product iamge

Computerized Systems for Diagnosis and Treatment of COVID-19

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Download
Search on Amazon

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

This book describes the application of signal and image processing technologies, artificial intelligence, and machine learning techniques to support Covid-19 diagnosis and treatment. The book focuses on two main applications: critical diagnosis requiring high precision and speed, and treatment of symptoms, including those affecting the cardiovascular and neurological systems.

The areas discussed in this book range from signal processing, time series analysis, and image segmentation to detection and classification. Technical approaches include deep learning, transfer learning, transformers, AutoML, and other machine learning techniques that can be considered not only for Covid-19 issues but also for different medical applications, with slight adjustments to the problem under study.

The Covid-19 pandemic has impacted the entire world and changed how societies and individuals interact. Due to the high infection and mortality rates, and the multiple consequences of the virus infection in the human body, the challenges were vast and enormous. These necessitated the integration of different disciplines to address the problems. As a global response, researchers across academia and industry made several developments to provide computational solutions to support epidemiologic, managerial, and health/medical decisions. To that end, this book provides state-of-the-art information on the most advanced solutions.

Author(s): Joao Alexandre Lobo Marques, Simon James Fong
Publisher: Springer
Year: 2023

Language: English
Pages: 209
City: Cham

Contents
Technology Developments to Face the COVID-19 Pandemic: Advances, Challenges, and Trends
1 Introduction
2 Technology and Scientific Advances
2.1 Development of New Vaccines
2.2 New Medical Devices
2.3 Computerized Systems
3 Challenges for Technology Adoption and Maturity
3.1 AI Systems and Technology Readiness Challenges
4 Current Trends
4.1 Precision Medicine for COVID-19 and Long COVID Patients
5 What to Expect from This Book
References
Lung Segmentation of Chest X-Rays Using Unet Convolutional Networks
1 Introduction
2 Materials and Methods
2.1 U-Net Convolutional Networks
2.2 Proposed System
2.3 Evaluation Metrics
2.4 Dataset
2.5 Experimental Design
3 Results and Discussions
3.1 Clinical Examples
4 Conclusions
References
Segmentation of CT-Scan Images Using UNet Network for Patients Diagnosed with COVID-19
1 Introduction
2 Background
2.1 Lung CT Scans Characteristics and COVID-19 Diagnosis
2.2 COVID-19 CT Segmentation
2.3 U-Net Network
2.4 Dataset
2.5 Evaluation Criteria
3 Experimental Results and Discussion
4 Conclusion
References
Covid-19 Detection Based on Chest X-Ray Images Using Multiple Transfer Learning CNN Models
1 Introduction
2 Transfer Learning
3 Experimental Methodology
3.1 Proposed Experiment
3.2 Performance Evaluation
4 Experiments
4.1 Resnet50
4.2 VGG-16
4.3 Squeezenet
4.4 Mobilenet
4.5 Densenet-201
4.6 Shufflenet
4.7 Efficientnet
4.8 Ghostnet
5 Consolidated Results
6 Conclusion
References
X-Ray Machine Learning Classification with VGG-16 for Feature Extraction
1 Introduction
2 Experimental Model
2.1 Machine Learning for Biomedical Imaging
2.2 Proposed Methodology
3 Experimental Results
3.1 Nearest Centroid (NC)
3.2 k-Nearest Neighbors (kNN)
3.3 Support Vector Machines (SVM)
3.4 Random Forest (RF)
3.5 Histogram Gradient Boosting (HGB)
3.6 Consolidated Results
4 Conclusions
References
Classification of COVID-19 CT Scans Using Convolutional Neural Networks and Transformers
1 Introduction
2 Concepts and Technical Background
2.1 Transformers
2.2 Vanilla Transformer
2.3 Transformer Architecture
2.4 Covid-19 Detection Using CT Scans of the Chest
2.5 Covid-19 Detection Using Transformers
2.6 Visual Transformers
2.7 Transfer Learning
2.8 Evaluation Criteria
3 Experimental Results and Discussion
4 Conclusion
References
COVID-19 Classification Using CT Scans with Convolutional Neural Networks
1 Introduction
2 Related Works
3 Materials and Methods
3.1 Dataset
3.2 CNN Models for COVID-19 Classification
3.3 Evaluation Metrics
3.4 Explainable AI (XAI) Techniques
3.5 XAI Implementation
4 Results
5 Conclusion
References
TPOT Automated Machine Learning Approach for Multiple Diagnostic Classification of Lung Radiography and Feature Extraction
1 Introduction
2 Technical Background
2.1 MobileNet
2.2 Automated Machine Learning—AutoML
2.3 Neural Architecture Search Problem
2.4 Bayesian Optimization
2.5 TPOT AutoML
3 Methodology
3.1 Database
3.2 Evaluation Criteria
4 Results
5 Conclusion
References
Evaluation of ECG Non-linear Features in Time-Frequency Domain for the Discrimination of COVID-19 Severity Stages
1 Introduction
2 ECG Collection
3 Patients' Selection
4 Methodology
4.1 Artifacts Removal
4.2 Signal Analysis and Feature Extraction
4.3 Feature Time-Series Data Vector Compression
4.4 Data Normalization
4.5 Statistical Analysis
5 Results
6 Discussion
7 Conclusion
References
Classification of Severity of COVID-19 Patients Based on the Heart Rate Variability
1 Introduction
2 Dataset
2.1 Dataset Creation
3 ECG Data Processing
3.1 ECG Acquisition
3.2 Preprocessing/Filtering Stage
3.3 QRS Detection
3.4 Heart Rate Variability Metrics
3.5 Compilation of HRV Metrics
4 Machine Learning Stage
4.1 Importance of Leave One Subject Out
4.2 Dataset Information and Data Correlation
4.3 Training Strategies and Their Results
4.4 General Comparison
4.5 Leave One Subject Out
4.6 K-Fold Training
5 Discussion
6 Conclusion
References
Exploratory Data Analysis on Clinical and Emotional Parameters of Pregnant Women with COVID-19 Symptoms
1 Introduction
2 Related Works
3 Materials and Methods
3.1 Study Design
3.2 Patients' Selection
3.3 COPE Survey
3.4 Groups of Study
3.5 Data and Sample Collection Procedures
3.6 Ethical Considerations
4 Exploratory Data Analysis—EDA
4.1 Dataset Characterization
4.2 Symptoms
4.3 Maternal Health Status
4.4 Birth Parameters
4.5 COPE Survey—Maternal Stress and Mental Health
5 Conclusion
References