TY - JOUR
T1 - Joint classification and regression via deep multi-task multi-channel learning for Alzheimer's disease diagnosis
AU - Liu, Mingxia
AU - Zhang, Jun
AU - Adeli, Ehsan
AU - Shen, DInggang
N1 - Funding Information:
Manuscript received August 3, 2018; accepted September 8, 2018. Date of publication September 13, 2018; date of current version April 19, 2019. This work was supported in part by NIH grants (EB006733, EB008374, EB009634, MH100217, AG041721, AG042599, AG010129, and AG030514). Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. (Mingxia Liu and Jun Zhang contributed equally to this work.) (Corresponding author: Dinggang. Shen.) M. Liu, J. Zhang, and E. Adeli are with the University of North Carolina at Chapel Hill.
Publisher Copyright:
© 1964-2012 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - In the field of computer-aided Alzheimer's disease (AD) diagnosis, jointly identifying brain diseases and predicting clinical scores using magnetic resonance imaging (MRI) have attracted increasing attention since these two tasks are highly correlated. Most of existing joint learning approaches require hand-crafted feature representations for MR images. Since hand-crafted features of MRI and classification/regression models may not coordinate well with each other, conventional methods may lead to sub-optimal learning performance. Also, demographic information (e.g., age, gender, and education) of subjects may also be related to brain status, and thus can help improve the diagnostic performance. However, conventional joint learning methods seldom incorporate such demographic information into the learning models. To this end, we propose a deep multi-task multi-channel learning (DM2L) framework for simultaneous brain disease classification and clinical score regression, using MRI data and demographic information of subjects. Specifically, we first identify the discriminative anatomical landmarks from MR images in a data-driven manner, and then extract multiple image patches around these detected landmarks. We then propose a deep multi-task multi-channel convolutional neural network for joint classification and regression. Our DM2L framework can not only automatically learn discriminative features for MR images, but also explicitly incorporate the demographic information of subjects into the learning process. We evaluate the proposed method on four large multi-center cohorts with 1984 subjects, and the experimental results demonstrate that DM2L is superior to several state-of-the-art joint learning methods in both the tasks of disease classification and clinical score regression.
AB - In the field of computer-aided Alzheimer's disease (AD) diagnosis, jointly identifying brain diseases and predicting clinical scores using magnetic resonance imaging (MRI) have attracted increasing attention since these two tasks are highly correlated. Most of existing joint learning approaches require hand-crafted feature representations for MR images. Since hand-crafted features of MRI and classification/regression models may not coordinate well with each other, conventional methods may lead to sub-optimal learning performance. Also, demographic information (e.g., age, gender, and education) of subjects may also be related to brain status, and thus can help improve the diagnostic performance. However, conventional joint learning methods seldom incorporate such demographic information into the learning models. To this end, we propose a deep multi-task multi-channel learning (DM2L) framework for simultaneous brain disease classification and clinical score regression, using MRI data and demographic information of subjects. Specifically, we first identify the discriminative anatomical landmarks from MR images in a data-driven manner, and then extract multiple image patches around these detected landmarks. We then propose a deep multi-task multi-channel convolutional neural network for joint classification and regression. Our DM2L framework can not only automatically learn discriminative features for MR images, but also explicitly incorporate the demographic information of subjects into the learning process. We evaluate the proposed method on four large multi-center cohorts with 1984 subjects, and the experimental results demonstrate that DM2L is superior to several state-of-the-art joint learning methods in both the tasks of disease classification and clinical score regression.
KW - Anatomical landmark
KW - Brain disease diagnosis
KW - Classification
KW - Convolutional neural network (CNN)
KW - Regression
UR - http://www.scopus.com/inward/record.url?scp=85053292802&partnerID=8YFLogxK
U2 - 10.1109/TBME.2018.2869989
DO - 10.1109/TBME.2018.2869989
M3 - Article
C2 - 30222548
AN - SCOPUS:85053292802
VL - 66
SP - 1195
EP - 1206
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
SN - 0018-9294
IS - 5
M1 - 8463559
ER -