Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: Evaluation in Alzheimer's disease

Autor: 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, Daniel, 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, Klaus, Schneider, Anja, Schott, Björn H., Spottke, Annika, Spruth, Eike J., Weber, Marc-André, Ertl-Wagner, Birgit, Wagner, Michael, Wiltfang, Jens, Jessen, Frank, Teipel, Stefan J.

Background: Although convolutional neural networks (CNN) 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 rea

Externí odkaz: http://arxiv.org/abs/2012.10294

Additional file 5 of Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease

Autor: 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, Daniel, 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, Klaus, Schneider, Anja, Schott, Björn H., Spottke, Annika, Spruth, Eike J., Weber, Marc-André, Ertl-Wagner, Birgit, Wagner, Michael, Wiltfang, Jens, Jessen, Frank, Teipel, Stefan J.

Additional file 5: Supplementary Figure 3. Comparison of mean relevance maps between samples.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::61201ce25eca6c19c24f18fadcd9b8bf

Additional file 6 of Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease

Autor: 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, Daniel, 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, Klaus, Schneider, Anja, Schott, Björn H., Spottke, Annika, Spruth, Eike J., Weber, Marc-André, Ertl-Wagner, Birgit, Wagner, Michael, Wiltfang, Jens, Jessen, Frank, Teipel, Stefan J.

Additional file 6: Supplementary Figure 4. Correlation matrix of hippocampus volume (residualized) and several brain regions’ relevance scores for DELCODE participants and the model trained on the whole ADNI-GO/2 dataset.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5e713be7da5f749b989a513ca2487892

Interactive Visualization of 3D CNN Relevance Maps to Aid Model Comprehensibility

Autor: Dyrba, Martin, Hanzig, Moritz

Publikováno v: Wiesbaden : Springer Fachmedien Wiesbaden, Informatik aktuell 317-322 (2021). doi:10.1007/978-3-658-33198-6_77
Bildverarbeitung für die Medizin 2021 / Palm, Christoph (Editor) ; Wiesbaden : Springer Fachmedien Wiesbaden, 2021, Chapter 77 ; ISSN: 1431-472X ; ISBN: 978-3-658-33197-9=978-3-658-33198-6 ; doi:10.1007/978-3-658-33198-6
Bildverarbeitung für die Medizin 2021 / Palm, Christoph (Editor) ; Wiesbaden : Springer Fachmedien Wiesbaden, 2021, Chapter 77 ; ISSN: 1431-472X ; ISBN: 978-3-658-33197-9=978-3-658-33198-6 ; doi:10.1007/978-3-658-33198-6German Workshop on Medical Image Computing, Regensburg, Germany, 2021-03-07

Relevance maps derived from convolutional neural networks (CNN) indicate the influence of a particular image region on the decision of the CNN model. Individual maps are obtained for each single input 3D MRI image and various visualization options ne

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_____10678::ddc0acf6c4f061e83caac92ed72eaf88
https://pub.dzne.de/record/155737

Additional file 4 of Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease

Autor: 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, Daniel, 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, Klaus, Schneider, Anja, Schott, Björn H., Spottke, Annika, Spruth, Eike J., Weber, Marc-André, Ertl-Wagner, Birgit, Wagner, Michael, Wiltfang, Jens, Jessen, Frank, Teipel, Stefan J.

Additional file 4: Supplementary Figure 2. Sequence diagram of function calls when selecting a new person.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e7f97bbf6bf0eaf7e4769e5e4c2bad1