Neurological Disorders and Imaging Physics, Volume 3: Application to Autism Spectrum Disorders and Alzheimer’s

PRELIMS.pdf
Preface
Acknowledgments
Editor biographies
Ayman El-Baz
Jasjit S Suri
List of contributors
CH001.pdf
Chapter 1 Machine learning applications to recognize autism and Alzheimer’s disease
1.1 Introduction
1.2 Brain disorders
1.2.1 Autism spectrum disorder (ASD)
1.2.2 Alzheimer’s disease (AD)
1.2.3 Mild cognitive impairment
1.3 Deep learning
1.3.1 ASD and deep learning
1.3.2 Alzheimer’s and deep learning
1.4 Conclusion
References
CH002.pdf
Chapter 2 Neuropathology and neuroimaging of Alzheimer’s disease
Abbreviations
2.1 Alzheimer’s disease: history, concept, clinical picture, and neurobiology
2.1.1 Brief history and concept
2.1.2 Clinical presentation
2.1.3 Neurobiology and physiopathology of Alzheimer’s disease
2.1.4 Clinical and physiopathological feature assessment
2.2 Biomarkers
2.2.1 CSF biomarkers
2.2.2 Neuroimaging biomarkers
2.3 Understanding AD progression through structural imaging
2.3.1 Mapping AD neuropathology through neuronal circuits: what is the point?
2.3.2 Cortical myelination throughout life
2.3.3 Models of the neuropathological progression of AD
2.3.4 Hypothetical models of neurodegeneration
2.3.5 Understanding the biophysical properties of DTI
2.4 Conclusions
References
CH003.pdf
Chapter 3 Retinal imaging in Alzheimer’s disease
3.1 Introduction
3.2 Lipofuscin hypothesis of AD
3.3 OCT and FAF in retinal diseases
3.3.1 SD-OCT and FAF in diagnosing AD
3.4 Misfolded proteins in the retina
3.5 Cryo-electron microscopy
3.6 Retinal imaging of misfolded proteins
3.7 Curcumin
3.8 AMD and AD
3.9 Glaucoma and AD
3.10 Alpha-synuclein in AD
3.11 Early diagnosis of AD
3.12 Biomarkers in AD
3.13 Discussion
References
CH004.pdf
Chapter 4 Clinically relevant depression and risk of Alzheimer’s disease in the elderly: meta-analysis of cohort studies
4.1 Introduction
4.2 Methods
4.2.1 Search strategy
4.2.2 Study selection
4.2.3 Data extraction
4.2.4 Quality assessment
4.2.5 Statistical analysis
4.3 Results
4.3.1 Study selection
4.3.2 Description of included studies
4.3.3 Effect estimation of AD risk based on depression
4.3.4 The risk of publication bias
4.3.5 Influence analysis
4.3.6 Population attributable fraction
4.4 Discussion
4.4.1 Main results
4.4.2 Comparison with previous studies
4.4.3 Strengths and limitations
4.4.4 Pathogenic hypotheses
4.4.5 Clinical implications
4.4.6 Public health implications
4.5 Conclusion
References
CH005.pdf
Chapter 5 The implications of genetic factors in autism spectrum disorder and Alzheimer’s disease
5.1 Autism spectrum disorder
5.2 Alzheimer’s disease
5.2.1 Introduction
5.2.2 Clinical assessment
5.2.3 Risk and protective factors
5.2.4 Neuropathological changes
5.2.5 Genetics of AD
References
CH006.pdf
Chapter 6 Nuclear neurology of autism spectrum disorder
6.1 Introduction
6.1.1 Imaging modalities
6.2 Specific neurochemical physiology
6.2.1 Dopaminergic neurotransmission
6.2.2 Serotoninergic neurotransmission
6.2.3 Serotonin synthesis
6.2.4 Serotonin transporter (SERT)
6.2.5 Serotonin (5-HT 2A) receptor
6.2.6 GABA
6.3 Basal physiology
6.3.1 Protein synthesis
6.3.2 Glucose metabolism
6.4 Regional cerebral blood flow
6.4.1 PET investigation
6.4.2 SPECT investigation
6.5 Conclusion
References
CH007.pdf
Chapter 7 Ethylene and ammonia in neurobehavioral disorders
7.1 Introduction
7.2 Method
7.3 Volatile organic compounds in autism and schizophrenia
7.3.1 Schizophrenia
7.3.2 Autism
7.3.3 Ethylene in mental disorders
7.3.4 Ammonia in mental disorders
7.4 Results and discussion
7.4.1 Protocol for breath gas sampling from schizophrenic patients
7.4.2 Ethylene and ammonia assessment using LPAS from schizophrenic patients
7.4.3 Protocol for breath gas sampling from autistic young adults
7.4.4 Ethylene and ammonia assessment using LPAS in autistic young adults
7.5 Conclusions and future directions
References
CH008.pdf
Chapter 8 The impact of stress on parental behavior following a diagnosis of autism
8.1 Parental stress and the ASD diagnosis
8.2 The potential effect of stress on parental treatment choices
8.2.1 The prevalence of fad treatments
8.3 Parents as the agents of behavioral change
8.4 Factors affecting parental involvement
8.4.1 Making parent training accessible
8.4.2 Focusing on the contingencies that maintain parents’ behaviors
8.5 Tying it all together: mitigating stress, selecting evidence-based treatments, and increasing parental involvement
References
CH009.pdf
Chapter 9 Visual saliency for medical imaging and computer-aided diagnosis
9.1 Introduction
9.2 Visual saliency for medical image analysis
9.3 Saliency model for Alzheimer’s disease detection from structural MRI
9.3.1 Visual assessment of brain atrophy for AD diagnosis
9.3.2 AD saliency map generation
Algorithm 1. STD map estimation
9.4 Visual interpretation of visual saliency
9.4.1 Region of interest detection and quantification
9.4.2 Comparison with state-of-the-art saliency models
9.5 AD classification using saliency maps
9.5.1 Proposed method
9.5.2 MRI data
9.5.3 Classification results
9.6 Conclusion
Acknowledgement
References
CH010.pdf
Chapter 10 The early diagnosis of Alzheimer’s disease using advanced biomedical engineering technology
10.1 Introduction
10.2 Literature review
10.3 Causes and effects of AD
10.4 Hallmarks of AD
10.5 The retina and AD
10.6 Tests for diagnosing AD
10.7 Early diagnosis of AD
10.8 Medical imaging techniques
10.9 Analysis of MRI and OCT images
10.9.1 Image acquisition
10.9.2 Pre-processing
10.9.3 Image segmentation
10.9.4 Image post-processing
10.9.5 Feature extraction
10.9.6 Feature selection
10.9.7 Classification
10.10 Discussion
10.11 Conclusion
Acknowledgments
References
CH011.pdf
Chapter 11 A local/regional computer aided system for the diagnosis of mild cognitive impairment
11.1 Introduction
11.2 Material and methods
11.2.1 Materials
11.2.2 Methods
11.3 Results
11.4 Discussion
Acknowledgments
References
CH012.pdf
Chapter 12 Identifying Alzheimer’s disease using feature reduction of GLCM and supervised classification techniques
12.1 Introduction
12.2 Related work
12.3 The proposed supervised-learning approach for AD identification
12.3.1 Voxel-based morphometric feature extraction
12.3.2 Texture feature extraction
12.3.3 Feature reduction
12.3.4 Classification
12.4 Experimental results and discussion
12.4.1 Dataset
12.4.2 Experimental work
12.5 Conclusion and future work
References
CH013.pdf
Chapter 13 Current trends and considerations of Alzheimer’s disease
13.1 Introduction
13.2 Anatomical background
13.2.1 Neurological diseases
13.2.2 Neurodegenerative diseases
13.2.3 Alzheimer’s disease
13.3 Medical imaging modalities for AD
13.3.1 Radiology
13.3.2 Printed signals/waves
13.4 AD literature review
13.4.1 CAD system based studies
13.5 Discussion
13.5.1 Databases
13.5.2 Modalities
13.5.3 Applied techniques
13.5.4 Subjects
13.6 Conclusion
References
CH014.pdf
Chapter 14 A noninvasive image-based approach toward an early diagnosis of autism
14.1 Introduction
14.2 Methods
14.2.1 Segmentation
14.2.2 Feature extraction
14.3 Experimental results and conclusions
References
CH015.pdf
Chapter 15 Towards a robust CAD system for early diagnosis of autism using structural MRI
15.1 Introduction
15.2 Methods
15.2.1 Cx and CWM segmentation from MRI scans
15.2.2 Extraction of shape features
15.2.3 Deep fusion classification network (DFCN)
15.3 Experimental results and conclusions
References
CH016.pdf
Chapter 16 Computational analysis techniques: a case study on fMRI for autism spectrum disorder
16.1 Introduction
16.2 Task based fMRI analysis
16.2.1 Building the design matrix
16.2.2 Multi level general linear model (GLM) in fMRI
16.2.3 GLM parameter estimates
16.2.4 Limitations of GLM for parameter estimation in fMRI analysis
16.3 RfMRI analysis
16.3.1 Principle components analysis in RfMRI analysis
16.3.2 Independent components analysis in RfMRI analysis
16.3.3 Restricted Boltzmann machines in RfMRI analysis
16.4 A case study of fMRI in autism
16.4.1 Task based fMRI findings in autism
16.4.2 Resting state fMRI findings in autism
16.5 Conclusions and future work
References
CH017.pdf
Chapter 17 Autism diagnosis using task-based functional MRI
17.1 Introduction
17.2 Materials and methods
17.2.1 Data preprocessing
17.2.2 Multi level general linear model (GLM) in fMRI
17.2.3 Feature selection and classification
17.3 Experimental results and conclusion
17.3.1 Higher level analysis
17.3.2 Classification results
17.3.3 Conclusion and future work
References