Cover Image

Robustness of convolutional neural networks in recognition of pigmented skin lesions

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Maron, Roman C. (Author) , Haggenmüller, Sarah (Author) , Kalle, Christof von (Author) , Utikal, Jochen (Author) , Meier, Friedegund (Author) , Gellrich, Frank F. (Author) , Hauschild, Axel (Author) , French, Lars E. (Author) , Schlaak, Max (Author) , Ghoreschi, Kamran (Author) , Kutzner, Heinz (Author) , Heppt, Markus V. (Author) , Haferkamp, Sebastian (Author) , Sondermann, Wiebke (Author) , Schadendorf, Dirk (Author) , Schilling, Bastian (Author) , Hekler, Achim (Author) , Krieghoff-Henning, Eva (Author) , Kather, Jakob Nikolas (Author) , Fröhling, Stefan (Author) , Lipka, Daniel (Author) , Brinker, Titus Josef (Author)
Format: Article (Journal)
Language:English
Published: 7 January 2021
In: European journal of cancer
Year: 2021, Volume: 145, Pages: 81-91
ISSN:1879-0852
DOI:10.1016/j.ejca.2020.11.020
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/j.ejca.2020.11.020
Verlag, lizenzpflichtig, Volltext: https://www.sciencedirect.com/science/article/pii/S0959804920313575
Get full text
Author Notes:Roman C. Maron, Sarah Haggenmüller, Christof von Kalle, Jochen S. Utikal, Friedegund Meier, Frank F. Gellrich, Axel Hauschild, Lars E. French, Max Schlaak, Kamran Ghoreschi, Heinz Kutzner, Markus V. Heppt, Sebastian Haferkamp, Wiebke Sondermann, Dirk Schadendorf, Bastian Schilling, Achim Hekler, Eva Krieghoff-Henning, Jakob N. Kather, Stefan Fröhling, Daniel B. Lipka, Titus J. Brinker
Description
Summary: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 the convolutional neural network (CNN)-mediated skin lesion classification and to evaluate three possible solutions for this problem (additional data augmentation, test-time augmentation, anti-aliasing). - Methods - We trained three commonly used CNN architectures to differentiate between dermoscopic melanoma and nevus images. Subsequently, their performance and susceptibility to minor changes (‘brittleness’) was tested on two distinct test sets with multiple images per lesion. For the first set, image changes, such as rotations or zooms, were generated artificially. The second set contained natural changes that stemmed from multiple photographs taken of the same lesions. - Results - All architectures exhibited brittleness on the artificial and natural test set. The three reviewed methods were able to decrease brittleness to varying degrees while still maintaining performance. The observed improvement was greater for the artificial than for the natural test set, where enhancements were minor. - Conclusions - Minor image changes, relatively inconspicuous for humans, can have an effect on the robustness of CNNs differentiating skin lesions. By the methods tested here, this effect can be reduced, but not fully eliminated. Thus, further research to sustain the performance of AI classifiers is needed to facilitate the translation of such systems into the clinic.
Item Description:Gesehen am 21.04.2021
Physical Description:Online Resource
ISSN:1879-0852
DOI:10.1016/j.ejca.2020.11.020

Similar Items