This book is based on deep learning approaches used for the diagnosis of neurological disorders, including basics of deep learning algorithms using diagrams, data tables, and practical examples, for diagnosis of neurodegenerative and neurodevelopmental disorders. It includes application of feed-forward neural networks, deep generative models, convolutional neural networks, graph convolutional networks, and recurrent neural networks in the field of diagnosis of neurological disorders. Along with this, data preprocessing including scaling, correction, trimming, and normalization is also included.
Offers a detailed description of the deep learning approaches used for the diagnosis of neurological disorders.
Demonstrates concepts of deep learning algorithms using diagrams, data tables, and examples for the diagnosis of neurodegenerative, neurodevelopmental, and psychiatric disorders.
Helps build, train, and deploy different types of deep architectures for diagnosis.
Explores data preprocessing techniques involved in diagnosis.
Includes real-time case studies and examples.
This book is aimed at graduate students and researchers in biomedical imaging and machine learning.
Author(s): Jyotismita Chaki
Publisher: CRC Press
Year: 2023
Language: English
Commentary: true
Pages: 237
Cover
Half Title
Title Page
Copyright Page
Table of Contents
Preface
About the Editor
List of Contributors
Chapter 1 Introduction to Deep Learning Techniques for Diagnosis of Neurological Disorders
Introduction
Chapter 2 A Comprehensive Study of Data Pre-Processing Techniques for Neurological Disease (NLD) Detection
2.1 Introduction
2.2 Related Works
2.3 Methods
2.3.1 Open-Access Data for NLD Disease Detection
2.3.1.1 ADNI
2.3.1.2 OASIS
2.3.1.3 COBRE
2.3.1.4 FBIRN
2.3.1.5 PPMI
2.3.2 ML Models for NLD Disease Detection
2.3.3 Deep Learning Models for NLD Disease Detection
2.4 Experimental Discussion of Data Pre-ProcessingTechniques for Brain Analysis
2.4.1 Filtering
2.4.1.1 Gaussian Filter
2.4.1.2 Output
2.4.1.3 Median Filter
2.4.1.4 Output
2.4.1.5 Weiner Filter
2.4.1.6 Output
2.4.1.7 Frequency Filter
2.4.1.8 Output
2.4.1.9 Unsharp Filter
2.4.1.10 Output
2.4.2 Normalization
2.4.2.1 Spatial Normalization
2.4.2.2 Intensity Normalization
2.4.2.3 Output
2.4.2.4 Histogram Normalization
2.4.2.5 Output
2.5 Conclusion
References
Chapter 3 Classification of the Level of Alzheimer’s Disease Using Anatomical Magnetic Resonance Images Based on a Novel Deep Learning Structure
3.1 Organization of the Chapter
3.2 Introduction
3.2.1 Motivation
3.2.2 Contribution
3.3 Materials and Methods
3.3.1 Dataset
3.3.2 Proposed Method
3.3.2.1 Images Processing
3.3.2.2 CNN Design
3.3.3 Evaluation Metrics
3.4 Results
3.5 Discussion
3.6 Conclusion
3.7 Future Scopes
References
Chapter 4 Detection of Alzheimer’s Disease Stages Based on Deep Learning Architectures from MRI Images
4.1 Introduction
4.2 Objectives of the Study
4.3 Literature Review
4.3.1 Early Diagnosis of Alzheimer’s Disease Using DL-Based Approaches
4.3.2 A Transfer Learning Approach for Early Diagnosis of AD on MRI Images
4.3.3 Classification of AD MRI Images Using a Hybrid CNN Technique
4.3.4 Ensembles of DL-Based Network Models for the Early Diagnosis of the AD
4.4 Gap Analysis
4.5 Research Methodology of the Study
4.6 Findings and Discussions
4.7 Conclusion and Recommendations
References
Chapter 5 Analysis on Detection of Alzheimer’s using Deep Neural Network
5.1 Introduction
5.2 A Study on Assorted Deep Neural Networks
5.2.1 CNN
5.2.2 LSTM
5.2.3 RNN
5.2.4 Autoencoder
5.2.5 Perceptron
5.2.6 DBN
5.2.7 RBM
5.3 Methodology
5.3.1 Types of CNN
5.3.2 ResNet
5.3.2.1 ResNet’s Features
5.3.3 GoogLeNet
5.3.3.1 Features of GoogLeNet
5.3.4 VGGNet-16 and VGGNet-19
5.3.4.1 Summary of VGGNet Model
5.3.5 AlexNet
5.3.5.1 Details of the model
5.3.6 LeNet
5.3.6.1 LeNet’s Features
5.4 Results and Discussion
5.4.1 Experimental Analysis and Discussion of Datasets
5.4.1.1 ADNI
5.4.1.2 OASIS
5.4.2 Analysis of Types of DNN
5.4.2.1 ADNI Dataset
5.4.2.2 OASIS Dataset
5.4.3 Performance Measures
5.5 Conclusion
References
Chapter 6 Detection and Classification of Alzheimer’s Disease: A Deep Learning Approach with Predictor Variables
6.1 Introduction
6.2 Related Work
6.3 Motivation and Objective
6.4 Deep Neural Network
6.5 Proposed Method
6.6 Experimental Setup
6.7 Dataset
6.8 Performance Metrics
6.9 Results and Discussion
6.10 Conclusion
References
Chapter 7 Classification of Brain Tumor Using Optimized Deep Neural Network Models
7.1 Introduction
7.2 Related Work
7.3 Dataset Used for Proposed Method
7.3.1 IBSR Dataset
7.3.2 MRI Scan Images
7.4 Performance Evaluation Method
7.4.1 Accuracy
7.4.2 Precision
7.4.3 Recall
7.4.4 F-Measure
7.4.5 FP Rate
7.4.6 TP Rate
7.5 Methodology of Proposed DNN Models
7.5.1 VGG16
7.5.2 ResNet50
7.5.3 Inception-V3
7.5.4 Develop a Model Approach
7.5.5 Pre-trained Model Approach
7.6 Results and Discussion
7.7 Conclusion
References
Chapter 8 Fully Automated Segmentation of Brain Stroke Lesions Using Mask Region-Based Convolutional Neural Network
8.1 Introduction
8.2 Materials and Methods
8.2.1 Imaging Dataset and Data Acquisition
8.2.2 Mask Region-Based Convolutional Neural Network (Mask R-CNN)
8.2.3 Backbone Structure
8.3 Results and Discussion
8.4 Conclusion
Acknowledgments
References
Chapter 9 Efficient Classification of Schizophrenia EEG Signals Using Deep Learning Methods
9.1 Introduction
9.2 Data Recording
9.3 Methodology
9.3.1 Time Domain Features
9.3.2 Creating Spectrogram Images Using Short-Time Fourier Transform (STFT)
9.3.3 Architecture of LSTM
9.3.4 Architecture of VGG-16
9.3.5 Architecture of AlexNet
9.4 Results and Discussion
9.4.1 Results of Binary Classification Using LSTM Model
9.4.2 Results of Binary Classification Using VGG-16 and AlexNet Models
9.4.3 Five-Fold Cross-Validation
9.5 Conclusion
References
Chapter 10 Implementation of a Deep Neural Network-Based Framework for Actigraphy Analysis and Prediction of Schizophrenia
10.1 Introduction
10.2 Related Work
10.2.1 Actigraphy
10.3 Materials and Method
10.4 Results and Discussion
10.4.1 Case (i)
10.4.2 Case (ii)
10.5 Conclusion
References
Chapter 11 Evaluating Psychomotor Skills in Autism Spectrum Disorder Through Deep Learning
11.1 Introduction
11.2 Search Methodology
11.3 Clinical Studies of ASD
11.3.1 Robot-Assisted Diagnosis
11.3.2 Eye Tracking
11.3.3 Facial Scanning
11.3.4 Gait Analysis for Stereotypical Movements
11.3.5 Facial Fused Gait Analysis
11.3.6 Electroencephalography
11.3.7 Functional near-Infrared Spectroscopy (f-NIRS)
11.3.8 MR Imaging (Structural and Functional)
11.4 Results and Discussions
11.5 Conclusion
11.5.1 Declarations
References
Chapter 12 Dementia Detection with Deep Networks Using Multi-Modal Image Data
12.1 Introduction
12.2 Related Work
12.2.1 Structural Imaging in Dementia
12.2.2 Molecular Imaging in Dementia
12.2.3 Multi-Modality Imaging Solutions
12.3 Methodology
12.3.1 Image Acquisition
12.3.2 Pre-Processing of Brain Scans
12.3.3 Implementation of Multi-Modal Imaging Networks
12.4 Results and Discussion
12.5 Conclusion
Acknowledgments
Notes
References
Chapter 13 The Importance of the Internet of Things in Neurological Disorder: A Literature Review
13.1 Introduction
13.2 Fundamentals of Deep Learning in Healthcare Systems
13.3 Developments in Healthcare Systems and IoT
13.4 IoT in Neurological Diseases
13.5 Conclusions and Future Scope
References
Index
