Оглавление
Группа авторов. Computational Analysis and Deep Learning for Medical Care
Table of Contents
List of Illustrations
List of Tables
Guide
Pages
Computational Analysis and Deep Learning for Medical Care. Principles, Methods, and Applications
Preface
1. CNN: A Review of Models, Application of IVD Segmentation
1.1 Introduction
1.2 Various CNN Models. 1.2.1 LeNet-5
1.2.2 AlexNet
1.2.3 ZFNet
1.2.4 VGGNet
1.2.5 GoogLeNet
1.2.6 ResNet
1.2.7 ResNeXt
1.2.8 SE-ResNet
1.2.9 DenseNet
1.2.10 MobileNets
1.3 Application of CNN to IVD Detection
1.4 Comparison With State-of-the-Art Segmentation Approaches for Spine T2W Images
1.5 Conclusion
References
2. Location-Aware Keyword Query Suggestion Techniques With Artificial Intelligence Perspective
2.1 Introduction
2.2 Related Work
2.3 Artificial Intelligence Perspective
2.3.1 Keyword Query Suggestion
2.3.1.1 Random Walk–Based Approaches
2.3.1.2 Cluster-Based Approaches
2.3.1.3 Learning to Rank Approaches
2.3.2 User Preference From Log
2.3.3 Location-Aware Keyword Query Suggestion
2.3.4 Enhancement With AI Perspective
2.3.4.1 Case Study
2.3.4.1.1 Personalization
2.3.4.1.2 Sending Adaptive Notifications
2.3.4.1.3 Analyzing
2.3.4.1.4 Reduce Labor at Routine Jobs
2.4 Architecture
2.4.1 Distance Measures
2.5 Conclusion
References
3. Identification of a Suitable Transfer Learning Architecture for Classification: A Case Study with Liver Tumors
3.1 Introduction
3.2 Related Works
3.3 Convolutional Neural Networks
3.3.1 Feature Learning in CNNs
3.3.2 Classification in CNNs
3.4 Transfer Learning
3.4.1 AlexNet
3.4.2 GoogLeNet
3.4.3 Residual Networks
3.4.3.1 ResNet-18
3.4.3.2 ResNet-50
3.5 System Model
3.6 Results and Discussions. 3.6.1 Dataset
3.6.2 Assessment of Transfer Learning Architectures
3.7 Conclusion
References
4. Optimization and Deep Learning–Based Content Retrieval, Indexing, and Metric Learning Approach for Medical Images
4.1 Introduction
4.2 Related Works
4.3 Proposed Method
4.3.1 Input Dataset
4.3.2 Pre-Processing
4.3.3 Combination of DCNN and CFML
4.3.4 Fine Tuning and Optimization
4.3.5 Feature Extraction
4.3.6 Localization of Abnormalities in MRI and CT Scanned Images
4.4 Results and Discussion
4.4.1 Metric Learning
4.4.2 Comparison of the Various Models for Image Retrieval
4.4.3 Precision vs. Recall Parameters Estimation for the CBIR
4.4.4 Convolutional Neural Networks–Based Landmark Localization
4.5 Conclusion
References
5. Deep Learning for Clinical and Health Informatics
5.1 Introduction
5.1.1 Deep Learning Over Machine Learning
5.2 Related Work
5.3 Motivation
5.4 Scope of the Work in Past, Present, and Future
5.5 Deep Learning Tools, Methods Available for Clinical, and Health Informatics
5.6 Deep Learning: Not-So-Near Future in Biomedical Imaging
5.6.1 Types of Medical Imaging
5.6.2 Uses and Benefits of Medical Imaging
5.7 Challenges Faced Toward Deep Learning Using in Biomedical Imaging
5.7.1 Deep Learning in Healthcare: Limitations and Challenges
5.8 Open Research Issues and Future Research Directions in Biomedical Imaging (Healthcare Informatics)
5.9 Conclusion
References
6. Biomedical Image Segmentation by Deep Learning Methods
6.1 Introduction
6.2 Overview of Deep Learning Algorithms
6.2.1 Deep Learning Classifier (DLC)
6.2.2 Deep Learning Architecture
6.3 Other Deep Learning Architecture. 6.3.1 Restricted Boltzmann Machine (RBM)
6.3.2 Deep Learning Architecture Containing Autoencoders
6.3.3 Sparse Coding Deep Learning Architecture
6.3.4 Generative Adversarial Network (GAN)
6.3.5 Recurrent Neural Network (RNN)
6.4 Biomedical Image Segmentation
6.4.1 Clinical Images
6.4.2 X-Ray Imaging
6.4.3 Computed Tomography (CT)
6.4.4 Magnetic Resonance Imaging (MRI)
6.4.5 Ultrasound Imaging (US)
6.4.6 Optical Coherence Tomography (OCT)
6.5 Conclusion
References
7. Multi-Lingual Handwritten Character Recognition Using Deep Learning
7.1 Introduction
7.2 Related Works
7.3 Materials and Methods
7.4 Experiments and Results
7.4.1 Dataset Description. 7.4.1.1 Handwritten Math Symbols
7.4.1.2 Bangla Handwritten Character Dataset
7.4.1.3 Devanagari Handwritten Character Dataset
7.4.2 Experimental Setup
7.4.3 Hype-Parameters
7.4.3.1 English Model
7.4.3.2 Hindi Model
7.4.3.3 Bangla Model
7.4.3.4 Math Symbol Model
7.4.3.5 Combined Model
7.4.4 Results and Discussion
7.4.4.1 Performance of Uni-Language Models
7.4.4.2 Uni-Language Model on English Dataset
7.4.4.3 Uni-Language Model on Hindi Dataset
7.4.4.4 Uni-Language Model on Bangla Dataset
7.4.4.5 Uni-Language Model on Math Symbol Dataset
7.4.4.6 Performance of Multi-Lingual Model on Combined Dataset
7.5 Conclusion
References
8. Disease Detection Platform Using Image Processing Through OpenCV
8.1 Introduction
8.1.1 Image Processing
8.2 Problem Statement. 8.2.1 Cataract
8.2.1.1 Causes
8.2.1.2 Types of Cataracts
8.2.1.3 Cataract Detection
8.2.1.4 Treatment
8.2.1.5 Prevention
8.2.1.6 Methodology
8.2.1.6.1 Pre-Processing
8.2.1.6.2 Feature Extraction
8.2.1.6.3 Area Extraction
8.2.1.6.4 Decision Making
8.2.2 Eye Cancer
8.2.2.1 Symptoms
8.2.2.2 Causes of Retinoblastoma
8.2.2.3 Phases
8.2.2.4 Spreading of Cancer
8.2.2.5 Diagnosis
8.2.2.6 Treatment
8.2.2.6.1 Various Treatment Techniques
8.2.2.7 Methodology
8.2.2.7.1 Pre-Processing
8.2.2.7.2 Morphological Transformations
8.2.2.7.3 Segmenting Tumor
8.2.3 Skin Cancer (Melanoma)
8.2.3.1 Signs and Symptoms
8.2.3.2 Stages
8.2.3.3 Causes of Melanoma
8.2.3.4 Diagnosis
8.2.3.5 Treatment
8.2.3.6 Methodology
8.2.3.6.1 Pre-Processing
8.2.3.6.2 Analyzing the Image
8.2.3.6.3 Identification and Classification
8.2.3.6.3.1 ABCD Rule
8.2.3.7 Asymmetry
8.2.3.8 Border
8.2.3.9 Color
8.2.3.10 Diameter Detection
8.2.3.11 Calculating TDS (Total Dermoscopy Score)
8.2.3.11.1 TDS Formula
8.3 Conclusion
8.4 Summary
References
9. Computer-Aided Diagnosis of Liver Fibrosis in Hepatitis Patients Using Convolutional Neural Network
9.1 Introduction
9.2 Overview of System
9.3 Methodology
9.3.1 Dataset
9.3.2 Pre-Processing
9.3.3 Feature Extraction
9.3.4 Feature Selection and Normalization
9.3.5 Classification Model
9.4 Performance and Analysis
9.5 Experimental Results
9.6 Conclusion and Future Scope
References
10. Lung Cancer Prediction in Deep Learning Perspective
10.1 Introduction
10.2 Machine Learning and Its Application. 10.2.1 Machine Learning
10.2.2 Different Machine Learning Techniques
10.2.2.1 Decision Tree
10.2.2.2 Support Vector Machine
10.2.2.3 Random Forest
10.2.2.4 K-Means Clustering
10.3 Related Work
10.4 Why Deep Learning on Top of Machine Learning?
10.4.1 Deep Neural Network
10.4.2 Deep Belief Network
10.4.3 Convolutio nal Neural Network
10.5 How is Deep Learning Used for Prediction of Lungs Cancer? 10.5.1 Proposed Architecture
10.5.1.1 Pre-Processing Block
10.5.1.2 Segmentation
10.5.1.3 Classification
10.6 Conclusion
References
11. Lesion Detection and Classification for Breast Cancer Diagnosis Based on Deep CNNs from Digital Mammographic Data
11.1 Introduction
11.2 Background. 11.2.1 Methods of Diagnosis of Breast Cancer
11.2.2 Types of Breast Cancer
11.2.3 Breast Cancer Treatment Options
11.2.4 Limitations and Risks of Diagnosis and Treatment Options. 11.2.4.1 Limitation of Diagnosis Methods
11.2.4.2 Limitations of Treatment Plans
11.2.5 Deep Learning Methods for Medical Image Analysis: Tumo r Classification
11.3 Methods. 11.3.1 Digital Repositories
11.3.1.1 DDSM Database
11.3.1.2 AMDI Database
11.3.1.3 IRMA Database
11.3.1.4 BreakHis Database
11.3.1.5 MIAS Database
11.3.2 Data Pre-Processing
11.3.2.1 Advantages of Pre-Processing Images
11.3.3 Convolutional Neural Networks (CNNs)
11.3.3.1 Architecture of CNN
11.3.4 Hyper-Parameters
11.3.4.1 Number of Hidden Layers
11.3.4.2 Dropout Rate
11.3.4.3 Activation Function
11.3.4.4 Learning Rate
11.3.4.5 Number of Epochs
11.3.4.6 Batch Size
11.3.5 Techniques to Improve CNN Performance. 11.3.5.1 Hyper-Parameter Tuning
11.3.5.2 Augmenting Images
11.3.5.3 Managing Over-Fitting and Under-Fitting
11.4 Application of Deep CNN for Mammography. 11.4.1 Lesion Detection and Localization
11.4.2 Lesion Classification
11.5 System Model and Results. 11.5.1 System Model
11.5.2 System Flowchart. 11.5.2.1 MIAS Database
11.5.2.2 Unannotated Images
11.5.3 Results. 11.5.3.1 Distribution and Processing of Dataset. 11.5.3.1.1 MIAS Database
11.5.3.1.2 Unannotated Labeled Images
11.5.3.2 Training of the Model
11.5.3.3 Prediction of Unannotated Images
11.6 Research Challenges and Discussion on Future Directions
11.7 Conclusion
References
12. Health Prediction Analytics Using Deep Learning Methods and Applications
12.1 Introduction
12.2 Background
12.3 Predictive Analytics
12.4 Deep Learning Predictive Analysis Applications. 12.4.1 Deep Learning Application Model to Predict COVID-19 Infection
12.4.2 Deep Transfer Learning for Mitigating the COVID-19 Pandemic
12.4.3 Health Status Prediction for the Elderly Based on Machine Learning
12.4.4 Deep Learning in Machine Health Monitoring
12.5 Discussion
12.6 Conclusion
References
13. Ambient-Assisted Living of Disabled Elderly in an Intelligent Home Using Behavior Prediction—A Reliable Deep Learning Prediction System
13.1 Introduction
13.2 Activities of Daily Living and Behavior Analysis
13.3 Intelligent Home Architecture
13.4 Methodology. 13.4.1 Record the Behaviors Using Sensor Data
13.4.2 Classify Discrete Events and Relate the Events Using Data Analysis Algorithms
13.4.3 Construct Behavior Dictionaries for Flexible Event Intervals Using Deep Learning Concepts
13.4.4 Use the Dictionary in Modeling the Behavior Patterns Through Prediction Techniques
13.4.5 Detection of Deviations From Expected Behaviors Aiding the Automated Elderly Monitoring Based on Decision Support Algorithm Systems
13.5 Senior Analytics Care Model
13.6 Results and Discussions
13.7 Conclusion
Nomenclature
References
14. Early Diagnosis Tool for Alzheimer’s Disease Using 3D Slicer
14.1 Introduction
14.2 Related Work
14.3 Existing System
14.4 Proposed System
14.4.1 Usage of 3D Slicer
14.5 Results and Discussion
14.6 Conclusion
References
15. Deep Learning for Medical Healthcare: Issues, Challenges, and Opportunities
15.1 Introduction
15.2 Related Work
15.3 Development of Personalized Medicine Using Deep Learning: A New Revolution in Healthcare Industry
15.3.1 Deep Feedforward Neural Network (DFF)
15.3.2 Convolutional Neural Network
15.3.3 Recurrent Neural Network (RNN)
15.3.4 Long/Short-Term Memory (LSTM)
15.3.5 Deep Belief Network (DBN)
15.3.6 Autoencoder (AE)
15.4 Deep Learning Applications in Precision Medicine
15.4.1 Discovery of Biomarker and Classification of Patient
15.4.2 Medical Imaging
15.5 Deep Learning for Medical Imaging
15.5.1 Medical Image Detection
15.5.1.1 Pathology Detection
15.5.1.2 Detection of Image Plane
15.5.1.3 Anatomical Landmark Localization
15.5.2 Medical Image Segmentation
15.5.2.1 Supervised Algorithms
15.5.2.2 Semi-Supervised Algorithms
15.5.3 Medical Image Enhancement
15.5.3.1 Two-Dimensional Super-Resolution Techniques
15.5.3.2 Three-Dimensional Super-Resolution Techniques
15.6 Drug Discovery and Development: A Promise Fulfilled by Deep Learning Technology
15.6.1 Prediction of Drug Properties
15.6.2 Prediction of Drug-Target Interaction
15.7 Application Areas of Deep Learning in Healthcare
15.7.1 Medical Chatbots
15.7.2 Smart Health Records
15.7.3 Cancer Diagnosis
15.8 Privacy Issues Arising With the Usage of Deep Learning in Healthcare
15.8.1 Private Data
15.8.2 Privacy Attacks
15.8.2.1 Evasion Attack
15.8.2.2 White-Box Attack
15.8.2.3 Black-Box Attack
15.8.2.4 Poisoning Attack
15.8.3 Privacy-Preserving Techniques
15.8.3.1 Differential Privacy With Deep Learning
15.8.3.2 Homomorphic Encryption (HE) on Deep Learning
15.8.3.3 Secure Multiparty Computation on Deep Learning
15.9 Challenges and Opportunities in Healthcare Using Deep Learning
15.10 Conclusion and Future Scope
References
16. A Perspective Analysis of Regularization and Optimization Techniques in Machine Learning
16.1 Introduction
16.1.1 Data Formats
16.1.1.1 Structured Data
16.1.1.2 Unstructured Data
16.1.1.3 Semi-Structured Data
16.1.2 Beginning With Learning Machines
16.1.2.1 Perception
16.1.2.2 Artificial Neural Network
16.1.2.3 Deep Networks and Learning
16.1.2.4 Model Selection, Over-Fitting, and Under-Fitting
16.2 Regularization in Machine Learning
16.2.1 Hamadard Conditions
16.2.2 Tikhonov Generalized Regularization
16.2.3 Ridge Regression
16.2.4 Lasso—L1 Regularization
16.2.5 Dropout as Regularization Feature
16.2.6 Augmenting Dataset
16.2.7 Early Stopping Criteria
16.3 Convexity Principles
16.3.1 Convex Sets
16.3.1.1 Affine Set and Convex Functions3
16.3.1.2 Properties of Convex Functions
16.3.1.2.1 Constraint Handling
16.3.1.2.2 No Local Minima
16.3.1.2.3 Lagrange Function
16.3.2 Optimization and Role of Optimizer in ML
16.3.2.1 Gradients-Descent Optimization Methods
16.3.2.2 Non-Convexity of Cost Functions
16.3.2.3 Basic Maths of SGD
16.3.2.4 Saddle Points
16.3.2.5 Gradient Pointing in the Wrong Direction
16.3.2.6 Momentum-Based Optimization
16.4 Conclusion and Discussion
References
17. Deep Learning-Based Prediction Techniques for Medical Care: Opportunities and Challenges
17.1 Introduction
17.2 Machine Learning and Deep Learning Framework
17.2.1 Supervised Learning
17.2.2 Unsupervised Learning
17.2.3 Reinforcement Learning
17.2.4 Deep Learning
17.3 Challenges and Opportunities
17.3.1 Literature Review
17.4 Clinical Databases—Electronic Health Records
17.5 Data Analytics Models—Classifiers and Clusters
17.5.1 Criteria for Classification
17.5.1.1 Probabilistic Classifier
17.5.1.2 Support Vector Machines (SVMs)
17.5.1.3 K-Nearest Neighbors
17.5.2 Criteria for Clustering
17.5.2.1 K-Means Clustering
17.5.2.2 Mean Shift Clustering
17.6 Deep Learning Approaches and Association Predictions
17.6.1 G-HR: Gene Signature–Based HRF Cluster
17.6.1.1 G-HR Procedure
17.6.2 Deep Learning Approach and Association Predictions
17.6.2.1 Deep Learning Approach
17.6.2.2 Intelligent Human Disease-Gene Association Prediction Technique (IHDGAP)
17.6.2.3 Convolution Neural Network
17.6.2.4 Disease Semantic Similarity
17.6.2.5 Computation of Scoring Matrix
17.6.3 Identified Problem
17.6.4 Deep Learning–Based Human Diseases Pattern Prediction Technique for High-Dimensional Human Diseases Datasets (ECNN-HDPT)
17.6.5 Performance Analysis
17.7 Conclusion
17.8 Applications
References
18. Machine Learning and Deep Learning: Open Issues and Future Research Directions for the Next 10 Years
18.1 Introduction
18.1.1 Comparison Among Data Mining, Machine Learning, and Deep Learning
18.1.2 Machine Learning
18.1.2.1 Importance of Machine Learning in Present Business Scenario
18.1.2.2 Applications of Machine Learning
18.1.2.3 Machine Learning Methods Used in Current Era
18.1.3 Deep Learning
18.1.3.1 Applications of Deep Learning
18.1.3.2 Deep Learning Techniques/Methods Used in Current Era
18.2 Evolution of Machine Learning and Deep Learning
18.3 The Forefront of Machine Learning Technology
18.3.1 Deep Learning
18.3.2 Reinforcement Learning
18.3.3 Transfer Learning
18.3.4 Adversarial Learning
18.3.5 Dual Learning
18.3.6 Distributed Machine Learning
18.3.7 Meta Learning
18.4 The Challenges Facing Machine Learning and Deep Learning
18.4.1 Explainable Machine Learning
18.4.2 Correlation and Causation
18.4.3 Machine Understands the Known and is Aware of the Unknown
18.4.4 People-Centric Machine Learning Evolution
18.4.5 Explainability: Stems From Practical Needs and Evolves Constantly
18.5 Possibilities With Machine Learning and Deep Learning
18.5.1 Possibilities With Machine Learning
18.5.1.1 Lightweight Machine Learning and Edge Computing
18.5.1.2 Quantum Machine Learning
18.5.1.3 Quantum Machine Learning Algorithms Based on Linear Algebra
18.5.1.4 Quantum Reinforcement Learning
18.5.1.5 Simple and Elegant Natural Laws
18.5.1.6 Improvisational Learning
18.5.1.7 Social Machine Learning
18.5.2 Possibilities With Deep Learning. 18.5.2.1 Quantum Deep Learning
18.6 Potential Limitations of Machine Learning and Deep Learning
18.6.1 Machine Learning
18.6.2 Deep Learning
18.7 Conclusion
Acknowledgement
Contribution/Disclosure
References
Index
WILEY END USER LICENSE AGREEMENT
