000277812 001__ 277812
000277812 005__ 20250423100225.0
000277812 020__ $$a978-3-658-47421-8 (print)
000277812 020__ $$a978-3-658-47422-5 (electronic)
000277812 0247_ $$2doi$$a10.1007/978-3-658-47422-5_18
000277812 037__ $$aDZNE-2025-00484
000277812 1001_ $$00000-0001-9468-2871$$aPalm, Christoph$$b0$$eEditor
000277812 1112_ $$aGerman Conference on Medical Image Computing$$cRegensburg$$d2025-03-09 - 2025-03-11$$wGermany
000277812 245__ $$aEvaluating the Fidelity of Explanations for Convolutional Neural Networks in Alzheimer’s Disease Detection
000277812 260__ $$aWiesbaden$$bSpringer Fachmedien Wiesbaden$$c2025
000277812 29510 $$aBildverarbeitung 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
000277812 300__ $$a76 - 81
000277812 3367_ $$2ORCID$$aCONFERENCE_PAPER
000277812 3367_ $$033$$2EndNote$$aConference Paper
000277812 3367_ $$2BibTeX$$aINPROCEEDINGS
000277812 3367_ $$2DRIVER$$aconferenceObject
000277812 3367_ $$2DataCite$$aOutput Types/Conference Paper
000277812 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1745321177_3108
000277812 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000277812 4900_ $$aInformatik aktuell
000277812 520__ $$aThe 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.
000277812 536__ $$0G:(DE-HGF)POF4-353$$a353 - Clinical and Health Care Research (POF4-353)$$cPOF4-353$$fPOF IV$$x0
000277812 588__ $$aDataset connected to CrossRef Book Series, Journals: pub.dzne.de
000277812 7001_ $$00000-0001-7600-5869$$aBreininger, Katharina$$b1$$eEditor
000277812 7001_ $$00000-0003-3492-4407$$aDeserno, Thomas$$b2$$eEditor
000277812 7001_ $$00000-0002-3499-4328$$aHandels, Heinz$$b3$$eEditor
000277812 7001_ $$00000-0002-9550-5284$$aMaier, Andreas$$b4$$eEditor
000277812 7001_ $$00000-0002-6626-2463$$aMaier-Hein, Klaus H.$$b5$$eEditor
000277812 7001_ $$00000-0002-8612-8157$$aTolxdorff, Thomas M.$$b6$$eEditor
000277812 7001_ $$0P:(DE-HGF)0$$aHiller, Bjarne C.$$b7$$eFirst author
000277812 7001_ $$0P:(DE-HGF)0$$aBader, Sebastian$$b8
000277812 7001_ $$0P:(DE-2719)9002353$$aSingh, Devesh$$b9$$udzne
000277812 7001_ $$0P:(DE-2719)9000364$$aKirste, Thomas$$b10
000277812 7001_ $$0P:(DE-HGF)0$$aBecker, Martin$$b11
000277812 7001_ $$0P:(DE-2719)2810283$$aDyrba, Martin$$b12$$eLast author$$udzne
000277812 773__ $$a10.1007/978-3-658-47422-5_18
000277812 909CO $$ooai:pub.dzne.de:277812$$pVDB
000277812 9101_ $$0I:(DE-588)1065079516$$6P:(DE-HGF)0$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b7$$kDZNE
000277812 9101_ $$0I:(DE-588)1065079516$$6P:(DE-HGF)0$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b8$$kDZNE
000277812 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9002353$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b9$$kDZNE
000277812 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9000364$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b10$$kDZNE
000277812 9101_ $$0I:(DE-588)1065079516$$6P:(DE-HGF)0$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b11$$kDZNE
000277812 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2810283$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b12$$kDZNE
000277812 9131_ $$0G:(DE-HGF)POF4-353$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vClinical and Health Care Research$$x0
000277812 9141_ $$y2025
000277812 9201_ $$0I:(DE-2719)1510100$$kAG Teipel$$lClinical Dementia Research (Rostock /Greifswald)$$x0
000277812 980__ $$acontrib
000277812 980__ $$aVDB
000277812 980__ $$acontb
000277812 980__ $$aI:(DE-2719)1510100
000277812 980__ $$aUNRESTRICTED