Deep Learning-Based Classification and Voxel-Based Visualization of Frontotemporal Dementia and Alzheimer's Disease
Frontotemporal dementia (FTD) and Alzheimer's disease (AD) have overlapping symptoms, and accurate differential diagnosis is important for targeted intervention and treatment. Previous studies suggest that the deep learning (DL) techniques have the potential to solve the differential diagnosis...
Saved in:
Published in | Frontiers in neuroscience Vol. 14; p. 626154 |
---|---|
Main Authors | , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Switzerland
Frontiers Research Foundation
21.01.2021
Frontiers Media S.A |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Frontotemporal dementia (FTD) and Alzheimer's disease (AD) have overlapping symptoms, and accurate differential diagnosis is important for targeted intervention and treatment. Previous studies suggest that the deep learning (DL) techniques have the potential to solve the differential diagnosis problem of FTD, AD and normal controls (NCs), but its performance is still unclear. In addition, existing DL-assisted diagnostic studies still rely on hypothesis-based expert-level preprocessing. On the one hand, it imposes high requirements on clinicians and data themselves; On the other hand, it hinders the backtracking of classification results to the original image data, resulting in the classification results cannot be interpreted intuitively. In the current study, a large cohort of 3D T1-weighted structural magnetic resonance imaging (MRI) volumes (
= 4,099) was collected from two publicly available databases, i.e., the ADNI and the NIFD. We trained a DL-based network directly based on raw T1 images to classify FTD, AD and corresponding NCs. And we evaluated the convergence speed, differential diagnosis ability, robustness and generalizability under nine scenarios. The proposed network yielded an accuracy of 91.83% based on the most common T1-weighted sequence [magnetization-prepared rapid acquisition with gradient echo (MPRAGE)]. The knowledge learned by the DL network through multiple classification tasks can also be used to solve subproblems, and the knowledge is generalizable and not limited to a specified dataset. Furthermore, we applied a gradient visualization algorithm based on guided backpropagation to calculate the contribution graph, which tells us intuitively why the DL-based networks make each decision. The regions making valuable contributions to FTD were more widespread in the right frontal white matter regions, while the left temporal, bilateral inferior frontal and parahippocampal regions were contributors to the classification of AD. Our results demonstrated that DL-based networks have the ability to solve the enigma of differential diagnosis of diseases without any hypothesis-based preprocessing. Moreover, they may mine the potential patterns that may be different from human clinicians, which may provide new insight into the understanding of FTD and AD. |
---|---|
Bibliography: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 Bruce L. Miller; University of California, San Francisco This article was submitted to Brain Imaging Methods, a section of the journal Frontiers in Neuroscience Edited by: Ahmed Soliman, University of Louisville, United States Data used in preparation of this article were partly obtained from the Frontotemporal Lobar Degeneration Neuroimaging Initiative (FTLDNI) database, whose nickname is NIFD. The investigators at NIFD/FTLDNI contributed to the design and implementation of FTLDNI and/or provided data, but did not participate in analysis or writing of this report. The FTLDNI investigators included the following individuals Adam L. Boxer; University of California, San Francisco Maria Luisa Mandelli; University of California, San Francisco Reviewed by: Islam Abdelmaksoud, Mansoura University, Egypt; Adil Bashir, Auburn University, United States Bradford C. Dickerson; Harvard Medical School and Massachusetts General Hospital Kimoko Domoto-Reilly; University of Washington School of Medicine David Knopman; Mayo Clinic, Rochester William W. Seeley; University of California, San Francisco Data used in preparation of this article were partly obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf. Howard Rosen; University of California, San Francisco (PI) Maria-Luisa Gorno-Tempini; University of California, San Francisco These authors have contributed equally to this work John Kornak; University of California, San Francisco Bradley F. Boeve; Mayo Clinic Rochester Scott McGinnis; University of California, San Francisco |
ISSN: | 1662-4548 1662-453X 1662-453X |
DOI: | 10.3389/fnins.2020.626154 |