Disruptive Trends in Computer Aided Diagnosis (Chapman & Hall/CRC Computational Intelligence and Its Applications)

Description

Disruptive Trends in Computer Aided Diagnosis collates novel techniques and methodologies in the domain of content based image classification and deep learning/machine learning techniques to design efficient computer aided diagnosis architecture. It is aimed to highlight new challenges and probable solutions in the domain of computer aided diagnosis to leverage balancing of sustainable ecology. The volume focuses on designing efficient algorithms for proposing CAD systems to mitigate the challenges of critical illnesses at an early stage. State-of-the-art novel methods are explored for envisaging automated diagnosis systems thereby overriding the limitations due to lack of training data, sample annotation, region of interest identification, proper segmentation and so on. The assorted techniques addresses the challenges encountered in existing systems thereby facilitating accurate patient healthcare and diagnosis. Features: An integrated interdisciplinary approach to address complex computer aided diagnosis problems and limitations. Elucidates a rich summary of the state-of-the-art tools and techniques related to automated detection and diagnosis of life threatening diseases including pandemics. Machine learning and deep learning methodologies on evolving accurate and precise early detection and medical diagnosis systems. Information presented in an accessible way for students, researchers and medical practitioners. The volume would come to the benefit of both post-graduate students and aspiring researchers in the field of medical informatics, computer science and electronics and communication engineering. In addition, the volume is also intended to serve as a guiding factor for the medical practitioners and radiologists in accurate diagnosis of diseases. Cover Half Title Series Information Title Page Copyright Page Dedication Table of Contents Figures Tables Editor Biographies Contributors Preface 1 Evolution of Computer Aided Diagnosis: The Inception and Progress 1.1 Introduction 1.2 Literature Survey 1.3 Data Preprocessing Illustration for Computer Aided Diagnosis 1.4 Future Scope 1.5 Conclusion References 2 Computer Aided Diagnosis for a Sustainable World 2.1 Introduction 2.1.1 Background and Evolution 2.1.2 Meaning and Significance 2.2 Challenges for Computer Aided Diagnosis 2.2.1 Data Acquisition and Its Assessment 2.2.2 Segmentation of Acquired Data 2.2.3 Feature Extraction / Selection 2.2.4 Classification of Data and Data Mining Approaches 2.2.5 Challenge of Big Data 2.2.6 Standardized Performance Assessment Approaches 2.2.7 Adoption of Computer Aided Diagnosis in Clinical Practice 2.3 Sustainability 2.3.1 Attainment of Sustainability 2.3.2 New Paradigm 2.3.2.1 Cohorting and Characterizing Disease 2.3.2.2 Full-Cycle Feedback and Training 2.3.2.3 Power of Real Time Clinical Data 2.3.2.4 Better Healthcare in Even Modest Means 2.4 Conclusion References 3 Applications of Computer Aided Diagnosis Techniques for a Sustainable World 3.1 Introduction 3.2 Computer Aided Diagnosis 3.3 Historical Background of Computer Aided Diagnosis 3.4 Applications of Computer Aided Diagnosis 3.5 Towards a Sustainable World 3.5.1 Environmental Sustainability 3.5.2 Social Sustainability 3.5.3 Economic Sustainability 3.6 Implications of Computer Aided Diagnosis 3.7 Limitations 3.8 Conclusion 3.9 The Road Ahead References 4 Applications of Generative Adversarial Network On Computer Aided Diagnosis 4.1 Introduction 4.2 Background 4.3 Computer Aided Detection and Research Progression 4.4 Implementation and Assessment of Clinical CAD 4.5 Application of Machine Learning and Deep Learning in Computer Aided Detection 4.5.1 Generative Adversarial Network – the State of the Art Architecture 4.5.2 Generative Adversarial Network – Evaluation Methodology 4.5.3 Case Study – Application of Generative Adversarial Network – CAD(x) Prediction of Congestive Heart Failure By GVR ... 4.5.3.1 Review of the Method 4.5.3.2 Review of Results 4.5.3.3 Conclusion 4.5.3.4 Inferences and Deduction for Patient Care 4.6 Computer Aided Diagnosis and Research Progression 4.6.1 Comparative Study of Generative Versus Discriminative Algorithms 4.6.1.1 Model Structures 4.6.1.2 Usage of Machine Learning and Deep Learning Algorithms in Computer Aided Diagnosis (Cad(x)) 4.6.1.3 Emergence of GAN and Its Applications 4.6.1.4 Usage of GAN in Computer Aided Diagnosis and the Stage of Maturity 4.7 Generative Adversarial Network and Its Contribution to Computer Aided Diagnosis 4.7.1 Discussion and Conclusion 4.8 Future Scope References 5 A Critical Review of Machine Learning Techniques for Diagnosing the Corona Virus Disease (COVID-19) 5.1 Introduction 5.2 Literature Review 5.3 Machine Learning Techniques for Diagnosis of Corona Virus Disease Through Medical Images 5.4 Discussion and Analysis 5.5 Conclusion References 6 Cardiac Health Assessment Using ANN in Diabetic Population 6.1 Introduction 6.2 Relevance of Early Diagnosis of Myocardial Ischemia 6.3 Materials and Methods 6.3.1 HRV Analysis Tool 6.4 Overview of HRV Analysis 6.5 Data Acquisition Protocol, Inclusion and Exclusion Criterion 6.6 Need of Classifier 6.7 Feature Set Design 6.8 ANN Classifier Design 6.9 Cluster Analysis 6.10 Results and Discussion 6.11 Scope and Limitations References 7 Efficient, Accurate and Early Detection of Myocardial Infarction Using Machine Learning 7.1 Introduction 7.1.1 Myocardial Infarction 7.1.2 Types of MI 7.1.2.1 STEMI (ST-Segment Elevation Myocardial Infarction) 7.1.2.2 NSTEMI (non-ST Segment Elevation Myocardial Infarction) 7.1.2.3 Angina 7.1.2.4 Demand Ischemia (DI) 7.1.2.5 Cardiac Arrest 7.2 Literature Review 7.2.1 Clinical Investigations 7.2.2 Healthcare and Artificial Intelligence 7.3 Research Gap 7.3.1 Research Objectives 7.4 Proposed Methods 7.4.1 Bucketization 7.4.2 Feature Selection Techniques 7.4.2.1 Filter Method 7.4.2.2 Wrapper Method 7.4.2.3 Embedded Method 7.4.3 Data Cleaning and Pruning Technique 7.4.4 Normalization 7.4.5 Machine Learning 7.5 Experimental Result With Existing Dataset 7.6 Implementation 7.6.1 Survey 7.6.2 Experimental Result 7.6.3 Enhanced Experimental Result 7.7 Conclusion and Future Scope 7.7.1 Future Scope References 8 Diagnostics and Decision Support for Cardiovascular System: A Tool Based On PPG Signature 8.1 Introduction and Background 8.2 PPG Data Acquisition System 8.3 Data Preprocessing 8.4 Beat Extraction 8.5 Fiducial Point Determination and Estimation of Clinical Parameters 8.6 Estimation of HRV Parameters 8.6.1 Estimation of Time Domain HRV Parameters Using PPG Signal 8.6.2 Estimation of Non-Linear HRV Parameter Using PPG Signal 8.7 Results and Discussions 8.8 Conclusion Acknowledgments References 9 ARIMA Prediction Model Based Forecasting for COVID-19 Infected and Recovered Cases 9.1 Introduction 9.2 Literature Review 9.3 Proposed Method 9.3.1 Data Collection 9.3.2 Auto Regressive Integrated Moving Average 9.4 Experimental Results and Discussion 9.5 Conclusion References 10 Conclusion References Index