Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis using Structural MRI

Chunfeng Lian, Mingxia Liu, Jun Zhang, Dinggang Shen

Research output: Contribution to journalArticle

12 Citations (Scopus)

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 languageEnglish
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
DOIs
Publication statusAccepted/In press - 2018 Jan 1
Externally publishedYes

Fingerprint

Magnetic Resonance Imaging
Magnetic resonance
Magnetic resonance imaging
Atrophy
Joints
Imaging techniques
Brain
Learning
Neural Networks
Neural networks
Hierarchical Classification
Computer aided diagnosis
Computer-aided Diagnosis
Brain Diseases
Neurodegenerative Diseases
Feature Extraction
Patch
Disorder
Feature extraction
Classifiers

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

@article{28bcb08d22c74d5a9999a69e8bb41df2,
title = "Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis using Structural MRI",
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.",
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",
author = "Chunfeng Lian and Mingxia Liu and Jun Zhang and Dinggang Shen",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/TPAMI.2018.2889096",
language = "English",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",

}

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 -