Skip to main content

2017 | Buch

Multimodal Neuroimaging Computing for the Characterization of Neurodegenerative Disorders

insite
SUCHEN

Über dieses Buch

This thesis covers various facets of brain image computing methods and illustrates the scientific understanding of neurodegenerative disorders based on four general aspects of multimodal neuroimaging computing: neuroimaging data pre-processing, brain feature modeling, pathological pattern analysis, and translational model development. It demonstrates how multimodal neuroimaging computing techniques can be integrated and applied to neurodegenerative disease research and management, highlighting relevant examples and case studies. Readers will also discover a number of interesting extension topics in longitudinal neuroimaging studies, subject-centered analysis, and the brain connectome. As such, the book will benefit all health informatics postgraduates, neuroscience researchers, neurology and psychiatry practitioners, and policymakers who are interested in medical image computing and computer-assisted interventions.

Inhaltsverzeichnis

Frontmatter
Chapter 1. Introduction
Abstract
Modern neuroimaging technologies, such as magnetic resonance imaging (MRI), positron emission tomography (PET) and electro-/magneto-encephalography (EEG/MEG), have transformed the way we study the brain (Kikinis et al., 3D slicer: A platform for subject-specific image analysis, visualization, and clinical support, Intraoperative imaging and image-guided therapy, 277–289, 2014, [48]) by providing essential anatomical and functional information about the brain in unprecedented details.
Sidong Liu
Chapter 2. Background
Abstract
This chapter reviews the recent neuroimaging studies with a focus on the characterization of neurodegenerative disorders. These studies fall into four categories based on the primary outputs of these analyses, which correspond to the four layers in the neuroimaging computing architecture, as illustrated in Fig. 2.1.
Sidong Liu
Chapter 3. ADNI Datasets and Pre-processing Protocols
Abstract
Datasets used in this study were obtained
Sidong Liu
Chapter 4. Encoding the Neurodegenerative Features
Abstract
Various feature descriptors have been proposed to model the disease pathologies. Chapter 2, Sect. 2.​2 reviews the common morphological, functional and learning-based features. These features are capable of capturing many important changes in the brain, such as brain atrophy and hypo-metabolism, but they are constrained to detect other subtle and complicated changes, such as shape of the cortical regions or contrast between the lesions and normal tissues. In addition, it is also very challenging to fuse the multimodal features.
Sidong Liu
Chapter 5. Recognizing the Neurodegenerative Patterns
Abstract
Neurodegenerative disorders always progress in certain patterns. In the case of Alzheimer’s Disease (AD), for example, its pathology starts within hippocampus and entorhinal cortex, and spreads throughout most of the temporal lobe and posterior cingulate, finally reaches the parietal, prefrontal and orbitofrontal regions (Desikan et al. BRAIN 132:2048–2057, 2009, [10], Risacher et al. Curr Alzheimer’s Res 6:347–361, 2009, [35], Fan et al. NeuroImage 39:1731–1743, 2008, [11]). Subjects with AD may appear with different patterns, and we could use these patterns to enhance our understanding of the disease and facilitate the diagnosis.
Sidong Liu
Chapter 6. Alzheimer’s Disease Staging and Prediction
Abstract
Alzheimer’s disease (AD), one of the most common and disabling neurodegenerative disorders among aging people, accounts for nearly 70% of all dementia cases.
Sidong Liu
Chapter 7. Neuroimaging Content-Based Retrieval
Abstract
Medical content-based retrieval (MCBR) is progressing rapidly with the advances in database systems, computer vision and medical informatics. MCBR has a wide range of medical applications, including medical imaging data management, clinical training and education. Most importantly, it provides access to the cases of previously diagnosed patients, thus is able to support clinical decisions for future cases (Müller et al., Int J Med Inf 73:1–23, 2004, [27]; Cai et al., Biomedical information technology, 2008, [4]).
Sidong Liu
Chapter 8. Conclusions and Future Directions
Abstract
A series of models and methods have been developed to systematically analyze the neurodegeneration from data acquisition to application development. This chapter concludes the research findings in neurodegenerative disorder based on the analysis on large-scale multimodal datasets and further outlines the future directions.
Sidong Liu
Backmatter
Metadaten
Titel
Multimodal Neuroimaging Computing for the Characterization of Neurodegenerative Disorders
verfasst von
Sidong Liu
Copyright-Jahr
2017
Verlag
Springer Singapore
Electronic ISBN
978-981-10-3533-3
Print ISBN
978-981-10-3532-6
DOI
https://doi.org/10.1007/978-981-10-3533-3

Neuer Inhalt