Computer-Aided Diagnosis (CAD) Tools and Applications for 3D Medical Imaging

1st Edition, Volume 136 - January 20, 2025
Editors: Abhishek Gupta, Bala Chakravarthy Neelapu, Shailendra Singh Rana
Language: English
Hardback ISBN:
9 7 8 - 0 - 3 2 3 - 9 8 8 5 7 - 5
eBook ISBN:
9 7 8 - 0 - 3 2 3 - 9 8 8 5 8 - 2

Computer-Aided Diagnosis (CAD) Tools and Applications for 3D Medical Imaging, Volume 136 in the Advances in Computers series, presents detailed coverage of innovations i… Read more

Purchase options

Institutional subscription on ScienceDirect

Request a sales quote

Computer-Aided Diagnosis (CAD) Tools and Applications for 3D Medical Imaging, Volume 136 in the Advances in Computers series, presents detailed coverage of innovations in computer hardware, software, theory, design, and applications. Chapters in this updated release include Introduction to Computer-aided diagnosis (CAD) tools and applications, Enhancement of three-dimensional medical images, Machine Learning Based Techniques for Computer Aided Diagnosis, AI-based image processing techniques for the automatic segmentation of human organs, Watermarking over medical images, Compressive Sensing for 3D Medical Image Compression, and more.

Additional chapters cover Image encryption of medical images, Image Registration for 3D Medical Images, Texture-based computations for processing volumetric dental image, Language Processing in the Brain :an fMRI Study, Research challenges and emerging futuristic evolution for 3D medical image processing, Software based medical image analysis, and Automated 3D Visualization and Volume Estimation of Hepatic Structures for Treatment Planning of Hepatocellular Carcinoma.

Computer-Aided Diagnosis (CAD) Tools and Applications for 3D Medical Imaging
Cover image
Title page
Table of Contents
Copyright
Dedication
Contributors
Preface
Chapter One Introduction to computer-aided diagnosis (CAD) tools and applications
Abstract
Keywords
1 Introduction
2 Medical imaging
3 Three-dimensional medical imaging modalities
4 Computer-aided diagnosis (CAD) tools utilizing medical images
5 Applications of three-dimensional (3D) medical imaging
6 Classification of applications of each three-dimensional medical imaging
6.1 Applications of CT imaging
6.2 Applications of MRI
6.3 Applications of CBCT
6.4 Applications of 3D ultrasound imaging
6.5 Applications of PET-CT
6.6 Applications of SPECT
6.7 Applications of VR and AR in medical field
7 Robotic surgery (robot-assisted surgery)
8 General steps to develop a computer-aided diagnostic (CAD) tool
9 Computer-aided diagnostic tools for medical images
10 Challenges of medical imaging
11 Challenges of computer-aided diagnosis (CAD) tools
12 Risk associated with CAD tools
13 Conclusion
References
Chapter Two Enhancement of three-dimensional medical images
Abstract
Keywords
1 Introduction
1.1 A brief overview of 3D medical imaging
1.2 Importance of enhancing 3D medical images for diagnosis
2 Fundamentals of 3D medical imaging
2.1 Explanation of standard 3D imaging techniques
2.2 Challenges and limitations in obtaining clear 3D images
3 Image enhancement techniques
3.1 Contrast enhancement methods
3.2 Noise reduction strategies
3.3 Sharpness and detailed enhancement techniques
4 Advanced filtering approaches
4.1 Application of advanced filters for specific image features
4.2 Adaptive filtering for varied medical imaging scenarios
5 Machine learning in image enhancement
5.1 Overview of how machine learning algorithms can improve 3D medical images
5.2 Examples of successful applications of machine learning in 3D medical images
6 Clinical applications
6.1 Enhanced images in disease diagnosis
6.2 Surgical planning and guidance using improved 3D images
7 Challenges and future directions
7.1 Current challenges in image enhancement
7.2 Responsible use of image enhancement in a medical context
7.3 Emerging technologies and future possibilities
8 Conclusion
8.1 Summary of key findings
8.2 Encouragement for further research and development
References
Chapter Three Machine learning-based techniques for computer-aided diagnosis
Abstract
Keywords
1 Introduction to computer-aided diagnosis (CAD)
1.1 Definition and purpose of CAD in medical contexts
1.2 Historical overview of CAD development
2 Fundamentals of machine learning
2.1 A brief explanation of fundamental machine learning concepts
2.2 Types of machine learning
3 Data preprocessing for medical imaging
3.1 Challenges and considerations in handling medical data
3.2 Preprocessing steps involved in handling medical data
4 Feature extraction and selection
4.1 Importance of relevant features in medical diagnosis
4.2 Techniques for extracting and selecting meaningful features
5 Supervised learning algorithms
5.1 Overview of algorithms like SVM, RF, and neural networks
5.2 Application of these algorithms in medical diagnosis
6 Unsupervised learning for anomaly detection
6.1 Clustering methods for identifying unusual patterns in medical data
6.2 Outlier detection and its significance
7 Deep learning in medical imaging
7.1 Introduction to CNNs and their application
7.2 Case studies highlighting successful deep learning applications in diagnosis
8 Validation and evaluation
8.1 Importance of robust validation methods in medical ML
8.2 Metrics used for evaluating the performance of CAD systems
9 Challenges and ethical considerations
9.1 Addressing challenges such as interpretability and generalization
9.2 Ethical concerns in deploying ML-based systems in healthcare
10 Future trends and directions
10.1 Emerging technologies and their potential impact
10.2 Areas for further research and development
11 Conclusion
References
Chapter Four AI-based image processing techniques for the automatic segmentation of human organs
Abstract
Keywords
1 Introduction
1.1 Contribution of study
1.2 Organization of manuscript
2 Search methodology
2.1 Research investigations
3 Related work
3.1 Role of AI to diagnose cancer using medical images
4 Framework of learning models to classify medical images
4.1 Dataset
4.2 Data preprocessing
4.3 Data split
4.4 Data augmentation
4.5 Learning models
4.6 Evaluation parameters
5 Research investigations
5.1 Which AI-based Learning approaches have been used extensively in Cancer Prediction using medical images?
5.2 Which site and the type of medical images have been used most extensively in the studies?
5.3 What factors affect the performance of AI-based prediction models?
5.4 What potential solutions address the difficulties encountered while segmenting organs?
5.5 How machine learning models are different than deep learning models
5.6 How can transfer learning be effectively utilized in deep learning models to improve cancer detection and classification performance, particularly in scenarios with limited labeled medical image data?
5.7 What are the future directions/scope in the field?
6 Discussion
7 Conclusion
Funding
Conflict of interest
Availability of data and material
Code availability
References
Chapter Five Watermarking over medical images
Abstract
Keywords
1 Introduction
1.1 Watermarking, steganography, and cryptography
1.2 Characteristics of digital watermarking
2 Necessity of watermarking
3 Security and privacy requirements in teleradiology
3.1 Expected threats and conventional security measures
3.2 Security and privacy standards
3.3 Medical information security requirements
3.4 Limitations of the existing security measures
4 Requirements for watermarking
5 A framework of a watermarking system
6 Classification of schemes of a watermarking
6.1 Type of application
6.2 Working domain
6.3 Based on the human perception
6.4 Method of detection
6.5 Based on the types of documents used
7 Applications of watermarking
7.1 Owner identification
7.2 Copyright protection
7.3 Content authentication
7.4 Fingerprinting
7.5 Integrity control
7.6 EPR annotation
7.7 Digital signatures
7.8 Source tracking
7.9 Secured e-voting systems
7.10 Medical applications
8 Watermarking benchmarks and performance analysis
9 Medical image watermarking
9.1 Objectives of medical image watermarking
9.2 Importance of medical image watermarking
9.3 Medical image watermarking system requirements
9.4 Methods of medical image watermarking
9.5 Advantages of medical image watermarking
10 Case study
10.1 “A blind medical image watermarking for secure e-healthcare application using a crypto-watermarking system”
10.2 “Information hiding in medical images: a robust medical image watermarking system for E-healthcare [118]”
11 Conclusion
References
Chapter Six Compressive sensing technique for 3D medical image compression
Abstract
Keywords
1 Introduction
1.1 Overview of the challenges in 3D medical image compression
1.2 Introduction to the concept of compressive sensing
1.3 Relevance of compressive sensing in addressing the challenges of 3D medical image compression
2 Fundamentals of compressive sensing
2.1 Principles and theory behind compressive sensing
2.2 Incoherence
2.3 Restricted isometry property (RIP)
2.4 Concept of sparsity
2.5 How compressive sensing differs from traditional image compression methods
3 Transform domains and sparsity
3.1 Exploration of transform domains suitable for achieving sparsity in 3d medical images
3.2 Analysis of sparsity models and their significance in compressive sensing
4 Sampling techniques in 3D medical image compression
4.1 Non-uniform and random sampling methods
4.2 Random sampling patterns and their impact on compressive sensing for 3D medical images
5 Reconstruction algorithms for 3D medical images
5.1 Overview of reconstruction algorithms employed in compressive sensing
5.2 Detailed explanation of sparse signal recovery algorithms
5.3 Computational complexities and optimization strategies in reconstruction
6 Implementation and applications
6.1 Real-world applications of compressive sensing in 3D medical image compression
6.2 Effectiveness and challenges in practical implementation
6.3 Effectiveness and challenges of implementing compressive sensing in various real-world scenarios
6.4 Potential advancements and future applications in the field
7 Conclusion
References
Chapter Seven Image encryption of medical images
Abstract
Keywords
1 Introduction
1.1 Brief overview of the importance of 3D medical and dental imaging
1.2 The increasing use of digital technologies in healthcare
1.3 The need for security of medical images
2 Security concerns in 3D medical/dental imaging
2.1 Patient privacy and confidentiality
2.2 Common types of image attacks
2.3 Risks of unauthorized access and data breaches
2.4 Potential legal and ethical implications
3 Encryption techniques
3.1 Chaotic maps based encryption
3.2 Elliptic curve cryptography (ECC)
3.3 DNA (deoxyribonucleic acid) based image encryption
3.4 PQC (post quantum cryptography) based encryption based
3.5 Types of encryption algorithms suitable for 3D images
3.6 Ensuring end-to-end encryption for data in transit and at rest
4 Advanced algorithms for securing medical images
4.1 Parallel computing based image encryption algorithm [67]
4.2 Region of interest (RoI) based encryption algorithm [68]
4.3 Securing secret content using steganography [69]
5 Authentication and access control
5.1 Implementing user authentication mechanisms
5.2 Role-based access control for different stakeholders
5.3 Multi-factor authentication for enhanced security
6 Regulatory compliance
6.1 Overview of healthcare data protection regulations (e.g., HIPAA, GDPR)
6.2 Ensuring compliance with industry standards
6.3 Consequences of non-compliance
7 Case studies and examples
7.1 Real-world examples of security breaches in medical imaging
7.2 Successful implementations of secure 3D imaging systems
7.3 Lessons learned from past incidents
8 Future trends and challenges
8.1 Emerging technologies in medical imaging and their security implications
8.2 Anticipated challenges in securing future 3D imaging systems
8.3 Recommendations and best practices
9 Conclusion
9.1 Recap of the importance of security in 3D medical and dental imaging
9.2 Encouragement for ongoing research and development in secure imaging technologies
9.3 Call to action for the healthcare industry to prioritize data security
References
Chapter Eight Image registration for 3D medical images
Abstract
Keywords
1 Introduction on registration on medical images
1.1 Medical images used
2 Classification criteria of medical image registration
2.1 Registration based on modality
2.2 Registration based on dimensionality
2.3 Registration basis
2.4 Registration based on nature of transformation
2.5 Registration based on domain of transformation
2.6 Registration based on interaction
2.7 Registration based on subject
2.8 Registration based on misalignment
2.9 Approaches on medical image registration
3 3D transformations on medical image registration
3.1 Translation
3.2 Scaling
3.3 Rotation
3.4 Reflection
3.5 Shear
4 3D/voxel based registration algorithms
5 Applications of medical image registration
5.1 Radiation therapy
5.2 Cancer detection
5.3 Template atlas application
5.4 Image-guided surgery
6 Evaluation metrics
6.1 Average sum of squared differences
6.2 Intensity variance
6.3 Average correlation coefficient
6.4 Mutual information
7 Case study
7.1 Case study: Image registration in medical imaging
8 Conclusion
Acknowledgment
References
Chapter Nine Texture-based computations for processing volumetric dental image
Abstract
Keywords
1 Introduction
2 Different methods for texture analysis
2.1 Classical methods
2.2 Modified texture analysis categories
2.3 Learning-based methods
3 Texture-based analysis on dental images
3.1 Dental image representation for segmentation and detection
3.2 Techniques for feature extraction in dental images
3.3 Deep learning (DL) approaches
4 Accuracy evaluation of ML models
5 Results and discussion
6 Conclusions
7 Future scope
Acknowledgments
References
Chapter Ten Language processing in the brain: An fMRI study
Abstract
Keywords
1 Introduction
1.1 Phonological processing
1.2 Syntactic processing
1.3 Semantic processing
1.4 Pragmatic processing
2 Functional magnetic resonance imaging (fMRI)
3 Brain regions involved in language processing
4 Representation of words in the brain
4.1 Neural networks and distributed representation
4.2 Semantic networks and conceptual hierarchy
4.3 Neural correlates of word processing
4.4 Embodied and sensorimotor influences
4.5 Individual variations and plasticity
4.6 Pseudowords (non-existent or nonsense words) vs. meaningful words
4.7 Noun representation in the brain
4.8 Representations of pronouns in the brain
4.9 Processing of action words or verbs in the brain
4.10 The representation of adjectives in the brain
4.11 The processing of adverbs in the brain
4.12 The processing of prepositions in the brain
4.13 Conjunction
4.14 Stop words
5 Language comprehension
5.1 Left hemisphere dominance
5.2 Temporal and frontal regions
5.3 Semantic processing
5.4 Syntactic processing
5.5 Context integration
5.6 Working memory and attention
5.7 The processing of different case forms
5.8 The processing of different types of sentences
5.9 Emotion processing in the brain
5.10 Music in the brain
6 The neural processes underlying reading in the brain
6.1 Visual word recognition
6.2 Phonological processing
6.3 Semantic processing
6.4 Sentence comprehension
6.5 Reading comprehension
6.6 Individual differences
7 The neural processes involved in writing
7.1 Motor planning and execution
7.2 Grapheme-to-phoneme mapping
7.3 Word retrieval and spelling
7.4 Working memory and executive functions
7.5 Language and semantic processing
7.6 Individual differences
8 fMRI study of language disorders
8.1 Specific language impairment (SLI)
8.2 Dyslexia
8.3 Aphasia
8.4 Developmental language disorder (DLD)
8.5 Autism spectrum disorder (ASD)
8.6 Language networks
8.7 Lesion location
8.8 Language processing deficits
8.9 Compensation mechanisms
8.10 Language recovery
8.11 Treatment effects
8.12 Specific language impairment (SLI)
8.13 Dyslexia
8.14 Developmental language disorder (DLD)
8.15 Autism spectrum disorder (ASD)
9 fMRI studies on languages other than English
9.1 Bilingual language processing
9.2 Neural plasticity
9.3 Language-specific features
9.4 Cross-linguistic comparisons
9.5 Language disorders
10 fMRI studies on low-resource languages
10.1 Data collection challenges
10.2 Multilingual contexts
10.3 Phonological processing
10.4 Semantic and syntactic processing
10.5 Cultural and contextual factors
10.6 Preservation and revitalization efforts
11 Processing of a second language
11.1 Brain regions involved in second language processing
11.2 Language control and switching mechanisms
11.3 Neural plasticity and language learning
11.4 Cross-linguistic influence and interference
11.5 Language proficiency and neural efficiency
11.6 Age effects on second language processing
11.7 Cognitive benefits of second language acquisition
11.8 Distinct neural networks for L1 and L2
11.9 Language proficiency and neural adaptation
11.10 Cross-linguistic influence and interference
11.11 Language switching and control mechanisms
11.12 Cognitive demands and processing strategies
11.13 Neural plasticity and age effects
12 Summary
12.1 Introduction: The intricacies of language processing
12.2 fMRI technology: The window into brain activity
12.3 Language processing areas of the brain: Mapping the terrain
12.4 Parts of speech processing using fMRI: Investigating neural patterns
12.5 Language disorders: Unraveling the complexity
12.6 Writing, reading, and comprehension: The cognitive triad
References
Further reading
Chapter Eleven Research challenges and emerging futuristic evolution for 3D medical image processing
Abstract
Keywords
1 Introduction
1.1 The importance of 3D imaging in healthcare
1.2 The need for addressing research challenges and exploring futuristic evolution
2 Research challenges in 3D medical image processing
2.1 Image acquisition challenges in 3D medical imaging
2.2 Different modalities (e.g., MRI, CT, ultrasound)
2.3 Handling motion artifacts and patient variability
2.4 Data preprocessing and noise reduction
2.5 Dealing with noise and artifacts in 3D data
2.6 Image registration and fusion challenges
2.7 Segmentation and feature extraction
2.8 Challenges in accurate organ and tissue segmentation
2.9 Extracting meaningful features for diagnosis
2.10 Computational complexity and resource constraints
2.11 Real-time processing and high computational demands
2.12 Challenges in deploying 3D image processing in clinical settings
3 Advanced techniques and solutions
3.1 State-of-the-art algorithms and methodologies
3.2 Deep learning approaches for 3D image analysis
3.3 Handling big data in 3D medical imaging
3.4 Managing large-scale 3D image datasets
3.5 Scalable processing solutions
3.6 Incorporating multimodal information
3.7 Fusion of 3D and 2D data for improved diagnosis
3.8 Challenges in validation and benchmarking
3.9 Establishing benchmarks for algorithm evaluation
3.10 Addressing the lack of ground truth data
4 Futuristic evolution in 3D medical image processing
4.1 Trends in 3D imaging technology
4.2 Emerging 3D imaging modalities (e.g., 3D ultrasound, 3D microscopy) [62,63]
4.3 Integration of 3D imaging with other technologies (e.g., AI, robotics)
4.4 Artificial intelligence and machine learning
4.5 AI-driven diagnosis and decision support
4.6 Autonomous systems for 3D image analysis
4.7 Personalized medicine and treatment planning
4.8 Tailoring medical interventions based on 3D imaging data
4.9 Predictive modeling using patient-specific 3D information
4.10 Augmented and virtual reality in healthcare
4.11 Applications of AR and VR in medical training and visualization
4.12 Enhanced 3D visualization for surgeons and clinicians
5 Ethical and regulatory considerations
5.1 Ethical challenges in 3D medical image processing
5.2 Patient data privacy and consent
5.3 Bias and fairness in AI-driven diagnosis
5.4 Regulatory frameworks and compliance
5.5 FDA approvals for 3D medical imaging technologies
5.6 Legal and ethical aspects of AI in healthcare
6 Conclusion
References
Chapter Twelve Software based medical/dental analysis
Abstract
Keywords
1 Introduction
2 Medical image processing tools
2.1 3D slicer
2.2 Arivis cloud
2.3 Insight toolkit
2.4 AMIDE
2.5 VTK
2.6 MITK
2.7 NiftySim
2.8 GIMIAS
2.9 Camino
2.10 Elastix
2.11 ANTS
2.12 SPM
3 Dental softwares
3.1 Romexis
3.2 DENTOMO
3.3 DentiMax
3.4 Apteryx
3.5 Dolphin Imaging suite: A radiant canvas for dental excellence
4 DICOM viewers
4.1 Weasis
4.2 MANGO
4.3 3Dim viewer
4.4 IrfanView
4.5 Ginkgo CADX
4.6 RadiAnt
4.7 MEDISP DICOM viewer
4.8 Onis viewer
4.9 Orpalis DICOM viewer
4.10 JiveX DICOM viewer
5 Conclusion
References
Chapter Thirteen Automated 3D visualization and volume estimation of hepatic structures for treatment planning of hepatocellular carcinoma
Abstract
Keywords
1 Introduction
1.1 Need for surgery planning for HCC
1.2 Semantic segmentation of hepatic structures
1.3 Works on semantic segmentation of hepatic structures
1.4 Works on liver volumetry
2 Methodology
2.1 DeepLabV3+ Architecture
2.2 3D visualization and volumetry framework
3 Experimental settings
3.1 Dataset
3.2 Semantic segmentation implementation
3.3 Learning environment
3.4 Segmentation metrics
4 Results and discussion
4.1 Experimental assessment of hepatic structures segmentation
4.2 Experimental assessment of 3D visualization and volume estimation
5 Conclusion
References

Abhishek Gupta

Abhishek Gupta is currently working as Senior Scientist at CSIR-Central Scientific Instruments Organisation Chandigarh. He is working in the field of computational image processing. His research areas are medical/dental imaging, computer vision and artificial intelligence. He has completed BE in Computer Engineering from Rajasthan University, ME in Computer Science and Engineering from PEC University of Technology, Chandigarh, and PhD in Engineering from AcSIR (Academy of Scientific and Innovative Research) at CSIR-Central Scientific Instruments Organisation, Chandigarh. He is working in the area of computational dentistry. He has filed eight patents in India and United States. Two US patents and two Indian patents have been granted in his credit. He has authored around 30 articles in SCI journals, and authored several other articles in conferences and other journals with reputed indexing. He has delivered many invited expert talks in several renowned organizations. He has supervised many PhD (Engineering) and M. Tech thesis. He has received many funded projects from government agencies.

Bala Chakravarthy Neelapu

Dr. Bala Chakravarthy Neelapu has completed B.Tech in Electronics and Communication Engineering Dr. Bala Chakravarthy Neelapu is working as an assistant professor in the Department of Biotechnology and Medical Engineering at the National Institute of Technology, Rourkela, India. His area of interest is medical image processing and computer vision. He has authored more than 20 articles in SCI-indexed journals. JNTU Hyderabad in 2008, M.Tech. in Electronics and Communication Engineering from JNTU Kakinada, in 2011, and PhD in Engineering from AcSIR (Academy of Scientific and Innovative Research) at CSIR-Central Scientific Instruments Organization, Chandigarh in 2018. Currently, he is working as Assistant Professor in the Department of Biotechnology and Medical Engineering of National Institute of Technology Rourkela, India. Prior to join NIT Rourkela, he had worked as Assistant Professor at K L University, Andhra Pradesh. His area of interest is Medical Image Processing and Computer Vision. He has authored more than 10 articles in SCI indexed journals and conferences. Dr. Bala Chakravarthy has filed 2 patents in India and US and 1 of them was granted by US Patent Office. He has served as a Guest Editor of 2 reputed SCI journals and also served as a reviewer of several SCI and SCOPUS indexed journals.

Affiliations and expertise

Assistant Professor, Department of Biotechnology and Medical Engineering, National Institute of Technology Rourkela, India

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health

Computer-Aided Diagnosis (CAD) Tools and Applications for 3D Medical Imaging

Purchase options

Institutional subscription on ScienceDirect

Abhishek Gupta

Bala Chakravarthy Neelapu