Ensembles
 Generalisation
 Melanoma
 Model soups
 Nevus
 Robustness
K10plus-PPN:1845598644
Verknüpfungen:→ Zeitschrift

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/69076856   QR-Code
zum Seitenanfang