Mining Biomedical Text, Images and Visual Features for Information Retrieval

1st Edition - November 15, 2024
Imprint: Academic Press
Editors: Sujata Dash, Subhendu Kumar Pani, Wellington Pinheiro Dos Santos, Jake Y Chen
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 1 5 4 5 2 - 2
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 1 5 4 5 1 - 5

Mining Biomedical Text, Images and Visual Features for Information Retrieval provides broad coverage of the concepts, themes, and instrumentalities of the important, evolvi… Read more

Purchase options

World Book Day Celebration!

Save up to 30% on books and eBooks!

Shop now

Institutional subscription on ScienceDirect

Request a sales quote

Mining Biomedical Text, Images and Visual Features for Information Retrieval provides broad coverage of the concepts, themes, and instrumentalities of the important, evolving area of biomedical text, images, and visual features towards information retrieval. The book aims to encourage an even wider adoption of IR methods for assisting in problem-solving and to stimulate research that may lead to additional innovations in this area of research. Topics covered include Internet of Things for health informatics; data privacy; smart healthcare; medical image processing; 3D medical images; evolutionary computing; deep learning; medical ontology; linguistic indexing; lexical analysis; and domain specific semantic categories in biomedical applications. This is a valuable resource for researchers and graduate students who are interested to learn more about data mining techniques to improve their research work.

Title of Book
Cover image
Title page
Table of Contents
Copyright
Dedication
Contributors
Acknowledgments
Section I. IoT for biomedical and health informatics
Chapter 1. Introduction to IoT and health informatics
1 Introduction
1.1 History of the IoT
1.2 The concept of integrated Internet of Things (IoT) technology with healthcare devices
1.3 Health informatics
1.4 Trends in health informatics
1.5 Principle of using IoT in healthcare
1.6 Examples of biosignals used by IoT devices to measure the human body parameters
1.7 Security and privacy in IoT healthcare
1.7.1 Ethical consideration regarding IoT in healthcare
1.7.2 Compliance with regulation
1.7.3 Impact of IoT on healthcare professionals
Chapter 2. Wireless internet of medical things: Technology and architectural design
1 Introduction
1.1 Increasing the hardware and wireless flexibility
2 WIoMT architecture
3 IoMT wireless technologies
3.1 WiFi/WLAN (IEEE 802.11) standard
3.2 WPAN/Bluetooth (IEEE 802.15.1) standard
3.3 LR-WPAN/ZigBee (IEEE 802.15.4) protocol
3.4 IEEE 802.15.6 protocol
4 Selection of WIoMT technology
5 WIoMT optimization models
5.1 WIoMT performance optimization models
5.1.1 Routing optimization
5.1.2 Back-off mechanism optimization
5.1.3 Channel access optimization
6 Potentiality for WIoMT
7 Conclusion
Chapter 3. An automated human behavior analysis using AI based predictive model in health care
1 Introduction
2 Literature review
3 Methodology
3.1 PCA algorithm
3.2 Brief of RNNs
3.3 HAR datasets
3.3.1 Sensors-based accelerometer
3.3.2 Sensors-based gyroscope
3.4 Integrated PCA-RNN model
3.4.1 Sequential model
3.4.2 Dense layer
3.4.3 Dropout
4 Result analysis
5 Conclusion
Chapter 4. Survey on security and privacy issues in IoT healthcare
1 Introduction
1.1 Overview of IoT in healthcare
1.1.1 Definition and scope
1.2 Importance and applications
1.3 Significance of security and privacy [19]
2 Security threats in IoT healthcare
2.1 Overview of security threat landscape
2.2 Common types of security threats
2.2.1 Unauthorized access
2.2.2 Data breaches
2.2.3 Malware and ransomware
2.2.4 Denial of service (DoS) [4] attacks
2.3 Vulnerabilities in IoT healthcare devices and systems
3 Privacy challenges in IoT healthcare
3.1 Overview of privacy concerns
3.2 Data privacy issues
3.2.1 Collection and storage of sensitive data
3.2.2 Consent and user awareness
3.3 Regulatory compliance and legal implications
3.3.1 HIPAA compliance
3.3.2 GDPR and other privacy regulations
4 Mitigation strategies
4.1 Security measures
4.1.1 Encryption and authentication
4.1.2 Intrusion detection and prevention systems
4.2 Privacy enhancing technologies
4.2.1 Anonymization and pseudonymization
4.2.2 Differential privacy
4.2.3 Privacy-preserving data-sharing mechanisms
5 Case studies and examples
5.1 Notable security breaches in IoT healthcare
5.2 Successful implementation of security measures
5.3 Impact of security and privacy on patient care
6 Future directions and challenges
6.1 Ethical considerations and societal implications
7 Conclusion
Chapter 5. Smart health monitoring system to prevent complications during pregnancy using IoT and Hadoop
1 Introduction
2 Literature review
3 Integrated model for prenatal health monitoring
3.1 Sensor data collection
3.2 Data transmission to cloud
3.3 Cloud storage and Hadoop
3.4 Machine learning and deep learning
3.5 Risk determination
3.6 Result distribution
3.7 Alert notifications
4 Dataset and experimental setup
4.1 Data source
4.2 Experimental setup
5 Result and analysis
5.1 Result summary
5.2 Analysis summary
5.3 Overall assessment
6 Limitations and future scope
7 Conclusion
Chapter 6. Methodical IoT-based information system in healthcare industry
1 Introduction
2 Chapter organization
3 Related work
4 Objectives
5 Methodology
6 Components of health information system
7 Challenges to e-health systems
8 Security threats to IoT devices
8.1 Security guidelines
9 Conclusions
Chapter 7. Role of IoT in developing smart healthcare monitoring systems
1 Introduction
2 Internet of Things (IoT)
2.1 Smart buildings with IoT
3 Analytics and big data management
3.1 Challenges
3.2 Cybersecurity
3.3 Personal information
4 Process of legacy construction and retrofit
4.1 Interoperability
4.2 Opportunities
4.2.1 Collaboration and joint ventures
4.3 Wellness and good health
4.4 Sustainability
5 Basics of malware
5.1 Emotet
5.2 Service denial
5.3 Man in the center
5.4 Phishing Attack
5.5 Injection of SQL data
5.6 Attacks on passwords
6 Case study
6.1 Content management system
6.2 Which states have the most (and the least) nursing facilities?
7 Conclusion and future scope
Chapter 8. Internet of things application to study the spontaneous quantitative drugs detoxification through biosensor
1 Introduction
2 Internet of things
3 Opportunities as well as challenges for biosensing and IoT in smart healthcare systems
3.1 The medical issues that elderly adults, older workers, and infants face
3.1.1 Hearing loss
3.1.2 Cardiovascular diseases
3.1.3 Cognitive impairments
3.1.4 Mental health issues
3.1.5 Balance disorders
4 Innovation healthcare: Benefits and problems
4.1 Low-cost technology
4.1.1 A scalable, extendable, and compatible approach
4.1.2 Big data and automated starting to learn
5 Applied research through IoT: Study on spontaneous quantitative drugs detoxification through biosensor
5.1 Case
5.1.1 Biosensor application to quantify
5.1.2 Tissue-specified sensor devices
5.1.3 Ionic conductor materials for detecting gas molecules
5.1.4 Molecular semiconductors on biosensor design
5.1.5 Ionic conductor materials for detecting gas molecules
6 IoT and IoMT building blocks for applications in health and wellness
6.1 Enablers of a smart environment
6.1.1 Ubiquitous and supportive medical devices
6.1.2 Mobile devices
6.1.3 IoT infrastructure and environmental control
6.1.4 Human surveillance using cameras
7 Preparation of allicin extracts formulation to detoxify cumulative body system
7.1 Calibration on detoxification assessments
7.1.1 Detoxification concept involved
7.1.2 Garlic roles in detoxification
7.2 Biosensor to detect allicin-based detoxification
7.2.1 Spontaneous storing of data information and auto-evaluation process
7.2.2 Data gathering and analysis software as BioSense
7.3 Technical control and management
7.4 Running software snap images (Fig. 8.8)
8 Miscellaneous
8.1 Modern research activities for smart healthcare applications
8.1.1 Monitoring body heat
8.1.2 Activity recognition
8.1.3 Monitoring blood glucose levels and hemoglobin levels
8.1.4 Monitoring and detecting respiration rates
8.1.5 Sleep monitoring
8.1.6 Blood-oxygen saturation detection
8.2 Use cases/applications
8.2.1 Stroke, cardiac monitoring devices, and heart-rate analysis
9 IoT-based healthcare monitoring systems: Its importance
9.1 IoT-based healthcare monitoring systems
9.2 IoT healthcare wireless network devices
9.2.1 Systems for monitoring healthcare with wearable sensors
9.2.2 Case study sensors for health monitoring: Application cases through IoT
Section II. Computational intelligence for medical image processing
Chapter 9. Supervised and unsupervised techniques for biomedical image classification
1 Introduction
2 General classification process
2.1 Preprocessing
2.1.1 Fast Fourier transform
2.1.2 Gabor filters
2.1.3 Principal component analysis
2.1.4 Local binary pattern
2.1.5 Discrete cosine transform
2.1.6 Discrete wavelet transform
2.2 Feature extraction
2.3 Classifiers
2.3.1 Unsupervised classification
2.3.2 Supervised classification
3 Applications
4 Classification outcomes
4.1 Performance evaluation parameters
5 Conclusion
Chapter 10. Image segmentation and parameterization for automatic diagnostics of medical images
1 Introduction
2 Related works
3 Image segmentation techniques
3.1 Traditional methods
3.1.1 Thresholding
3.1.2 Region-based segmentation
3.1.3 Edge detection
3.1.4 Active contours (snakes)
3.1.5 Graph-based segmentation
3.1.6 Machine learning approaches
3.1.7 Random forests
3.1.8 Support vector machines (SVM)
3.1.9 CNN
3.1.10 Deep Boltzmann machines (DBM)
3.1.11 Conditional random fields (CRF)
4 Parameterization of medical images
4.1 Shape-based features
5 Texture analysis in parameterization of medical images
6 Entropy (H)
7 Contrast and homogeneity
8 Intensity-based features in parameterization of medical images
9 Standard deviation (σ)
10 Skewness (γ)
11 Integration process of segmentation and parameterization
12 Applications in automatic diagnostics
13 Tumor characterization
14 Neurological disorders
15 Cardiovascular diseases
16 Musculoskeletal disorders
17 Respiratory disorders
18 Future directions
19 Conclusion
Chapter 11. Computational intelligence on medical imaging with artificial neural networks
1 Introduction
2 Analysis of medical images
2.1 Computer tomography (CT)
2.2 Histology images
2.3 Magnetic resonance imaging (MRI)
2.4 Positron emission tomography (PET)
2.5 Ultrasound
2.6 X-rays
3 Artificial neaural networks on medical imaging
3.1 Artificial neural networks (ANNs)
3.1.1 Deep learning (DL)
3.1.2 Convolutional neural networks (CNNs)
3.1.3 Pre-trained networks
3.1.4 Recurrent neural networks (RNNs)
3.1.5 Autoencoders
3.1.6 Generative adversarial networks (GANs)
4 Classifications, detections, and segmentations of anomalies
5 Discussions
6 Conclusions
Chapter 12. A fine-tuned deep transfer learning model in classifying multiclass brain tumors for preclinical MRI image analysis
1 Introduction
2 Related work
3 Proposed model
3.1 Data preprocessing
3.2 Proposed layers
3.3 Hyperparameters and loss function
4 Results and discussion
4.1 Experimental setup
4.2 Model performance metrics
4.3 Discussion
5 Conclusion
Chapter 13. Transformer models for Topic Extraction from narratives and biomedical text analysis
1 Introduction
1.1 Biomedical data
1.2 Clinical text and narratives
1.3 Clinical natural language processing
2 Healthcare 4.0 and electronic health records
3 Biomedical natural language processing tasks
3.1 Natural language inference
3.2 Entity extraction
3.3 Semantic text similarity
4 Transformer model
5 Transformer model architecture
5.1 Foundation layer
5.2 Embedding layer
5.3 Transformer encoder
6 Challenges in biomedical text analysis
7 Biomedical text analysis applications
8 Conclusion
Chapter 14. Deep learning in medical image analysis
1 Introduction
2 Related work
3 Deep learning Architectures for Medical Image Analysis
3.1 Convolutional neural networks
3.2 Recurrent neural networks (RNNs)
3.3 Attention mechanisms
3.4 Capsule networks
3.5 Hybrid architectures
3.5.1 Convolutional-recurrent networks
3.6 Challenges and limitations of deep learning in medical image analysis
3.7 Data scarcity and quality
3.8 Interpretability and explainability
3.8.1 Saliency maps
3.8.2 Layer-wise relevance propagation
4 Future directions and opportunities
4.1 Multimodal integration
4.2 Federated learning and privacy—Preserving AI
4.3 Continual learning and adaptive models
5 Conclusion
Chapter 15. Automatic segmentation of multiple organs on CT images by using deep learning approaches
1 Introduction
1.1 CT imaging in clinical practice
1.2 Importance of organ segmentation on CT images
1.3 Challenges in organ segmentation on CT images
1.4 Automated segmentation with deep learning
1.5 Preprocessing steps for automatic segmentation of organs on CT images
1.6 Datasets and evaluation metrics for deep learning-based organ segmentation on CT images
1.7 Future directions in deep learning-based organ segmentation on CT images
1.8 Overview of the chapter
1.9 Related work
1.10 Methodology
2 Case study 1—Liver
2.1 Dataset description
2.2 Preprocessing
2.3 Model architecture
2.4 Case study 2—Pancreas
2.4.1 Dataset description
2.4.2 Preprocessing
2.4.3 Model architecture
2.5 Case study 3—Kidney
2.5.1 Dataset description
2.5.2 Preprocessing
2.5.3 Model architecture
2.6 Case study 4-Spleen
2.6.1 Dataset description
2.6.2 Preprocessing
2.6.3 Model architecture
3 Proposed work
3.1 Dataset description
3.2 Experimental setup
3.3 Model architecture
4 Experimental analysis
4.1 LiTS dataset
4.2 Pancreas-CT dataset
4.3 KiTS19 dataset
4.4 SPL dataset
4.5 Combined dataset
5 Discussion
6 Conclusions
7 Future scope
Chapter 16. Deep learning approaches for cervical cancer classification and segmentation: Advances and challenges
1 Introduction
2 Literature review
3 Cervical cancer datasets
4 Numerical dataset (clinical dataset) of cervical cancer
4.1 Image dataset of cervical cancer
5 Methods used for diagnosis of cervical cancer
5.1 Conventional methods
5.2 AI-based methods
6 Treatments of cervical cancer
6.1 Treatment of stage IA cervical cancer
6.2 Treatment of stages IB and IIA cervical cancer
6.3 Treatment of stages IIB, III, and IVA cervical cancer
7 Proposed method
7.1 Dataset
7.2 Classification
7.3 Performance evaluation metrics
8 Experimental result
8.1 Classification result
8.2 Comparison
9 Conclusion
Chapter 17. Synthesis of clinical images for oral cancer detection and prediction using deep learning
1 Introduction
2 Literature survey
3 Methods used and proposed methodology
3.1 Dataset description and preprocessing
3.2 Methods used
3.2.1 Convolutional neural network
3.2.2 LeNet-5
3.2.3 AlexNet
3.3.4 VGG-16
3.2.5 Inception-v3
3.2.6 RestNet
4 Proposed method
5 Results and discussion
6 Conclusion
Chapter 18. Medical image mining using data mining techniques
1 Introduction
2 Overview of medical image mining and its significance in the field of medicine
3 History of development of MIM
4 Challenges and opportunities in medical image mining
4.1 Challenges in medical image mining (MIM)
4.2 Opportunities in medical image mining
5 Data mining techniques for medical image mining
6 Image processing techniques for medical image enhancement, segmentation, and registration
6.1 Acquiring medical images
6.2 Image preprocessing: Reconstruction and enhancement
6.3 Segmentation of medical images
6.4 Feature selection and quantification
6.5 Image mining: Classification, clustering, and association
7 Machine learning and deep learning techniques for medical image classification and diagnosis
7.1 Classical ML techniques used in image segmentation
7.2 Deep learning methods
8 Pattern recognition techniques for medical image feature extraction and analysis
9 Applications of medical image mining
10 Image-based diagnosis for various medical conditions
10.1 Tumor histopathological image classification, fragmentation, and clustering
10.2 Diagnosing cerebral hemorrhage image classification, fragmentation, and clustering
10.3 Ocular disease and diabetic retinopathy image classification, fragmentation, and clustering
10.4 Pneumonia and COVID-19 diagnosis image classification, fragmentation, and clustering
11 Image-assisted therapy for planning and monitoring treatment
12 Image-based population studies for disease epidemiology and population health management
13 Challenges and limitations in the validation of medical image mining methods
14 Case studies
14.1 Case study 1: Pneumonia detection using deep learning
14.2 Case study 2: Brain tumor segmentation with deep learning
14.3 Case study 3: Identifying breast cancer with machine learning techniques
14.4 Case study 4: Diabetic retinopathy detection using deep learning
14.5 Case study 5: Google’s lymph node assistant (LYNA)
14.6 Case study 6: IBM’s Watson for Oncology
15 Future directions for medical image mining research and development
16 Conclusion
Chapter 19. Biomedical image characterization and radio genomics using machine learning techniques
1 Introduction
1.1 History of medical imaging
2 An insight of radiogenomics
2.1 Conventional and deep radiomics
3 Overall flow of radiogenomics
4 The era of radiogenomics in precision medicine
5 What has radiogenomics accomplished thus far?
6 Artificial intelligence in radiogenomics
6.1 What AI offers: A computational perspective
7 Radiomic characterization of medical imaging
7.1 Handcrafted radiomic analysis
7.2 Deep learning-based radiomic analysis
7.3 Multimodality/multiparametric radiomics
8 Uncovering the mechanisms of cancer using radiogenomics
9 Clinical challenges and a view for the future
9.1 Significance of radiogenomics
9.2 Brief overview of machine learning in biomedical imaging
9.3 Biomedical image characterization
9.3.1 Importance of image characterization
9.3.2 Challenges in biomedical image characterization
9.4 Goals for segmenting medical images
9.4.1 Categories of techniques for medical image segmentation
9.4.2 Importance of completely autonomous methods
9.4.3 Practical uses for medical image segmentation
9.5 The study of radiogenomics
9.5.1 Machine learning integrated with radiogenomics and biomedical imaging
9.5.2 Biogenomic characteristics in deep learning frameworks
9.5.3 Difficulties and prospects
10 Conclusion
Chapter 20. Image informatics for clinical and preclinical biomedical analysis
1 Introduction
2 Fundamentals of image acquisition
3 Anatomic (structural) imaging
4 Functional imaging
4.1 Image-based functional brain imaging
5 Imaging modalities
5.1 Light
5.2 X-rays
5.3 Ultrasound
5.4 Nuclear magnetic resonance (NMR)
5.5 Nuclear medicine imaging (NMI)
6 Image quality
6.1 Characteristics of image quality
6.2 Contrast agents
7 Image reconstruction
7.1 Historical development
7.2 Principles of image reconstruction in CT
7.3 Application beyond CT: Reconstruction in other modalities
8 Imaging methods in other medical domains
8.1 Microscopic/cellular imaging
8.2 Pathology/tissue imaging
8.3 Ophthalmologic imaging
8.4 Dermatologic imaging
9 Image content representation
10 Representing visual content in digital images
11 Representing knowledge content in digital images
12 Image processing
13 Types of image processing methods
14 Feature extraction and representation
15 Selection of relevant features
16 Texture analysis
17 Shape analysis
18 Feature descriptor techniques
19 Image segmentation
20 Thresholding methods
21 Region-based segmentation
22 Edge detection techniques
23 Watershed transformation
24 Image classification and diagnosis
25 Machine learning algorithms for image classification
26 Deep learning approaches
27 Ensemble methods
28 Clinical decision support systems
29 Quantitative image analysis
30 Quantification of biomarkers
31 Volumetric analysis
32 Morphological measurements
33 Statistical analysis techniques
34 Applications in clinical biomedical analysis
35 Disease diagnosis and prognosis
36 Treatment response assessment
37 Radiomics and radiogenomics
38 Computer-aided diagnosis (CAD)
39 Applications in preclinical biomedical analysis
40 Drug discovery and development
41 Animal models and imaging
42 Pharmacokinetics and pharmacodynamics
43 Challenges and future directions
44 Data privacy and security
45 Integration of multi-modal imaging data
46 Standardization and interoperability
47 Emerging technologies and trends
48 Conclusion
49 Future prospects and opportunities
Chapter 21. Persistent homology diagram (PHD) based web service for cancer tagging of mammograms
1 Introduction
2 Motivation and contribution of current work
3 Related works
4 Method
4.1 PHD—A topological data analysis signature
4.2 From mammograms to PHD
4.3 EMD—A similarity metric
5 Implementation
5.1 Dataset
5.2 Outline of the implementation
5.3 Transformation of a mammogram into PHD
5.4 Training process
5.5 Representative selection
5.6 Validation process
6 Performance of the proposed method
6.1 Results from compiler test
6.2 Results with validation set
7 Algorithmic web service utility
8 Conclusion
Section III. Biomedical natural language processing
Chapter 22. Tooth segmentation on dental panoramic X-rays using Mask R-CNN
1 Introduction
2 Materials and methods
2.1 Convolutional neural network (CNN)
2.2 Mask R-CNN
2.3 R-CNN
2.4 Feature pyramid network
2.5 ROI align
2.6 Dental panoramic X-ray database
3 Experimental results
3.1 Intersection over union in the field of image segmentation
3.2 COCO
3.3 Visualization of the prediction results
4 Conclusion
Chapter 23. Medical ontology for text categorization system and its applications
1 Introduction
2 Related works
3 Ontology levels
3.1 Upper-level ontology
3.2 Domain ontology
3.3 Task ontology
3.4 Application ontology
4 Text categorization in medical ontology
4.1 Advantages of using text categorization in medical ontology
4.2 Disadvantages of using text categorization in medical ontology
5 Role of machine learning for text categorization
5.1 Document management
5.2 Spam filtering
5.3 Sentiment analysis
5.4 News categorization
6 Proposed idea
7 Case study
8 Medical ontology for text categorization in healthcare
9 Conclusion
Chapter 24. Biomedical terminologies: Resources for information retrieval
1 Introduction
1.1 Definition of text mining and its application in biology and biomedicine
1.2 Importance of text mining in generating insights and discoveries
2 Methods and techniques of text mining
2.1 Explanation of how text mining works in biology and biomedicine
3 Applications of text mining in biology and biomedicine
3.1 Exploration of how text mining is used in different areas of biology and biomedicine
3.2 Drug discovery and development
3.3 Precision medicine
3.4 Disease diagnosis and treatment
3.5 Gene and protein analysis
3.6 Literature curation and annotation
4 Challenges and limitations of text mining in biology and biomedicine
5 Complexity and heterogeneity of biological data
5.1 Quality of data and accuracy of text mining results
5.2 Integration of text mining with other data sources
6 Future directions of text mining in biology and biomedicine
7 Conclusion
Chapter 25. Multimodal medical image retrieval system for clinical decision support system
1 Introduction
2 Medical image retrieval methods
2.1 Text-based medical image retrieval
2.2 Content-based medical image retrieval
2.3 Semantic-based image retrieval
3 Significance of CBIR in healthcare
4 Convolutional neural network
5 Two-dimensional image retrieval
6 Need for three-dimensional image retrieval
7 State of art to prior work
7.1 Materials and methods
8 Proposed methodology
8.1 Architectures
8.2 Training parameters and implementation
8.3 LeNet coder
8.4 VGG coder
8.5 ResNet coder
9 Similarity metrics in image retrieval
10 Performance metrics in image retrieval
11 Results and discussion
11.1 Image retrieval results of LeNet coder
11.2 Image retrieval results of VGG coder
11.3 Image retrieval results of Res coder
11.4 Comparison of image retrieval performance for the proposed networks
12 Summary and conclusion
Chapter 26. Translation of biomedical terms using inferring rewriting rules
1 Introduction
2 Translation technique
3 Revising rules
4 Lattice of rules
5 Verification
6 Translation investigations
7 Investigation of cross-language information retrieval
8 Possible mistakes
9 Associated work
10 Other techniques
11 Conclusion
Chapter 27. Lexical analysis of biomedical ontologies
1 Introduction
2 Literature rreview
3 Contributory work
4 Conclusion and future work
Chapter 28. Word sense disambiguation in biomedical applications
1 Introduction
2 The applicability of machine learning for word sense disambiguation (WSD) in biomedical applications
3 Machine learning approach for word sense disambiguation in biomedical applications
4 Top of form
4.1 The challenges of WSD in biomedical applications using machine learning
5 The future prospects of WSD in biomedical applications using machine learning
6 Conclusion
Chapter 29. Domain specific semantic categories in biomedical applications
1 Introduction
2 General overview
3 Types of semantic category in the biomedical field
4 Gene ontology
5 Human phenotype ontology
6 Human disease ontology
7 Coronavirus infectious disease ontology
8 Medical subject headings
9 Foundational model of anatomy
10 Current procedural terminology
11 Applications of semantic categories in biomedical sciences
11.1 Electronic health records (EHRs)
11.2 Clinical decision support systems
11.3 Clinical reasoning ontologies
11.4 Ontology-based approaches in clinical decision support
11.5 Text mining and information extraction in healthcare
11.6 Domain ontology creation in biomedical sciences
12 Challenges in implementing semantic categories in biomedical applications
12.1 Acceptance and training
12.2 Complexity and standardization
12.3 Ontology recommendation
12.4 Multilingualism
12.5 Cost and resources
12.6 Conclusion
13 Overview of semantic categories in biomedical applications
14 Importance of domain specific semantic categories in biomedical applications
15 Challenges in semantic categories for biomedical data
16 Integration with existing systems
17 Domain specific semantic categories: taxonomy and applications in biomedical research
17.1 Diseases
17.2 Treatments
17.3 Genes and biomolecules
17.4 Biological processes
17.5 Medical imaging
17.6 Patient demographics
18 Examples and use cases of domain specific semantic categories in biomedical research
18.1 Precision medicine
18.2 Clinical decision support systems
18.3 Drug discovery and development
18.4 Epidemiological studies
18.5 Biomedical text mining
18.6 Integration of emerging technologies
18.7 Interconnected applications
18.8 Future implications and innovations
18.9 Ethical considerations and privacy concerns
18.10 Global collaborations and knowledge sharing
18.11 Educational initiatives and workforce training
19 Expanded exploration of challenges and solutions in domain specific semantic categories
19.1 Ambiguity and variability in biomedical data
19.1.1 Ambiguity
19.1.2 Variability
19.2 Integration with existing systems
19.2.1 Data standardization
19.2.2 Interoperability
19.2.3 Legacy systems
19.2.4 User adoption
19.2.5 Semantic interoperability
20 Emerging technologies in domain specific semantic categories in biomedical research
20.1 Machine learning and deep learning
20.2 Explainable AI
20.3 Graph databases and knowledge graphs
20.4 Blockchain technology
20.5 Natural language processing advancements
21 Conclusion: Charting transformative frontiers with domain specific semantic categories in biomedical research
Index

Sujata Dash

Sujata Dash holds the position of Professor at the Information Technology School of Engineering and Technology, Nagaland University, Dimapur Campus, Nagaland, India, bringing more than three decades of dedicated service in teaching and mentoring students. She has been honoured with the prestigious Titular Fellowship from the Association of Commonwealth Universities, United Kingdom. As a testament to her global contributions, she served as a visiting professor in the Computer Science Department at the University of Manitoba, Canada. With a prolific academic record, she has authored over 200 technical papers published in esteemed international journals, and conference proceedings, and edited book chapters by reputed publishers Serving as a reviewer and Associate Editor for approximately 15 international journals.

Affiliations and expertise

Department of Information Technology, School of Engineering and Technology, Nagaland University, India

Subhendu Kumar Pani

Subhendu Kumar Pani received his Ph.D. from Utkal University Odisha, India. He has more than 16 years of teaching and research experience. His research interests include data mining, big data analysis, web data analytics, fuzzy decision making and computational intelligence. He is a fellow in SSARSC and life member in IE, ISTE, ISCA, OBA.OMS, SMIACSIT, SMUACEE, CSI.

Affiliations and expertise

Department of Computer Science and Engineering, Krupajal Engineering College, Bhubaneswar, Odisha, India

Wellington Pinheiro Dos Santos

Professor dos Santos is creator and developer of innovative healthcare solutions for diagnosis and treatment using Artificial Intelligence. Applications in digital epidemiology, neuroscience, diagnostic imaging, diagnosis by signs, diagnosis by laboratory tests, health informatics and bioinformatics. Founder of the Ada Lovelace Association. Leader of the Research Group on Biomedical Computing at UFPE. Enthusiast of social entrepreneurship and innovation in health.

Affiliations and expertise

Professor of Biomedical Engineering, Federal University of Pernambuco, Brazil

Jake Y Chen

Before joining UAB, Dr. Chen was the founding director of the Indiana Center for Systems Biology and Personalized Medicine at Indiana University and a tenured faculty member at Indiana University School of Informatics and Purdue University Computer Science Department. Dr. Chen has over 20 years of research and development experience in biological data mining, systems biology, and translational informatics in both Academia and the industry. He has over 150 peer-reviewed publications and presented worldwide on topics related to biocomputing, bioinformatics, and data sciences in life sciences. He was elected as the President-elect of the Midsouth Computational Biology and Bioinformatics Society (MCBIOS) in 2019. He also serves on the editorial boards of BMC Bioinformatics, Journal of American Medical Informatics Association (JAMIA), and Personalized Medicine.

Affiliations and expertise

Associate Director and Chief Bioinformatics Officer of the University of Alabama-Birmingham (UAB) Informatics Institute Professor of Genetics, Computer Science, and Biomedical Engineering, and Chief of the Informatics Section of the UAB School of Medicine, Department of Genetics, Birmingham, AL, USA

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health

Mining Biomedical Text, Images and Visual Features for Information Retrieval

Purchase options

World Book Day Celebration!

Institutional subscription on ScienceDirect

Sujata Dash

Subhendu Kumar Pani

Wellington Pinheiro Dos Santos

Jake Y Chen

Related books