Abstract
Most automated techniques for brain disease diagnosis utilize hand-crafted (e.g., voxel-based or region-based) biomarkers from structural magnetic resonance (MR) images as feature representations. However, these hand-crafted features are usually high-dimensional or require regions-of-interest (ROIs) defined by experts. In addition, because of the possibly heterogeneous property between the hand-crafted features and the subsequent model, existing methods may lead to sub-optimal performances in brain disease diagnosis. In this paper, we propose a landmark based deep feature learning (LDFL) framework to automatically extract patch-based representation from MRI for automatic diagnosis of Alzheimer's disease (AD). We first identify discriminative anatomical landmarks from MR images in a data-driven manner, and then propose a convolutional neural network (CNN) for patch-based deep feature learning. We have evaluated the proposed method on subjects from three public datasets, including the Alzheimer's Disease Neuroimaging Initiative (ADNI-1), ADNI-2, and the Minimal Interval Resonance Imaging in Alzheimer's Disease (MIRIAD) dataset. Experimental results of both tasks of brain disease classification and MR image retrieval demonstrate that the proposed LDFL method improves the performance of brain disease classification and MR image retrieval.
| Original language | English |
|---|---|
| Journal | IEEE Journal of Biomedical and Health Informatics |
| DOIs | |
| Publication status | Accepted/In press - 2018 Jan 9 |
Fingerprint
Keywords
- Anatomical landmarks
- brain disease diagnosis
- classification
- convolutional neural network
- Dementia
- Feature extraction
- Image retrieval
- image retrieval
- Testing
- Training
ASJC Scopus subject areas
- Biotechnology
- Computer Science Applications
- Electrical and Electronic Engineering
- Health Information Management
Cite this
Anatomical Landmark based Deep Feature Representation for MR Images in Brain Disease Diagnosis. / Liu, Mingxia; Zhang, Jun; Nie, Dong; Yap, Pew Thian; Shen, Dinggang.
In: IEEE Journal of Biomedical and Health Informatics, 09.01.2018.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Anatomical Landmark based Deep Feature Representation for MR Images in Brain Disease Diagnosis
AU - Liu, Mingxia
AU - Zhang, Jun
AU - Nie, Dong
AU - Yap, Pew Thian
AU - Shen, Dinggang
PY - 2018/1/9
Y1 - 2018/1/9
N2 - Most automated techniques for brain disease diagnosis utilize hand-crafted (e.g., voxel-based or region-based) biomarkers from structural magnetic resonance (MR) images as feature representations. However, these hand-crafted features are usually high-dimensional or require regions-of-interest (ROIs) defined by experts. In addition, because of the possibly heterogeneous property between the hand-crafted features and the subsequent model, existing methods may lead to sub-optimal performances in brain disease diagnosis. In this paper, we propose a landmark based deep feature learning (LDFL) framework to automatically extract patch-based representation from MRI for automatic diagnosis of Alzheimer's disease (AD). We first identify discriminative anatomical landmarks from MR images in a data-driven manner, and then propose a convolutional neural network (CNN) for patch-based deep feature learning. We have evaluated the proposed method on subjects from three public datasets, including the Alzheimer's Disease Neuroimaging Initiative (ADNI-1), ADNI-2, and the Minimal Interval Resonance Imaging in Alzheimer's Disease (MIRIAD) dataset. Experimental results of both tasks of brain disease classification and MR image retrieval demonstrate that the proposed LDFL method improves the performance of brain disease classification and MR image retrieval.
AB - Most automated techniques for brain disease diagnosis utilize hand-crafted (e.g., voxel-based or region-based) biomarkers from structural magnetic resonance (MR) images as feature representations. However, these hand-crafted features are usually high-dimensional or require regions-of-interest (ROIs) defined by experts. In addition, because of the possibly heterogeneous property between the hand-crafted features and the subsequent model, existing methods may lead to sub-optimal performances in brain disease diagnosis. In this paper, we propose a landmark based deep feature learning (LDFL) framework to automatically extract patch-based representation from MRI for automatic diagnosis of Alzheimer's disease (AD). We first identify discriminative anatomical landmarks from MR images in a data-driven manner, and then propose a convolutional neural network (CNN) for patch-based deep feature learning. We have evaluated the proposed method on subjects from three public datasets, including the Alzheimer's Disease Neuroimaging Initiative (ADNI-1), ADNI-2, and the Minimal Interval Resonance Imaging in Alzheimer's Disease (MIRIAD) dataset. Experimental results of both tasks of brain disease classification and MR image retrieval demonstrate that the proposed LDFL method improves the performance of brain disease classification and MR image retrieval.
KW - Anatomical landmarks
KW - brain disease diagnosis
KW - classification
KW - convolutional neural network
KW - Dementia
KW - Feature extraction
KW - Image retrieval
KW - image retrieval
KW - Testing
KW - Training
UR - http://www.scopus.com/inward/record.url?scp=85041234710&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85041234710&partnerID=8YFLogxK
U2 - 10.1109/JBHI.2018.2791863
DO - 10.1109/JBHI.2018.2791863
M3 - Article
C2 - 29994175
AN - SCOPUS:85041234710
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
SN - 2168-2194
ER -