% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Palm:277812,
      author       = {Hiller, Bjarne C. and Bader, Sebastian and Singh, Devesh
                      and Kirste, Thomas and Becker, Martin and Dyrba, Martin},
      editor       = {Palm, Christoph and Breininger, Katharina and Deserno,
                      Thomas and Handels, Heinz and Maier, Andreas and Maier-Hein,
                      Klaus H. and Tolxdorff, Thomas M.},
      title        = {{E}valuating the {F}idelity of {E}xplanations for
                      {C}onvolutional {N}eural {N}etworks in {A}lzheimer’s
                      {D}isease {D}etection},
      address      = {Wiesbaden},
      publisher    = {Springer Fachmedien Wiesbaden},
      reportid     = {DZNE-2025-00484},
      isbn         = {978-3-658-47421-8 (print)},
      series       = {Informatik aktuell},
      pages        = {76 - 81},
      year         = {2025},
      comment      = {Bildverarbeitung für die Medizin 2025 / Palm, Christoph
                      (Editor) [https://orcid.org/0000-0001-9468-2871] ; Wiesbaden
                      : Springer Fachmedien Wiesbaden, 2025, Chapter 18 ; ISSN:
                      1431-472X=2628-8958 ; ISBN:
                      978-3-658-47421-8=978-3-658-47422-5 ;
                      doi:10.1007/978-3-658-47422-5},
      booktitle     = {Bildverarbeitung für die Medizin 2025
                       / Palm, Christoph (Editor)
                       [https://orcid.org/0000-0001-9468-2871]
                       ; Wiesbaden : Springer Fachmedien
                       Wiesbaden, 2025, Chapter 18 ; ISSN:
                       1431-472X=2628-8958 ; ISBN:
                       978-3-658-47421-8=978-3-658-47422-5 ;
                       doi:10.1007/978-3-658-47422-5},
      abstract     = {The black-box nature of deep learning still prevents its
                      widespread clinical use due to the high risk of hidden
                      biases and prediction errors. Over the last decade, various
                      explanation methods have been proposed to reveal the latent
                      mechanisms of neural networks and support their decisions.
                      However, interpreting the explanations themselves can be
                      challenging, and there is still little consensus on how to
                      evaluate the quality of explanations. To investigate the
                      fidelity of explanations provided by prominent feature
                      attribution methods for Convolutional Neural Networks in
                      Alzheimer’s Disease (AD) detection, this paper applies
                      relevance-guided perturbation to the Magnetic Resonance
                      Imaging (MRI) input images. According to the fidelity
                      metric, the AD class probability showed the steepest decline
                      when the perturbation was guided by Integrated Gradients or
                      DeepLift. We conclude by highlighting the role of the
                      reference image in feature attribution with regard to AD
                      detection from MRI images. The source code for the
                      experiments is publicly available on GitHub at
                      https://github.com/bckrlab/ad-fidelity.},
      month         = {Mar},
      date          = {2025-03-09},
      organization  = {German Conference on Medical Image
                       Computing, Regensburg (Germany), 9 Mar
                       2025 - 11 Mar 2025},
      cin          = {AG Teipel},
      cid          = {I:(DE-2719)1510100},
      pnm          = {353 - Clinical and Health Care Research (POF4-353)},
      pid          = {G:(DE-HGF)POF4-353},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.1007/978-3-658-47422-5_18},
      url          = {https://pub.dzne.de/record/277812},
}