Authors: Dyrba, Martin, Hanzig, Moritz, Altenstein, Slawek, Bader, Sebastian, Ballarini, Tommaso, Brosseron, Frederic, Buerger, Katharina, Cantré, Daniel, Dechent, Peter, Dobisch, Laura, Düzel, Emrah, Ewers, Michael, Fliessbach, Klaus, Glanz, Wenzel, Haynes, John-Dylan, Heneka, Michael T., Janowitz, Keles, Deniz B., Kilimann, Ingo, Laske, Christoph, Maier, Franziska, Metzger, Coraline D., Munk, Matthias H., Perneczky, Robert, Peters, Oliver, Preis, Lukas, Priller, Josef, Rauchmann, Boris, Roy, Nina, Scheffler, Schneider, Anja, Schott, Björn H., Spottke, Annika, Spruth, Eike J., Weber, Marc-André, Ertl-Wagner, Birgit, Wagner, Wiltfang, Jens, Jessen, Frank, Teipel, Stefan J., for the ADNI, AIBL, DELCODE study groups, Martin; German Center for Neurodegenerative Diseases (DZNE), Rostock, Germany, Moritz; Institute of Visual and Analytic Computing, University of Rostock, Slawek; Department of Psychiatry and Psychotherapy, Charité – Universitätsmedizin Berlin, Berlin, Sebastian; Institute of Visual and Analytic Computing, Tommaso; German Center for Neurodegenerative Diseases (DZNE), Bonn, Frederic; Department for Neurodegenerative Diseases and Geriatric Psychiatry, University Hospital Bonn, Katharina; Institute for Stroke and Dementia Research (ISD), University Hospital, Ludwig Maximilian University, Munich, Daniel; Institute of Diagnostic and Interventional Radiology, Pediatric Radiology and Neuroradiology, Rostock University Medical Center, Peter; MR-Research in Neurosciences, Department of Cognitive Neurology, Georg-August-University, Goettingen, Laura; German Center for Neurodegenerative Diseases (DZNE), Magdeburg, Emrah; Institute of Cognitive Neurology and Dementia Research (IKND), Otto-von-Guericke University, Michael; Institute for Stroke and Dementia Research (ISD), Klaus; Department for Neurodegenerative Diseases and Geriatric Psychiatry, Wenzel; German Center for Neurodegenerative Diseases (DZNE), John-Dylan; Bernstein Center for Computational Neuroscience, Michael T.; Department for Neurodegenerative Diseases and Geriatric Psychiatry, Daniel; Institute for Stroke and Dementia Research (ISD), Deniz B.; Department of Psychiatry and Psychotherapy, Ingo; Department of Psychosomatic Medicine, Christoph; Department of Psychiatry and Psychotherapy, University of Tuebingen, Tuebingen, Franziska; Department of Psychiatry, Medical Faculty, University of Cologne, Cologne, Coraline D.; Department of Psychiatry and Psychotherapy, Matthias H.; Systems Neurophysiology, Department of Biology, Darmstadt University of Technology, Darmstadt, Robert; Ageing Epidemiology Research Unit (AGE), School of Public Health, Imperial College London, London, UK, Oliver; Department of Psychiatry and Psychotherapy, Lukas; Department of Psychiatry and Psychotherapy, Josef; Department of Psychiatry and Psychotherapy, Klinikum rechts der Isar, Technical University Munich, Boris; Department of Psychiatry and Psychotherapy, Nina; German Center for Neurodegenerative Diseases (DZNE), Klaus; Department for Biomedical Magnetic Resonance, Anja; Department for Neurodegenerative Diseases and Geriatric Psychiatry, Björn H.; Leibniz Institute for Neurobiology, Annika; Department of Neurology, Eike J.; Department of Psychiatry and Psychotherapy, Marc-André; Institute of Diagnostic and Interventional Radiology, Birgit; Department of Medical Imaging, University of Toronto, Toronto, Canada, Michael; Department for Neurodegenerative Diseases and Geriatric Psychiatry, Jens; Neurosciences and Signaling Group, Institute of Biomedicine (iBiMED), Department of Medical Sciences, University of Aveiro, Aveiro, Portugal, Frank; Excellence Cluster on Cellular Stress Responses in Aging-Associated Diseases (CECAD), Stefan J.; Department of Psychosomatic Medicine, ; Department of Psychosomatic Medicine
Venue: Alzheimer's Research & Therapy
Type: Publication
Abstract: Abstract Background Although convolutional neural networks (CNNs) achieve high diagnostic accuracy for detecting Alzheimer’s disease (AD) dementia based on magnetic resonance imaging (MRI) scans, they are not yet applied in clinical routine. One important reason for this is a lack of model comprehensibility. Recently developed visualization methods for deriving CNN relevance maps may help to fill this gap as they allow the visualization of key input image features that drive the decision of the model. We investigated whether models with highe...
(read more)
Topics: 
Artificial intelligence
Machine learning
Loading (it may take a couple of seconds)...
Loading (it may take a couple of seconds)...