Applied Smart Health Care Informatics

Dr. Sourav De, Associate Professor, Department of Computer Science and Engineering, Cooch Behar Government Engineering College, India. Dr. Rik Das, Assistant Professor, Department of Information Technology, Xavier Institute of Social Service, India. Dr. Siddhartha Bhattacharyya, Principal, Rajnagar Mahavidyalaya, India. Dr. Ujjwal Maulik, Professor, Department of Computer Science and Engineering, Jadavpur University, India.

• Preface xiiiAbout the Editors xixList of Contributors xxv1 An Overview of Applied Smart Health Care Informatics in the Context of Computational Intelligence 1Sourav De and Rik Das1.1 Introduction 11.2 Big Data Analytics in Healthcare 21.3 AI in Healthcare 31.4 Cloud Computing in Healthcare 41.5 IoT in Healthcare 41.6 Conclusion 5References 52 A Review on Deep Learning Method for Lung Cancer Stage Classification Using PET-CT 9Kaushik Pratim Das, Chandra J, and Dr Nachamai M2.1 Introduction 92.1.1 Scope of the Research 102.1.2 TNM Staging 112.1.2.1 TNM Descriptors for Staging per IASLC Guidelines 112.1.2.2 PET-CT Scan in Lung Cancer Imaging 122.2 Related Works 122.2.1 Artificial Intelligence in Medical Imaging 142.2.2 Classification for Medical Imaging 142.2.2.1 Deep Learning 152.2.2.2 Image Classification Using Deep-learning Techniques 152.3 Methods 152.3.1 Transfer Learning 152.3.2 AlexNet 162.3.3 AlexNet Architecture 162.3.4 Experimental Setup 172.3.4.1 Image Processing 182.3.4.2 Data Augmentation 192.3.4.3 Training and Validation 192.4 Results and Discussion 192.4.1 Primary Tumor (T) 192.4.2 Metastasis (M) 212.4.3 Lymph Node (N) 212.4.4 Classification Accuracy of AlexNet 242.4.5 Comparative Analysis 252.4.6 Limitations 262.5 Conclusion 26References 273 Formal Methods for the Security of Medical Devices 31Srinivas Pinisetty, Nathan Allen, Hammond Pearce, Mark Trew, Manoj Singh Gaur, and Partha Roop3.1 Introduction 313.1.1 Pacemaker Security 333.1.2 Overview 343.2 Background: Cardiac Pacemakers 343.2.1 Pacemakers 353.2.1.1 Operation of a DDD Mode Pacemaker 363.2.2 The Cardiac System 373.2.2.1 Electrograms and Electrocardiograms 383.3 State of the Art, Formal Verification Techniques 393.3.1 Formal Verification Techniques 403.3.1.1 Static Verification Techniques 413.3.1.2 Dynamic Verification Techniques 423.3.2 Runtime Verification 433.3.2.1 A Brief Overview of Some Runtime Verification Frameworks 443.3.3 Correcting Execution of a System at Runtime (Runtime Enforcement) 453.3.3.1 Runtime Enforcement of Untimed Properties 463.3.3.2 Runtime Enforcement Approaches for Timed Properties 463.4 Formal Runtime-Based Approaches for Medical Device Security 473.4.1 Overview of the Approach 473.4.2 Mapping EGM Properties to ECG Properties 483.4.3 Security of Pacemakers Using Runtime Verification 493.4.3.1 Timed Words, Timed Languages, and Defining Timed Properties 503.4.3.2 Runtime Verification Monitor 513.4.3.3 Architecture of the Monitoring System 533.4.3.4 Implementation of the ECG Processing and RV Monitor Modules 533.4.3.5 Summary of Experiments and Results 543.4.4 Securing Pacemakers with Runtime Enforcement Hardware 543.4.4.1 Preliminaries: Words, Languages, and Defining Properties as DTA 553.4.4.2 Runtime Enforcement Monitor 563.4.4.3 Verification of the Enforcer Hardware 583.4.4.4 How Does the Enforcer Prevent Security Attacks? 583.4.4.5 Summary of Experiments and Results 593.5 Summary 59References 604 Integrating Two Deep Learning Models to Identify Gene Signatures in Head and Neck Cancer from  Multi-Omics Data 67Suparna Saha, Sumanta Ray, and Sanghamitra Bandyopadhyay4.1 Introduction 674.2 Related Work 684.3 Materials and Methods 704.3.1 A Brief Introduction of the Capsule Network 704.3.2 An Introduction to Autoencoders 714.4 Results 724.4.1 Data Set Details 724.4.1.1 Gene Expression Data (Illumina Hiseq) 724.4.1.2 Human Methylation 450K 734.4.2 Architecture of Autoencoder Model 734.4.3 Architecture of the Proposed Capsule Network Model 744.4.4 Validation of Two Deep Learning Models 754.4.5 Gene Signatures from Primary Capsules 764.5 Discussion 77Acknowledgments 78References 795 A Review of Computational Learning and IoT Applications to High-Throughput Array-Based Sequencing and Medical Imaging Data in Drug Discovery and Other Health Care Systems 83Soham Choudhuri, Saurav Mallik, Bhaswar Ghosh, Tapas Si, Tapas Bhadra, Ujjwal Maulik, and Aimin Li5.1 Introduction 835.2 Biological Terms 845.3 Single-Cell Sequencing (scRNA-seq) Data 865.3.1 Computational Methods for Interpreting scRNA-seq Data 865.3.1.1 Visualizing and Clustering Cells 865.3.1.2 Inference and Branching Analysis of Cellular Trajectory 865.3.1.3 Identifying Highly Variable Genes 865.3.1.4 Identifying Marker and Differentially Expressed Genes 905.4 Methods of Multi-Omic Data Integration 905.4.1 Unsupervised Data Integration Methods 915.4.1.1 Matrix Factorization Methods 915.4.1.2 Bayesian Methods 915.4.1.3 Network-Based Methods 945.4.1.4 Multi-Step Analysis and Multiple Kernel Learning 945.4.2 Supervised Data Integration 955.4.2.1 Network-Based Methods 955.4.2.2 Multiple Kernel Learning 955.4.2.3 Multi-Step Analysis 955.4.3 Semi-Supervised Data Integration 955.4.3.1 GeneticInterPred 975.5 AI Drug Discovery 975.5.1 AI Primary Drug Screening 975.5.1.1 Cell Sorting and Classification with Image Analysis 975.5.2 AI Secondary Drug Screening 995.5.2.1 Physical Properties Predictions 995.5.2.2 Predictions of Bio-Activity 995.5.2.3 Prediction of Toxicity 995.5.3 AI in Drug Design 995.5.3.1 Prediction of Target Protein 3D Structures 995.5.3.2 Predicting Drug-Protein Interactions 1005.5.4 Planning Chemical Synthesis with AI 1005.5.4.1 Retro-Synthesis Pathway Prediction 1005.5.4.2 Reaction Yield Predictions and Reaction Mechanism Insights 1005.6 Medical Imaging Data Analysis 1005.6.1 Analysis: Radio-Mic Quantification 1015.6.2 Analysis: Bio-Marker Identification 1015.7 Applying IoT (Internet of Things) to Biomedical Research 1025.7.1 IoT and IoMT Applications for Healthcare and Well-Being 1025.7.1.1 Wireless Medical Devices 1025.8 Conclusions 102Acknowledgments 102References 1026 Association Rule Mining Based on Ethnic Groups and Classification using Super Learning 111Md Faisal Kabir and Simone A. Ludwig6.1 Introduction 1116.2 Background 1126.3 Motivation and Contribution 1146.4 Data Analysis 1156.4.1 Data Description 1156.4.2 Data Preprocessing 1156.4.3 Further Preprocessing for Ethnic Group Rule Discovery with Multiple Consequences 1156.4.3.1 Transaction-Like Database for Association Rule 1156.4.4 Classification Data Set 1166.5 Methodology 1176.5.1 Association Rule Mining 1176.5.2 Super Learning 1186.5.2.1 Ensemble or Super Learner Set-Up 1186.6 Experiments and Results 1196.6.1 Rules Discovery 1206.6.1.1 Rules of Breast Cancer Patients Based on Ethnic Groups 1206.6.1.2 Interpreting Rules 1206.6.2 Evaluation Criteria of Classification Model 1216.6.2.1 Super Learner Results 1246.6.3 Discussion 1256.7 Conclusion and Future Work 126References 1277 Neuro-Rough Hybridization for Recognition of Virus Particles from TEM Images 131Debamita Kumar and Pradipta Maji7.1 Introduction 1317.2 Existing Approaches for Virus Particle Classification 1327.3 Proposed Algorithm 1347.3.1 Extraction of Local Textural Features 1357.3.2 Selection of Class-Pair Relevant Features 1357.3.3 Extraction of Discriminating Features 1387.3.4 Classification 1397.4 Experimental Results and Discussion 1407.4.1 Experimental Setup 1407.4.2 Methods Compared 1407.4.3 Database Considered 1417.4.4 Effectiveness of Proposed Approach 1417.4.5 Comparative Performance Analysis 1437.4.5.1 Comparison with Deep Architectures 1447.4.5.2 Comparison with Existing Approaches 1457.5 Conclusion 146References 1478 Neural Network Optimizers for Brain Tumor Image Detection 151T. Kalaiselvi and S.T. Padmapriya8.1 Introduction 1518.2 Related Works 1528.3 Background 1538.3.1 Types of Neural Networks 1538.3.2 Tunable Elements of Neural Networks 1548.3.2.1 Basic Parameters 1548.3.2.2 Hyperparameters 1548.3.2.3 Regularization Techniques 1558.3.2.4 Neural Network Optimizers 1568.4 Case Study - Brain Tumor Detection 1578.4.1 Methodology 1578.4.2 Data Sets and Metrics 1578.4.3 Results and Discussion 1598.5 Conclusion 162References 1629 Abnormal Slice Classification from MRI Volumes using the Bilateral Symmetry of Human Head Scans 165N. Kalaichelvi, T. Kalaiselvi, and K. Somasundaram9.1 Introduction 1659.1.1 MRIs of the Human Brain 1659.1.2 Normal and Abnormal Slices 1669.1.3 Background 1679.1.3.1 Decision Tree Classifiers 1679.1.3.2 K-Nearest Neighbours (KNN) Classifiers 1689.1.3.3 Support Vector Machine (SVM) 1689.1.3.4 Naive Bayes 1699.1.3.5 Artificial Neural Network (ANN) 1699.1.3.6 Back-Propagation Neural Network (BPN) 1709.1.3.7 Random Forest Classifiers 1709.2 Literature Review 1719.3 Methodology 1729.3.1 Preprocessing 1739.3.2 Feature Extraction 1749.3.3 Feature Selection 1759.3.4 Classification 1779.3.5 Cross-Validation 1779.3.6 Training Validation and Testing 1789.4 Materials and Metrics 1799.4.1 Confusion Matrix 1799.5 Results and Discussion 1809.6 Conclusion 182References 18310 Conclusion 187Siddhartha BhattacharyyaReferences 188Index 191