Year: 2019
Type: article
Abstract: discrimination.Visualization of learning process by guided Grad-CAM revealed that CIS became more focused by the CNN as the training progressed.DLB/AD score was significantly associated with three core-features of DLB.Conclusions: Deep learning-based imaging classification was useful not only for objective and accurate differentiation of DLB from AD but also for predicting clinical features of DLB.The CIS was identified as a specific feature during DLB classification.The visualization of specific features and learning process could have important implications for the potential of deep learning to discover new imaging features.
Source: Alzheimer s & Dementia
Authors: Liana G. Apostolova, Leonardo Iaccarino, Jessica A. Collins, Paul S. Aisen, Bret J. Borowski, Ani Eloyan, Anne M. Fagan, Tatiana M. Foroud, Constantine Gatsonis, Clifford R. Jack, Joel H. Kramer, Robert A. Koeppe, Andrew J. Saykin, Arthur W. Toga, Prashanthi Vemuri, Gregory S. Day, Neill R. Graff-Radford, Lawrence S. Honig, David T. Jones, Joseph C. Masdeu, Mario F. Mendez, Chiadi U. Onyike, Emily J. Rogalski, Stephen Salloway, David A. Wolk, Thomas S. Wingo, Gil D. Rabinovici, Brad C. Dickerson, Maria C. Carrillo
Institutions: Indiana University Indianapolis, Indiana University School of Medicine, University of California, San Francisco, Massachusetts General Hospital, Mayo Clinic, Brown University, Washington University in St. Louis, University of Michigan, University of Southern California, Mayo Clinic in Florida, Columbia University Irving Medical Center, Houston Methodist, University of California, Los Angeles, Johns Hopkins University, Northwestern University, Butler Hospital, University of Pennsylvania, Emory University, Harvard University, Alzheimer's Association
Language: English
Subfield: Psychiatry and Mental health
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Estimated APC paid: $3,150
OpenAlex ID: W2980628076