Deep Learning-Based Classification and Voxel-Based Visualization of Frontotemporal Dementia and Alzheimer's Disease

• Published in: Frontiers in neuroscience Vol. 14; p. 626154
• Main Authors: Hu, Jingjing, Qing, Zhao, Liu, Renyuan, Zhang, Xin, Lv, Pin, Wang, Maoxue, Wang, Yang, He, Kelei, Gao, Yang, Zhang, Bing
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 21.01.2021; Frontiers Media S.A
• Subjects: Algorithms; Alzheimer's disease; Classification; Clinical medicine; convolutional neural network; Decision making; Deep learning; Dementia; Dementia disorders; Design; Differential diagnosis; Frontotemporal dementia; Hypotheses; Magnetic resonance imaging; MRI; Neurodegenerative diseases; Neuroscience; Parahippocampal gyrus; Patients; Substantia alba; visulization; visulization; deep learning; frontotemporal dementia; Alzheimer’s disease; MRI; convolutional neural network
• ISSN: 1662-4548; 1662-453X; 1662-453X
• DOI: 10.3389/fnins.2020.626154

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.