TY - JOUR
T1 - A unified framework for personalized regions selection and functional relation modeling for early MCI identification
AU - The Alzheimer’S Disease Neuroimaging Initiative
AU - Lee, Jiyeon
AU - Ko, Wonjun
AU - Kang, Eunsong
AU - Suk, Heung Il
N1 - Funding Information:
This work was supported by National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2019R1A2C1006543 ) and partially by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2019-0-00079, Artificial Intelligence Graduate School Program (Korea University)).
Publisher Copyright:
© 2021 The Author(s)
PY - 2021/8/1
Y1 - 2021/8/1
N2 - Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely adopted to investigate functional abnormalities in brain diseases. Rs-fMRI data is unsupervised in nature because the psychological and neurological labels are coarse-grained, and no accurate region-wise label is provided along with the complex co-activities of multiple regions. To the best of our knowledge, most studies regarding univariate group analysis or multivariate pattern recognition for brain disease identification have focused on discovering functional characteristics shared across subjects; however, they have paid less attention to individual properties of neural activities that result from different symptoms or degrees of abnormality. In this work, we propose a novel framework that can identify subjects with early-stage mild cognitive impairment (eMCI) and consider individual variability by learning functional relations from automatically selected regions of interest (ROIs) for each subject concurrently. In particular, we devise a deep neural network composed of a temporal embedding module, an ROI selection module, and a disease-identification module. Notably, the ROI selection module is equipped with a reinforcement learning mechanism so it adaptively selects ROIs to facilitate the learning of discriminative feature representations from a temporally embedded blood-oxygen-level-dependent signals. Furthermore, our method allows us to capture the functional relations of a subject-specific ROI subset through the use of a graph-based neural network. Our method considers individual characteristics for diagnosis, as opposed to most conventional methods that identify the same biomarkers across subjects within a group. Based on the ADNI cohort, we validate the effectiveness of our method by presenting the superior performance of our network in eMCI identification. Furthermore, we provide insightful neuroscientific interpretations by analyzing the regions selected for the eMCI classification.
AB - Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely adopted to investigate functional abnormalities in brain diseases. Rs-fMRI data is unsupervised in nature because the psychological and neurological labels are coarse-grained, and no accurate region-wise label is provided along with the complex co-activities of multiple regions. To the best of our knowledge, most studies regarding univariate group analysis or multivariate pattern recognition for brain disease identification have focused on discovering functional characteristics shared across subjects; however, they have paid less attention to individual properties of neural activities that result from different symptoms or degrees of abnormality. In this work, we propose a novel framework that can identify subjects with early-stage mild cognitive impairment (eMCI) and consider individual variability by learning functional relations from automatically selected regions of interest (ROIs) for each subject concurrently. In particular, we devise a deep neural network composed of a temporal embedding module, an ROI selection module, and a disease-identification module. Notably, the ROI selection module is equipped with a reinforcement learning mechanism so it adaptively selects ROIs to facilitate the learning of discriminative feature representations from a temporally embedded blood-oxygen-level-dependent signals. Furthermore, our method allows us to capture the functional relations of a subject-specific ROI subset through the use of a graph-based neural network. Our method considers individual characteristics for diagnosis, as opposed to most conventional methods that identify the same biomarkers across subjects within a group. Based on the ADNI cohort, we validate the effectiveness of our method by presenting the superior performance of our network in eMCI identification. Furthermore, we provide insightful neuroscientific interpretations by analyzing the regions selected for the eMCI classification.
KW - Deep learning
KW - Graph neural network
KW - Mild cognitive impairment
KW - Personalized regions selection
KW - Reinforcement learning
KW - Resting-state functional magnetic resonance imaging
UR - http://www.scopus.com/inward/record.url?scp=85104907550&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2021.118048
DO - 10.1016/j.neuroimage.2021.118048
M3 - Article
C2 - 33878379
AN - SCOPUS:85104907550
SN - 1053-8119
VL - 236
JO - NeuroImage
JF - NeuroImage
M1 - 118048
ER -