Startseite UR

Robustness of convolutional neural networks in recognition of pigmented skin lesions

Maron, Roman C. ; Haggenmüller, Sarah ; von Kalle, Christof ; Utikal, Jochen S. ; Meier, Friedegund ; Gellrich, Frank F. ; Hauschild, Axel ; French, Lars E. ; Schlaak, Max ; Ghoreschi, Kamran ; Kutzner, Heinz ; Heppt, Markus V. ; Haferkamp, Sebastian ; Sondermann, Wiebke ; Schadendorf, Dirk ; Schilling, Bastian ; Hekler, Achim ; Krieghoff-Henning, Eva ; Kather, Jakob N. ; Fröhling, Stefan ; Lipka, Daniel B. ; Brinker, Titus J.



Zusammenfassung

Background: A basic requirement for artificial intelligence (AI)-based image analysis systems, which are to be integrated into clinical practice, is a high robustness. Minor changes in how those images are acquired, for example, during routine skin cancer screening, should not change the diagnosis of such assistance systems. Objective: To quantify to what extent minor image perturbations affect ...

plus


Nur für Besitzer und Autoren: Kontrollseite des Eintrags
  1. Universität

Universitätsbibliothek

Publikationsserver

Kontakt:

Publizieren: oa@ur.de
0941 943 -4239 oder -69394

Dissertationen: dissertationen@ur.de
0941 943 -3904

Forschungsdaten: datahub@ur.de
0941 943 -5707

Ansprechpartner