Computational Analysis and Deep Learning for Medical Care

Principles, Methods, and Applications

Inbunden, Engelska, 2021

2 540 kr

Beställningsvara. Skickas inom 11-20 vardagar. Fri frakt över 249 kr.

Beskrivning

The book details deep learning models like ANN, RNN, LSTM, in many industrial sectors such as transportation, healthcare, military, agriculture, with valid and effective results, which will help researchers find solutions to their deep learning research problems.We have entered the era of smart world devices, where robots or machines are being used in most applications to solve real-world problems. These smart machines/devices reduce the burden on doctors, which in turn make their lives easier and the lives of their patients better, thereby increasing patient longevity, which is the ultimate goal of computer vision. Therefore, the goal in writing this book is to attempt to provide complete information on reliable deep learning models required for e-healthcare applications. Ways in which deep learning can enhance healthcare images or text data for making useful decisions are discussed. Also presented are reliable deep learning models, such as neural networks, convolutional neural networks, backpropagation, and recurrent neural networks, which are increasingly being used in medical image processing, including for colorization of black and white X-ray images, automatic machine translation images, object classification in photographs/images (CT scans), character or useful generation (ECG), image caption generation, etc. Hence, reliable deep learning methods for the perception or production of better results are a necessity for highly effective e-healthcare applications. Currently, the most difficult data-related problem that needs to be solved concerns the rapid increase of data occurring each day via billions of smart devices. To address the growing amount of data in healthcare applications, challenges such as not having standard tools, efficient algorithms, and a sufficient number of skilled data scientists need to be overcome. Hence, there is growing interest in investigating deep learning models and their use in e-healthcare applications.AudienceResearchers in artificial intelligence, big data, computer science, and electronic engineering, as well as industry engineers in transportation, healthcare, biomedicine, military, agriculture.

Produktinformation

Utgivningsdatum:2021-08-24
Mått:10 x 10 x 10 mm
Vikt:454 g
Format:Inbunden
Språk:Engelska
Antal sidor:528
Förlag:John Wiley & Sons Inc
ISBN:9781119785729

Utforska kategorier

Mer om författaren

Amit Kumar Tyagi is an assistant professor and senior researcher at Vellore Institute of Technology (VIT), Chennai Campus, India. He received his PhD in 2018 from Pondicherry Central University, India. He has published more than 8 patents in the area of deep learning, Internet of Things, cyber physical systems and computer vision.

Innehållsförteckning

Preface xixPart I: Deep Learning and Its Models 11 CNN: A Review of Models, Application of IVD Segmentation 3Leena Silvoster M. and R. Mathusoothana S. Kumar1.1 Introduction 41.2 Various CNN Models 41.2.1 LeNet-5 41.2.2 AlexNet 71.2.3 ZFNet 81.2.4 VGGNet 101.2.5 GoogLeNet 121.2.6 ResNet 161.2.7 ResNeXt 211.2.8 SE-ResNet 241.2.9 DenseNet 241.2.10 MobileNets 251.3 Application of CNN to IVD Detection 261.4 Comparison With State-of-the-Art Segmentation Approaches for Spine T2W Images 281.5 Conclusion 28References 332 Location-Aware Keyword Query Suggestion Techniques With Artificial Intelligence Perspective 35R. Ravinder Reddy, C. Vaishnavi, Ch. Mamatha and S. Ananthakumaran2.1 Introduction 362.2 Related Work 392.3 Artificial Intelligence Perspective 412.3.1 Keyword Query Suggestion 422.3.1.1 Random Walk–Based Approaches 422.3.1.2 Cluster-Based Approaches 422.3.1.3 Learning to Rank Approaches 432.3.2 User Preference From Log 432.3.3 Location-Aware Keyword Query Suggestion 442.3.4 Enhancement With AI Perspective 442.3.4.1 Case Study 452.4 Architecture 462.4.1 Distance Measures 472.5 Conclusion 49References 493 Identification of a Suitable Transfer Learning Architecture for Classification: A Case Study with Liver Tumors 53B. Lakshmi Priya, K. Jayanthi, Biju Pottakkat and G. Ramkumar3.1 Introduction 543.2 Related Works 563.3 Convolutional Neural Networks 583.3.1 Feature Learning in CNNs 593.3.2 Classification in CNNs 603.4 Transfer Learning 613.4.1 AlexNet 613.4.2 GoogLeNet 623.4.3 Residual Networks 633.4.3.1 ResNet-18 653.4.3.2 ResNet-50 653.5 System Model 663.6 Results and Discussions 673.6.1 Dataset 673.6.2 Assessment of Transfer Learning Architectures 673.7 Conclusion 73References 744 Optimization and Deep Learning-Based Content Retrieval, Indexing, and Metric Learning Approach for Medical Images 79Suresh Kumar K., Sundaresan S., Nishanth R. and Ananth Kumar T.4.1 Introduction 804.2 Related Works 824.3 Proposed Method 854.3.1 Input Dataset 864.3.2 Pre-Processing 864.3.3 Combination of DCNN and CFML 864.3.4 Fine Tuning and Optimization 884.3.5 Feature Extraction 894.3.6 Localization of Abnormalities in MRI and CT Scanned Images 904.4 Results and Discussion 924.4.1 Metric Learning 924.4.2 Comparison of the Various Models for Image Retrieval 924.4.3 Precision vs. Recall Parameters Estimation for the CBIR 934.4.4 Convolutional Neural Networks–Based Landmark Localization 964.5 Conclusion 104References 104Part II: Applications of Deep Learning 1075 Deep Learning for Clinical and Health Informatics 109Amit Kumar Tyagi and Meghna Mannoj Nair5.1 Introduction 1105.1.1 Deep Learning Over Machine Learning 1115.2 Related Work 1135.3 Motivation 1155.4 Scope of the Work in Past, Present, and Future 1155.5 Deep Learning Tools, Methods Available for Clinical, and Health Informatics 1175.6 Deep Learning: Not-So-Near Future in Biomedical Imaging 1195.6.1 Types of Medical Imaging 1195.6.2 Use and Benefits of Medical Imaging 1205.7 Challenges Faced Toward Deep Learning Using Biomedical Imaging 1215.7.1 Deep Learning in Healthcare: Limitations and Challenges 1225.8 Open Research Issues and Future Research Directions Biomedical Imaging (Healthcare Informatics) 1245.9 Conclusion 127References 1276 Biomedical Image Segmentation by Deep Learning Methods 131K. Anita Davamani, C.R. Rene Robin, S. Amudha and L. Jani Anbarasi6.1 Introduction 1326.2 Overview of Deep Learning Algorithms 1356.2.1 Deep Learning Classifier (DLC) 1366.2.2 Deep Learning Architecture 1376.3 Other Deep Learning Architecture 1396.3.1 Restricted Boltzmann Machine (RBM) 1396.3.2 Deep Learning Architecture Containing Autoencoders 1406.3.3 Sparse Coding Deep Learning Architecture 1416.3.4 Generative Adversarial Network (GAN) 1416.3.5 Recurrent Neural Network (RNN) 1416.4 Biomedical Image Segmentation 1456.4.1 Clinical Images 1466.4.2 X-Ray Imaging 1466.4.3 Computed Tomography (CT) 1476.4.4 Magnetic Resonance Imaging (MRI) 1476.4.5 Ultrasound Imaging (US) 1486.4.6 Optical Coherence Tomography (OCT) 1486.5 Conclusion 149References 1497 Multi-Lingual Handwritten Character Recognition Using Deep Learning 155Giriraj Parihar, Ratnavel Rajalakshmi and Bhuvana J.7.1 Introduction 1567.2 Related Works 1577.3 Materials and Methods 1607.4 Experiments and Results 1617.4.1 Dataset Description 1627.4.1.1 Handwritten Math Symbols 1627.4.1.2 Bangla Handwritten Character Dataset 1627.4.1.3 Devanagari Handwritten Character Dataset 1627.4.2 Experimental Setup 1627.4.3 Hype-Parameters 1647.4.3.1 English Model 1647.4.3.2 Hindi Model 1657.4.3.3 Bangla Model 1657.4.3.4 Math Symbol Model 1657.4.3.5 Combined Model 1667.4.4 Results and Discussion 1677.4.4.1 Performance of Uni-Language Models 1677.4.4.2 Uni-Language Model on English Dataset 1687.4.4.3 Uni-Language Model on Hindi Dataset 1687.4.4.4 Uni-Language Model on Bangla Dataset 1697.4.4.5 Uni-Language Model on Math Symbol Dataset 1697.4.4.6 Performance of Multi-Lingual Model on Combined Dataset 1717.5 Conclusion 177References 1788 Disease Detection Platform Using Image Processing Through OpenCV 181Neetu Faujdar and Aparna Sinha8.1 Introduction 1828.1.1 Image Processing 1838.2 Problem Statement 1838.2.1 Cataract 1838.2.1.1 Causes 1848.2.1.2 Types of Cataracts 1848.2.1.3 Cataract Detection 1858.2.1.4 Treatment 1868.2.1.5 Prevention 1868.2.1.6 Methodology 1868.2.2 Eye Cancer 1928.2.2.1 Symptoms 1948.2.2.2 Causes of Retinoblastoma 1948.2.2.3 Phases 1958.2.2.4 Spreading of Cancer 1968.2.2.5 Diagnosis 1968.2.2.6 Treatment 1978.2.2.7 Methodology 1998.2.3 Skin Cancer (Melanoma) 2028.2.3.1 Signs and Symptoms 2038.2.3.2 Stages 2038.2.3.3 Causes of Melanoma 2048.2.3.4 Diagnosis 2048.2.3.5 Treatment 2058.2.3.6 Methodology 2068.2.3.7 Asymmetry 2078.2.3.8 Border 2088.2.3.9 Color 2088.2.3.10 Diameter Detection 2098.2.3.11 Calculating TDS (Total Dermoscopy Score) 2108.3 Conclusion 2108.4 Summary 212References 2129 Computer-Aided Diagnosis of Liver Fibrosis in Hepatitis Patients Using Convolutional Neural Network 217Aswathy S. U., Ajesh F., Shermin Shamsudheen and Jarin T.9.1 Introduction 2189.2 Overview of System 2199.3 Methodology 2199.3.1 Dataset 2209.3.2 Pre-Processing 2219.3.3 Feature Extraction 2219.3.4 Feature Selection and Normalization 2239.3.5 Classification Model 2259.4 Performance and Analysis 2279.5 Experimental Results 2329.6 Conclusion and Future Scope 232References 233Part III: Future Deep Learning Models 23710 Lung Cancer Prediction in Deep Learning Perspective 239Nikita Banerjee and Subhalaxmi Das10.1 Introduction 23910.2 Machine Learning and Its Application 24010.2.1 Machine Learning 24010.2.2 Different Machine Learning Techniques 24110.2.2.1 Decision Tree 24210.2.2.2 Support Vector Machine 24210.2.2.3 Random Forest 24210.2.2.4 K-Means Clustering 24210.3 Related Work 24310.4 Why Deep Learning on Top of Machine Learning? 24510.4.1 Deep Neural Network 24610.4.2 Deep Belief Network 24710.4.3 Convolutional Neural Network 24710.5 How is Deep Learning Used for Prediction of Lungs Cancer? 24810.5.1 Proposed Architecture 24810.5.1.1 Pre-Processing Block 25010.5.1.2 Segmentation 25010.5.1.3 Classification 25210.6 Conclusion 253References 25311 Lesion Detection and Classification for Breast Cancer Diagnosis Based on Deep CNNs from Digital Mammographic Data 257Diksha Rajpal, Sumita Mishra and Anil Kumar11.1 Introduction 25711.2 Background 25811.2.1 Methods of Diagnosis of Breast Cancer 25811.2.2 Types of Breast Cancer 26011.2.3 Breast Cancer Treatment Options 26111.2.4 Limitations and Risks of Diagnosis and Treatment Options 26211.2.4.1 Limitation of Diagnosis Methods 26211.2.4.2 Limitations of Treatment Plans 26311.2.5 Deep Learning Methods for Medical Image Analysis: Tumor Classification 26311.3 Methods 26511.3.1 Digital Repositories 26511.3.1.1 DDSM Database 26511.3.1.2 AMDI Database 26511.3.1.3 IRMA Database 26511.3.1.4 BreakHis Database 26511.3.1.5 MIAS Database 26611.3.2 Data Pre-Processing 26611.3.2.1 Advantages of Pre-Processing Images 26711.3.3 Convolutional Neural Networks (CNNs) 26811.3.3.1 Architecture of CNN 26911.3.4 Hyper-Parameters 27211.3.4.1 Number of Hidden Layers 27311.3.4.2 Dropout Rate 27311.3.4.3 Activation Function 27311.3.4.4 Learning Rate 27411.3.4.5 Number of Epochs 27411.3.4.6 Batch Size 27411.3.5 Techniques to Improve CNN Performance 27411.3.5.1 Hyper-Parameter Tuning 27411.3.5.2 Augmenting Images 27411.3.5.3 Managing Over-Fitting and Under-Fitting 27511.4 Application of Deep CNN for Mammography 27511.4.1 Lesion Detection and Localization 27511.4.2 Lesion Classification 27911.5 System Model and Results 28011.5.1 System Model 28011.5.2 System Flowchart 28111.5.2.1 MIAS Database 28111.5.2.2 Unannotated Images 28111.5.3 Results 28211.5.3.1 Distribution and Processing of Dataset 28211.5.3.2 Training of the Model 28311.5.3.3 Prediction of Unannotated Images 28611.6 Research Challenges and Discussion on Future Directions 28611.7 Conclusion 288References 28912 Health Prediction Analytics Using Deep Learning Methods and Applications 293Sapna Jain, M. Afshar Alam, Nevine Makrim Labib and Eiad Yafi12.1 Introduction 29412.2 Background 29812.3 Predictive Analytics 29912.4 Deep Learning Predictive Analysis Applications 30512.4.1 Deep Learning Application Model to Predict COVID-19 Infection 30512.4.2 Deep Transfer Learning for Mitigating the COVID-19 Pandemic 30812.4.3 Health Status Prediction for the Elderly Based on Machine Learning 30912.4.4 Deep Learning in Machine Health Monitoring 31112.5 Discussion 31912.6 Conclusion 320References 32113 Ambient-Assisted Living of Disabled Elderly in an Intelligent Home Using Behavior Prediction—A Reliable Deep Learning Prediction System 329Sophia S., Sridevi U.K., Boselin Prabhu S.R. and P. Thamaraiselvi13.1 Introduction 33013.2 Activities of Daily Living and Behavior Analysis 33113.3 Intelligent Home Architecture 33313.4 Methodology 33513.4.1 Record the Behaviors Using Sensor Data 33513.4.2 Classify Discrete Events and Relate the Events Using Data Analysis Algorithms 33513.4.3 Construct Behavior Dictionaries for Flexible Event Intervals Using Deep Learning Concepts 33513.4.4 Use the Dictionary in Modeling the Behavior Patterns Through Prediction Techniques 33613.4.5 Detection of Deviations From Expected Behaviors Aiding the Automated Elderly Monitoring Based on Decision Support Algorithm Systems 33613.5 Senior Analytics Care Model 33713.6 Results and Discussions 33813.7 Conclusion 341Nomenclature 341References 34214 Early Diagnosis Tool for Alzheimer’s Disease Using 3D Slicer 343V. Krishna Kumar, M.S. Geetha Devasena and G. Gopu14.1 Introduction 34414.2 Related Work 34514.3 Existing System 34714.4 Proposed System 34714.4.1 Usage of 3D Slicer 35014.5 Results and Discussion 35314.6 Conclusion 356References 356Part IV: Deep Learning – Importance and Challenges for Other Sectors 36115 Deep Learning for Medical Healthcare: Issues, Challenges, and Opportunities 363Meenu Gupta, Akash Gupta and Gaganjot Kaur15.1 Introduction 36415.2 Related Work 36515.3 Development of Personalized Medicine Using Deep Learning: A New Revolution in Healthcare Industry 36715.3.1 Deep Feedforward Neural Network (DFF) 36715.3.2 Convolutional Neural Network 36715.3.3 Recurrent Neural Network (RNN) 36915.3.4 Long/Short-Term Memory (LSTM) 36915.3.5 Deep Belief Network (DBN) 37015.3.6 Autoencoder (AE) 37015.4 Deep Learning Applications in Precision Medicine 37015.4.1 Discovery of Biomarker and Classification of Patient 37015.4.2 Medical Imaging 37115.5 Deep Learning for Medical Imaging 37215.5.1 Medical Image Detection 37215.5.1.1 Pathology Detection 37215.5.1.2 Detection of Image Plane 37315.5.1.3 Anatomical Landmark Localization 37315.5.2 Medical Image Segmentation 37315.5.2.1 Supervised Algorithms 37415.5.2.2 Semi-Supervised Algorithms 37415.5.3 Medical Image Enhancement 37515.5.3.1 Two-Dimensional Super-Resolution Techniques 37515.5.3.2 Three-Dimensional Super-Resolution Techniques 37515.6 Drug Discovery and Development: A Promise Fulfilled by Deep Learning Technology 37515.6.1 Prediction of Drug Properties 37615.6.2 Prediction of Drug-Target Interaction 37715.7 Application Areas of Deep Learning in Healthcare 37715.7.1 Medical Chatbots 37715.7.2 Smart Health Records 37715.7.3 Cancer Diagnosis 37815.8 Privacy Issues Arising With the Usage of Deep Learning in Healthcare 37915.8.1 Private Data 37915.8.2 Privacy Attacks 38015.8.2.1 Evasion Attack 38015.8.2.2 White-Box Attack 38015.8.2.3 Black-Box Attack 38015.8.2.4 Poisoning Attack 38115.8.3 Privacy-Preserving Techniques 38115.8.3.1 Differential Privacy With Deep Learning 38115.8.3.2 Homomorphic Encryption (HE) on Deep Learning 38215.8.3.3 Secure Multiparty Computation on Deep Learning 38315.9 Challenges and Opportunities in Healthcare Using Deep Learning 38315.10 Conclusion and Future Scope 386References 38716 A Perspective Analysis of Regularization and Optimization Techniques in Machine Learning 393Ajeet K. Jain, PVRD Prasad Rao and K. Venkatesh Sharma16.1 Introduction 39416.1.1 Data Formats 39516.1.1.1 Structured Data 39516.1.1.2 Unstructured Data 39616.1.1.3 Semi-Structured Data 39616.1.2 Beginning With Learning Machines 39716.1.2.1 Perception 39716.1.2.2 Artificial Neural Network 39816.1.2.3 Deep Networks and Learning 39916.1.2.4 Model Selection, Over-Fitting, and Under-Fitting 40016.2 Regularization in Machine Learning 40216.2.1 Hamadard Conditions 40316.2.2 Tikhonov Generalized Regularization 40416.2.3 Ridge Regression 40616.2.4 Lasso—L1 Regularization 40616.2.5 Dropout as Regularization Feature 40716.2.6 Augmenting Dataset 40816.2.7 Early Stopping Criteria 40816.3 Convexity Principles 40916.3.1 Convex Sets 41016.3.1.1 Affine Set and Convex Functions 41116.3.1.2 Properties of Convex Functions 41116.3.2 Optimization and Role of Optimizer in ML 41316.3.2.1 Gradients-Descent Optimization Methods 41416.3.2.2 Non-Convexity of Cost Functions 41616.3.2.3 Basic Maths of SGD 41816.3.2.4 Saddle Points 41816.3.2.5 Gradient Pointing in the Wrong Direction 42016.3.2.6 Momentum-Based Optimization 42316.4 Conclusion and Discussion 424References 42517 Deep Learning-Based Prediction Techniques for Medical Care: Opportunities and Challenges 429S. Subasree and N. K. Sakthivel17.1 Introduction 43017.2 Machine Learning and Deep Learning Framework 43117.2.1 Supervised Learning 43317.2.2 Unsupervised Learning 43317.2.3 Reinforcement Learning 43417.2.4 Deep Learning 43417.3 Challenges and Opportunities 43517.3.1 Literature Review 43517.4 Clinical Databases—Electronic Health Records 43617.5 Data Analytics Models—Classifiers and Clusters 43617.5.1 Criteria for Classification 43817.5.1.1 Probabilistic Classifier 43917.5.1.2 Support Vector Machines (SVMs) 43917.5.1.3 K-Nearest Neighbors 44017.5.2 Criteria for Clustering 44117.5.2.1 K-Means Clustering 44217.5.2.2 Mean Shift Clustering 44217.6 Deep Learning Approaches and Association Predictions 44417.6.1 G-HR: Gene Signature–Based HRF Cluster 44417.6.1.1 G-HR Procedure 44617.6.2 Deep Learning Approach and Association Predictions 44617.6.2.1 Deep Learning Approach 44617.6.2.2 Intelligent Human Disease-Gene Association Prediction Technique (IHDGAP) 44717.6.2.3 Convolution Neural Network 44717.6.2.4 Disease Semantic Similarity 44917.6.2.5 Computation of Scoring Matrix 45017.6.3 Identified Problem 45017.6.4 Deep Learning–Based Human Diseases Pattern Prediction Technique for High-Dimensional Human Diseases Datasets (ECNN-HDPT) 45117.6.5 Performance Analysis 45317.7 Conclusion 45717.8 Applications 458References 45918 Machine Learning and Deep Learning: Open Issues and Future Research Directions for the Next 10 Years 463Akshara Pramod, Harsh Sankar Naicker and Amit Kumar Tyagi18.1 Introduction 46418.1.1 Comparison Among Data Mining, Machine Learning, and Deep Learning 46518.1.2 Machine Learning 46518.1.2.1 Importance of Machine Learning in Present Business Scenario 46718.1.2.2 Applications of Machine Learning 46718.1.2.3 Machine Learning Methods Used in Current Era 46918.1.3 Deep Learning 47118.1.3.1 Applications of Deep Learning 47118.1.3.2 Deep Learning Techniques/Methods Used in Current Era 47318.2 Evolution of Machine Learning and Deep Learning 47518.3 The Forefront of Machine Learning Technology 47618.3.1 Deep Learning 47618.3.2 Reinforcement Learning 47718.3.3 Transfer Learning 47718.3.4 Adversarial Learning 47718.3.5 Dual Learning 47818.3.6 Distributed Machine Learning 47818.3.7 Meta Learning 47818.4 The Challenges Facing Machine Learning and Deep Learning 47818.4.1 Explainable Machine Learning 47918.4.2 Correlation and Causation 47918.4.3 Machine Understands the Known and is Aware of the Unknown 47918.4.4 People-Centric Machine Learning Evolution 48018.4.5 Explainability: Stems From Practical Needs and Evolves Constantly 48018.5 Possibilities With Machine Learning and Deep Learning 48118.5.1 Possibilities With Machine Learning 48118.5.1.1 Lightweight Machine Learning and Edge Computing 48118.5.1.2 Quantum Machine Learning 48218.5.1.3 Quantum Machine Learning Algorithms Based on Linear Algebra 48218.5.1.4 Quantum Reinforcement Learning 48318.5.1.5 Simple and Elegant Natural Laws 48318.5.1.6 Improvisational Learning 48418.5.1.7 Social Machine Learning 48518.5.2 Possibilities With Deep Learning 48518.5.2.1 Quantum Deep Learning 48518.6 Potential Limitations of Machine Learning and Deep Learning 48618.6.1 Machine Learning 48618.6.2 Deep Learning 48718.7 Conclusion 488Acknowledgement 489Contribution/Disclosure 489References 489Index 491