Abstract
Structural magnetic resonance imaging (sMRI) has been widely used for computer-aided diagnosis of neurodegenerative disorders, e.g., Alzheimer's disease (AD), due to its sensitivity to morphological changes caused by brain atrophy. Recently, a few deep learning methods (e.g., convolutional neural networks, CNNs) have been proposed to learn task-oriented features from sMRI for AD diagnosis, and achieved superior performance than the conventional learning-based methods using hand-crafted features. However, these existing CNN-based methods still require the pre-determination of informative locations in sMRI. That is, the stage of discriminative atrophy localization is isolated to the latter stages of feature extraction and classifier construction. In this paper, we propose a hierarchical fully convolutional network (H-FCN) to automatically identify discriminative local patches and regions in the whole brain sMRI, upon which multi-scale feature representations are then jointly learned and fused to construct hierarchical classification models for AD diagnosis. Our proposed H-FCN method was evaluated on a large cohort of subjects from two independent datasets (i.e., ADNI-1 and ADNI-2), demonstrating good performance on joint discriminative atrophy localization and brain disease diagnosis.
| Original language | English |
|---|---|
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| DOIs | |
| Publication status | Accepted/In press - 2018 Jan 1 |
| Externally published | Yes |
Fingerprint
Keywords
- Alzheimer's disease
- Atrophy
- Brain modeling
- Computer-Aided Alzheimer's Disease Diagnosis
- Discriminative Atrophy Localization
- Feature extraction
- Fully Convolutional Networks
- Medical diagnosis
- Solid modeling
- Structural MRI
- Support vector machines
- Weakly-Supervised Learning
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
- Computational Theory and Mathematics
- Artificial Intelligence
- Applied Mathematics
Cite this
Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis using Structural MRI. / Lian, Chunfeng; Liu, Mingxia; Zhang, Jun; Shen, Dinggang.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 01.01.2018.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis using Structural MRI
AU - Lian, Chunfeng
AU - Liu, Mingxia
AU - Zhang, Jun
AU - Shen, Dinggang
PY - 2018/1/1
Y1 - 2018/1/1
N2 - Structural magnetic resonance imaging (sMRI) has been widely used for computer-aided diagnosis of neurodegenerative disorders, e.g., Alzheimer's disease (AD), due to its sensitivity to morphological changes caused by brain atrophy. Recently, a few deep learning methods (e.g., convolutional neural networks, CNNs) have been proposed to learn task-oriented features from sMRI for AD diagnosis, and achieved superior performance than the conventional learning-based methods using hand-crafted features. However, these existing CNN-based methods still require the pre-determination of informative locations in sMRI. That is, the stage of discriminative atrophy localization is isolated to the latter stages of feature extraction and classifier construction. In this paper, we propose a hierarchical fully convolutional network (H-FCN) to automatically identify discriminative local patches and regions in the whole brain sMRI, upon which multi-scale feature representations are then jointly learned and fused to construct hierarchical classification models for AD diagnosis. Our proposed H-FCN method was evaluated on a large cohort of subjects from two independent datasets (i.e., ADNI-1 and ADNI-2), demonstrating good performance on joint discriminative atrophy localization and brain disease diagnosis.
AB - Structural magnetic resonance imaging (sMRI) has been widely used for computer-aided diagnosis of neurodegenerative disorders, e.g., Alzheimer's disease (AD), due to its sensitivity to morphological changes caused by brain atrophy. Recently, a few deep learning methods (e.g., convolutional neural networks, CNNs) have been proposed to learn task-oriented features from sMRI for AD diagnosis, and achieved superior performance than the conventional learning-based methods using hand-crafted features. However, these existing CNN-based methods still require the pre-determination of informative locations in sMRI. That is, the stage of discriminative atrophy localization is isolated to the latter stages of feature extraction and classifier construction. In this paper, we propose a hierarchical fully convolutional network (H-FCN) to automatically identify discriminative local patches and regions in the whole brain sMRI, upon which multi-scale feature representations are then jointly learned and fused to construct hierarchical classification models for AD diagnosis. Our proposed H-FCN method was evaluated on a large cohort of subjects from two independent datasets (i.e., ADNI-1 and ADNI-2), demonstrating good performance on joint discriminative atrophy localization and brain disease diagnosis.
KW - Alzheimer's disease
KW - Atrophy
KW - Brain modeling
KW - Computer-Aided Alzheimer's Disease Diagnosis
KW - Discriminative Atrophy Localization
KW - Feature extraction
KW - Fully Convolutional Networks
KW - Medical diagnosis
KW - Solid modeling
KW - Structural MRI
KW - Support vector machines
KW - Weakly-Supervised Learning
UR - http://www.scopus.com/inward/record.url?scp=85058985521&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058985521&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2018.2889096
DO - 10.1109/TPAMI.2018.2889096
M3 - Article
AN - SCOPUS:85058985521
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
ER -