This book takes an interdisciplinary approach by covering topics on health care and artificial intelligence. Data sets related to biomedical signals (ECG, EEG, EMG) and images (X-rays, MRI, CT) are explored, analyzed, and processed through different computation intelligence methods. Applications of computational intelligence techniques like artificial and deep neural networks, swarm optimization, expert systems, decision support systems, clustering, and classification techniques on medial datasets are explained. Survey of medical signals, medial images, and computation intelligence methods are also provided in this book.
Key Features
- Covers computational Intelligence techniques like artificial neural networks, deep neural networks, and optimization algorithms for Healthcare systems
- Provides easy understanding for concepts like signal and image filtering techniques
- Includes discussion over data preprocessing and classification problems
- Details studies with medical signal (ECG, EEG, EMG) and image (X-ray, FMRI, CT) datasets
- Describes evolution parameters such as accuracy, precision, and recall etc.
This book is aimed at researchers and graduate students in medical signal and image processing, machine and deep learning, and healthcare technologies.
Author(s): Anil Kumar, Mitul Kumar Ahirwal, Narendra D. Londhe
Publisher: CRC Press
Year: 2022
Language: English
Pages: 331
City: Boca Raton
Cover
Half Title
Title Page
Copyright Page
Dedication
Contents
Foreword
Preface
Acknowledgement
Editors Biographies
Contributors
1. A Survey of Machine Learning in Healthcare
1.1 Introduction
1.2 Artificial Intelligence
1.2.1 Machine Learning
1.2.1.1 Steps in Developing an ML System
1.2.1.2 Types of Machine Learning
1.2.2 Deep Learning
1.2.3 The Major Types of DL
1.3 Applications of ML in Healthcare
1.3.1 Cardiovascular Diseases
1.3.2 Medical Imaging
1.3.3 Drug Discovery/Manufacturing
1.3.4 Electronic Health Records
1.3.5 Clinical Decision Support System
1.3.6 Surgical Robotics
1.3.7 Precision Medicine
1.3.8 Population Health Management
1.3.9 mHealth and Smart Devices
1.3.10 AI for Tackling Pandemic
1.4 ML Use Cases in Healthcare
1.5 Limitations and Challenges in Adoption of AI in Healthcare
1.6 Conclusion
Acknowledgements
References
2. A Review on Biomedical Signals with Fundamentals of Digital Signal Processing
2.1 Introduction
2.2 Biomedical Signals
2.2.1 Electrocardiogram (ECG) Signal
2.2.1.1 ECG Terminology and Recording
2.2.1.2 Different Types of Recording Techniques
2.2.1.3 ECG Processing
2.2.1.4 Common Problems
2.2.1.5 Common ECG Applications
2.2.1.5.1 Review of Recent and New Applications of ECG
2.2.2 Electroencephalogram (EEG) Signal
2.2.2.1 Basic Terminology and Recording
2.2.2.2 Types of EEG Signals
2.2.2.3 EEG Processing
2.2.2.4 Common Problems
2.2.2.5 EEG Applications
2.2.3 Electromyography (EMG)
2.2.3.1 EMG Signal Recording
2.2.3.2 EMG Signal Processing
2.2.3.3 Common Problems
2.2.3.4 EMG Applications
2.2.4 Electro-Oculogram (EOG)
2.2.4.1 EOG Signal Recording
2.2.4.2 EOG Processing
2.2.4.3 Common Problems
2.2.4.4 Applications of EOG Signal
References
3. Images in Radiology: Concepts of Image Acquisition and the Nature of Images
3.1 Introduction
3.2 Radiography
3.3 Ultrasonography
3.4 Computed Tomography
3.4.1 Noncontrast and Contrast-Enhanced CT
3.4.2 High-Resolution CT
3.4.3 CT Angiography/Venography
3.4.4 Cardiac CT/Coronary CT Angiography
3.4.5 CT Perfusion
3.5 Magnetic Resonance Imaging (MRI)
3.5.1 Contrast-Enhanced MRI
3.5.2 MRI Perfusion
3.5.3 MR Spectroscopy
3.5.4 Diffusion-Weighted and Diffusion Tensor MRI
3.5.5 Cardiac MRI
3.6 Digital Subtraction Angiography
3.7 Conclusion
References
4. Fundamentals of Artificial Intelligence and Computational Intelligence Techniques with Their Applications in Healthcare Systems
4.1 Introduction
4.2 Healthcare Data
4.2.1 Clinical Data
4.2.1.1 Image Data
4.2.1.2 Signal Data
4.2.2 Omics Data
4.2.2.1 Genomic Data
4.2.2.2 Transcriptomic Data
4.2.2.3 Proteomic Data
4.3 Diseases Targeted by AI
4.4 Computational Intelligence Techniques and Their Applications
4.4.1 Artificial Neural Network
4.4.2 Evolutionary Computation
4.4.3 Fuzzy Systems
4.5 No-Code AI Tools
4.6 Performance Parameters
4.7 Challenges
4.8 Conclusion
References
5. Machine Learning Approach with Data Normalization Technique for Early Stage Detection of Hypothyroidism
5.1 Introduction
5.1.1 Related Work
5.2 Material and Methods
5.2.1 System Framework
5.2.2 Hypothyroid Disease (HD) Dataset
5.2.3 Min-Max Scaler Technique
5.2.4 ML Classifiers
5.2.5 Performance Measures
5.3 Results
5.4 Discussions
5.5 Conclusion
References
6. GPU-based Medical Image Segmentation: Brain MRI Analysis Using 3D Slicer
6.1 Introduction
6.2 Related Works
6.3 Image Segmentation Techniques
6.3.1 Seeded Region Growing
6.3.2 Watershed
6.3.3 Level Set Approaches/Methods
6.3.4 Active Contours
6.4 GPU Segmentation Demonstration: NVIDIA AIAA
6.5 Conclusion
References
7. Preliminary Study of Retinal Lesions Classification on Retinal Fundus Images for the Diagnosis of Retinal Diseases
7.1 Introduction
7.2 Retinal Imaging Modalities
7.3 Fundus Imaging
7.3.1 Fundus Image Formation
7.4 Eye Anatomy and Retinal Diseases
7.4.1 Normal Retina
7.4.2 Retinal Lesions Associated with Various Retinal Diseases
7.4.2.1 Dark Lesions
7.4.2.2 Microaneurysms
7.4.2.3 Haemorrhages
7.4.2.4 Bright Lesions
7.4.2.5 Exudates
7.4.2.6 Cotton Wool Spots
7.5 Need and Challenges in Computer Aided Retinal Diseases Detection Method
7.6 Need and Challenges in Retinal Image Enhancement
7.7 Need and Challenges in Characterization of Anatomical Structures and Lesions
7.7.1 Segmentation of Retinal Blood Vasculature
7.7.2 Detection of Optic Disk
7.7.3 Segmentation of Retinal Lesions
7.8 Need and Challenges in Computer Aided Classification and Grading Method
7.9 Conclusion
References
8. Automatic Screening of COVID-19 Based on CT Scan Images Through Extreme Gradient Boosting
8.1 Introduction
8.2 Methodology
8.2.1 Traditional Methods
8.2.2 Proposed Method
8.2.2.1 Histogram of Oriented Gradients (HOG) Features
8.2.2.2 Local Binary Pattern (LBP) Features
8.2.2.3 KAZE Features
8.2.2.4 SIFT Features
8.2.2.5 Speeded Up Robust Features (SURF)
8.2.2.6 Normalization
8.2.2.7 Principal Component Analysis (PCA)
8.2.3 Datasets Used
8.2.4 Experiments Performed
8.2.4.1 Adaboost
8.2.4.2 Bagging
8.2.4.3 k-Nearest Neighbor
8.2.4.4 Naïve Bayesian Classification
8.2.4.5 Random Forest
8.2.4.6 Support Vector Machine (SVM)
8.2.4.7 Extreme Gradient Boosting (XGB)
8.3 Results
8.3.1 Comparative Study
8.4 Conclusion and Future Works
References
9. Investigations on Convolutional Neural Network in Classification of the Chest X-Ray Images for COVID-19 and Pneumonia
9.1 Introduction
9.2 Dataset and Processing
9.3 Methodology
9.4 Results
9.5 Conclusion
References
10. Improving the Detection of Abdominal and Mediastinal Lymph Nodes in CT Images Using Attention U-Net Based Deep Learning Model
10.1 Introduction
10.2 Methodology
10.2.1 Dataset Details
10.3 Training Configuration and Experimental Setup
10.4 Results
10.5 Discussions
10.6 Conclusion and Future Work
10.7 Future Work
References
11. Swarm Optimized Hybrid Layer Decomposition and Reconstruction Model for Multi-Modal Neurological Image Fusion
11.1 Introduction
11.2 Methodology
11.2.1 Hybrid Layer Decomposition
11.2.2 Whale Optimization Algorithm
11.2.3 Proposed Method
11.2.4 Dataset
11.2.5 Experiments Performed
11.2.6 Performance Metrics
11.3 Results and Discussions
11.3.1 Performance Comparison of Source and Fused Images
11.3.2 Performance Comparison for Anatomical-Anatomical Image Fusion
11.3.3 Performance Comparison for Anatomical-Functional Image Fusion
11.4 Conclusion
References
12. Hybrid Seeker Optimization Algorithm-based Accurate Image Clustering for Automatic Psoriasis Lesion Detection
12.1 Introduction
12.2 Methodology
12.2.1 Database
12.2.2 Seeker Optimization Algorithm
12.2.3 Hybrid Seeker Optimization Algorithm (HSOA)
12.2.4 Post Processing
12.3 Results
12.3.1 Experimental Results
12.4 Discussions
12.5 Conclusion
Acknowledgment
References
13. A COVID-19 Tracker for Medical Front-Liners
13.1 Introduction
13.2 Methodology
13.2.1 Background
13.2.2 Proposed System
13.2.3 System Requirements
13.2.4 Technical Details
13.3 Modules
13.3.1 Data Collection and Pre-processing
13.3.2 Geocoding and Geotagging Patients
13.3.3 Assigning Health Center and Field Worker
13.3.4 Hospital Management System
13.3.5 Ambulance Management System
13.3.6 Report Generation
13.3.6.1 Patient Discharge Report
13.3.6.2 Custom Data Reports
13.3.7 Analytics
13.4 Mathematical Model
13.5 Results
13.6 Applications
13.7 Conclusion
13.8 Future Work
References
14. Implementation of One Dimensional Convolutional Neural Network for ECG Classification on Python Platform
14.1 Introduction
14.2 Overview of 1D-CNN
14.2.1 Convolutional Block
14.2.2 Output Block
14.2.3 Training of Model
14.2.4 Python Platform
14.3 Database 01
14.4 Implementation of 1D-CNN Model 1 for Binary Classification
14.5 Model Evaluation (Results)
14.6 Database 02
14.7 Implementation of 1D-CNN Model 2 for Multi Class Classification
14.8 Model Evaluation for Multi-Class Classification (Results)
14.9 Conclusion
References
15. Pneumonia Detection from X-Ray Images by Two Dimensional Convolutional Neural Network on Python Platform
15.1 Introduction
15.1.1 Architecture Overview of Two-Dimensional Convolutional Neural Network (2DCNN)
15.2 Dataset
15.3 Implemented Models of CNN
15.3.1 Model 1 for Binary Classification of X-Ray Images
15.3.2 Model 2 for Binary Classification of X-Ray Images
15.4 Model Evaluation
15.5 Results
15.5.1 Performance Evaluation of Model 1
15.5.2 Performance Evaluation of Model 2
15.6 Conclusion
References
Index
