With the development of deep learning in diagnosing autism spectrum disorder (ASD), multi-site resting-state functional magnetic resonance imaging (rs-fMRI) images have made excellent progress. However, there is a heterogeneous problem between the multi-site data caused by inconsistent data distribution. Existing domain adaptation methods cannot deal with the issue that the target domain data is unavailable during the training stage. To address this problem, we propose a deep domain generalization method via low-rank category constraint (DDGLCC) for multi-site ASD identification. The main idea is capturing the category discriminative information through the domain-specific networks and gaining the consistently shared information through the domain-invariant network. A novel category-based low-rank constraint strategy is used to align two types of networks. In the test stage, the well-trained domain-invariant network is applied to the unseen target domain data. Whether the results on different deep structure experiments or different lowrank constraints experiments, the proposed DDGLCC method achieves the best performance.
KEYWORDS: Matrices, Feature extraction, Education and training, Neurological disorders, Data processing, Data modeling, Ablation, Deep learning, Surgery, Photonic integrated circuits
With the development of deep learning in diagnosing autism spectrum disorder (ASD), multi-site resting-state functional magnetic resonance imaging (rs-fMRI) images have made excellent progress. However, there is a heterogeneous problem between the multi-site data caused by inconsistent data distribution. To address this problem, we propose a combining autoencoder and category-based low-rank domain adaptation (AECLR) method for multi-site ASD identification. The main idea is to extract non-linear features and alignment the distribution of these features. In the first stage, the unsupervised autoencoder is used to obtain the non-linear representation. In the second stage, the common structure between all domains was mined by the category-based low-rank constraints, which transform all source domain data and the target domain data into the common latent space and then the source domain data could be linearly represented by the target domain data. As a result, the ablation experiments of the AECLR method achieve independent performance and the AECLR method also obtain a satisfactory classification when compared with the state-of-the-art method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.