Multidisciplinary Computational Anatomy: Toward Integration of Artificial Intelligence with MCA-based Medicine

Foreword
Preface
Contents
Part I: Introduction: Perspectives Toward MCA-Based Medicine
	1: From Geometric Models to AI in Computer-Assisted Interventions
		1.1	 Introduction
		1.2	 Prostate Cancer and the Introduction of Multiparametric MRI
			1.2.1	 A Statistical Shape Model of the Prostate for Registration of MR-Derived Information to Transrectal Ultrasound
			1.2.2	 A Multi-Scale Model of Pathology
			1.2.3	 Integration of AI Methods
		1.3	 Unmet Clinical Need: Laparoscopic Liver Surgery
			1.3.1	 Methodological Steps to a Comprehensive Image Guidance System for Laparoscopic Surgery
		1.4	 Discussion and Conclusion
		References
Part II: Basic Principles of MCA: Fundamental Theories and Techniques
	2: A Concept of Multidisciplinary Computational Anatomy (MCA)
		2.1	 Computational Anatomy
		2.2	 Multiplicity of Computational Anatomy
		2.3	 Data Representation Space for MCA
		2.4	 From Data Representation Space to Multi-Attribute Data Space
		2.5	 Goal of MCA
		2.6	 Challenge to “Comprehensive Understanding of the Human Body”
		References
	3: Construction of Multi-Resolution Model of Pancreas Tumor
		3.1	 Introduction
			3.1.1	 Data Description
			3.1.2	 Image Registration for the Description of Tumor Growth
			3.1.3	 3D Reconstruction of Microscopic Tumor Image
		3.2	 Construction of Multi-Resolution Model of Pancreatic Tumor Image
			3.2.1	 Summary
		References
	4: Fundamental Technologies for Integration of Multiscale Spatiotemporal Morphology in MCA
		4.1	 Introduction
		4.2	 Spatiotemporal Statistical Model of Time Series Data
			4.2.1	 Modelling with a Small Sample of Data
			4.2.2	 Modelling with Smoothness Constraint along a Time Axis
			4.2.3	 Modelling with Nested and Neighbouring Constraints
			4.2.4	 Modelling of Topological Changes along a Time Axis
		4.3	 Multiscale Model
			4.3.1	 Dictionary-Based Super-Resolution [7, 8]
			4.3.2	 Deep Learning-Based Super-Resolution [10]
			4.3.3	 Super-Resolution Problem under the Noisy Environment
		4.4	 Image Processing of Pathological Images
			4.4.1	 3D Tissue Structure from Pathological Images
			4.4.2	 Hyperspectral Image Processing of Pathological Images
		4.5	 Conclusion
		References
	5: Fundamental Technologies for Integration and Pathology in MCA
		5.1	 Introduction
		5.2	 AI-Based Segmentation and Cross-Modality Image Synthesis
		5.3	 High-Fidelity Anatomy Modeling for Functional Simulations
			5.3.1	 Constructing High-Fidelity Model Templates from Cadaver Cryosection Data
			5.3.2	 Patient-Specific Musculoskeletal High-Fidelity Modeling from Clinical Images
		5.4	 Functioning and Pathological Anatomy Modeling
			5.4.1	 Functioning Anatomy Modeling
			5.4.2	 Pathological Anatomy Modeling
		5.5	 Summary
		References
Part III: Basic Principles of MCA: Application Systems and Applied Techniques Based on MCA Model
	6: Pre-/Intra-operative Diagnostic and Navigational Assistance Based on Multidisciplinary Computational Anatomy
		6.1	 Introduction
		6.2	 MCA and Clinical Procedure Assistance
		6.3	 Macroscopic Anatomy and its Therapeutic Application
			6.3.1	 Macroscopic Anatomical Structure Analysis
			6.3.2	 Blood Vessel Recognition
			6.3.3	 Surgical Navigation
			6.3.4	 3D-Printed Anatomical Model
		6.4	 Colonoscopy Assistance Based on Macro- and Microanatomical Structure Analysis
		6.5	 Micro-Scale Anatomical Structure Segmentation
			6.5.1	 Micro-CT Images
			6.5.2	 Micro-Anatomical Structure Segmentation from Micro-CT Images of Lung Specimen
			6.5.3	 Super-Resolution of Clinical CT Images Based on Micro-CT Image Database
		6.6	 Conclusion
		References
	7: Cancer Diagnosis and Prognosis Assistance Based on MCA
		7.1	 Introduction
		7.2	 Three-Dimensional Lung Microstructure
		7.3	 Pulmonary Vascular System and Lymph Node System
		7.4	 Detection and Diagnosis of Early Lung Cancer Using Low-Dose CT Images and High-Resolution CT Images
			7.4.1	 Malignancy Prediction of Suspicious Nodule on Low-Dose CT Images
			7.4.2	 Prognosis Prediction of Lung Cancer on Thin-Section CT Images
		7.5	 Risk of Emphysematous Lesions by Long-Term Low-Dose 3D CT Images and Genetic Information and Airway Lesion Detection by High-Resolution 3D CT Images
		7.6	 Conclusion
		References
	8: Function Integrated Diagnostic Assistance Based on MCA Models
		8.1	 Introduction
		8.2	 Basic Techniques for Building Anatomical Models
			8.2.1	 Purpose
			8.2.2	 Method
			8.2.3	 Results
			8.2.4	 Conclusion
		8.3	 Analysis of Functional Imaging
			8.3.1	 Automated Evaluation of Tumour Activities on FDG-PET CT Images
				8.3.1.1	 Purpose
				8.3.1.2	 Methods
				8.3.1.3	 Results
				8.3.1.4	 Conclusion
			8.3.2	 Automated Detection of Lung Nodule in PET/CT Images
				8.3.2.1	 Purpose
				8.3.2.2	 Methods
				8.3.2.3	 Results and Conclusion
			8.3.3	 Recognizing Skeletal Muscle Regions for Muscle Function Analysis
				8.3.3.1	 Purpose
				8.3.3.2	 Method
				8.3.3.3	 Results
				8.3.3.4	 Conclusion
			8.3.4	 Knee Extension Strength Using Ultrasound Images
				8.3.4.1	 Purpose
				8.3.4.2	 Methods
				8.3.4.3	 Results
				8.3.4.4	 Conclusion
		8.4	 Other CAD Applications
			8.4.1	 Automated Malignancy Analysis in CT Images Using GAN
				8.4.1.1	 Purpose
				8.4.1.2	 Methods
				8.4.1.3	 Results
				8.4.1.4	 Conclusion
			8.4.2	 Automated Classification of Cytological Images Using CNN
				8.4.2.1	 Purpose
				8.4.2.2	 Methods
				8.4.2.3	 Results
				8.4.2.4	 Conclusion
			8.4.3	 Miscellaneous
				8.4.3.1	 CAD with Radiogenomics
				8.4.3.2	 Detection of Cardiovascular Disease Using Funduscopy
				8.4.3.3	 Detection and Classification of Teeth for Automatic Dental Record Filing
		8.5	 Summary
		References
Part IV: Basic Principles of MCA: Clinical and Scientific Application of MCA
	9: Clinical Applications of MCA to Surgery
		9.1	 Introduction
		9.2	 Application of MCA Model in the Research of Pancreatic Cancer
		9.3	 Clinical Application of MCA Model in Surgical Treatment
		9.4	 MCA-Based Surgical Processing Model (SPM)
		9.5	 Conclusion
		References
	10: Clinical Applications of MCA to Diagnosis
		10.1	 Introduction
		10.2	 Methods
			10.2.1	 Unsupervised Learning, Semi-Supervised Learning, and Transfer Learning for Efficient Training of Classifiers for DLD Opacities
			10.2.2	 Image Registration Techniques and Detection of Abnormalities on Temporal Subtraction Images
			10.2.3	 Optimization of Network Architecture for Deep Learning
			10.2.4	 Classification of Lung Tumors into Benign and Malignant Based on Medical Findings Using Deep Learning
			10.2.5	 EC for CTC
			10.2.6	 Establishment of 3D-Whole Lungs for Medical Image Investigation
		10.3	 Conclusion
		References
	11: Application of MCA across Biomedical Engineering
		11.1	 Introduction
		11.2	 Study on Stapler Device Control for Pancreatic Tissue Damage Suppression
			11.2.1	 Analysis of Pancreatic Injury Based on Mechanics and Pathology
			11.2.2	 Application to the Robotic Stapler and Future Work
		11.3	 Navigation and Robotic System for Oral and Maxillofacial Surgery
			11.3.1	 OMS Robot for Precise Positioning and Drilling with patient’s Specific Safety Mechanism
			11.3.2	 Markerless Navigation System for OMS
			11.3.3	 Integration of Navigation System for Compact Robot
			11.3.4	 Prospects for the Next OMS Robot and Navigation System
		11.4	 Conclusion
		References
Part V: New Frontier of Technology in Clinical Applications Based on MCA Models: Lifelong Human Growth
	12: Three-Dimensional Analyses of Human Organogenesis
		12.1	 Three-Dimensional Analysis of Human Development Using Histological Sections
		12.2	 3D Analysis of Human Development Using Imaging Modalities in High Resolution
			12.2.1	 Morphological Observations
			12.2.2	 Morphometry
			12.2.3	 Quantitative Analysis Using 3D Coordinates
			12.2.4	 Quantitative Movements (Differential Growth)
			12.2.5	 Shared Mechanism for Human Organogenesis (Branching Morphogenesis)
			12.2.6	 Information Concerning Physical and Structural Property
		12.3	 Perspective
			12.3.1	 Shift from Embryonic Period to Early-Fetal Period (9-12 Weeks after Fertilization)
			12.3.2	 Application to Prenatal Diagnosis
		References
	13: Skeletal System Analysis during the Human Embryonic Period Based on MCA
		13.1	 Introduction
		13.2	 Methods
		13.3	 Results
			13.3.1	 Rib Cage
			13.3.2	 Femur
			13.3.3	 Shoulder Girdle
		13.4	 Conclusion
		References
	14: MCA-Based Embryology and Embryo Imaging
		14.1	 History of Human Embryology, Embryo Collection, and Morphometrics
			14.1.1	 Human Embryo Collections
			14.1.2	 Classical Morphometrics Using Human Embryos and Fetuses
		14.2	 Imaging of Human Embryo and Fetus
			14.2.1	 Episcopic Fluorescence Image Capture
			14.2.2	 Magnetic Resonance Imaging, MR Microscopy
			14.2.3	 X-Ray Computed Tomography
		14.3	 Morphometrics of Human Embryos Using 3D Imaging
		References
	15: Modeling of Congenital Heart Malformations with a Focus on Topology
		15.1	 Modeling for Congenital Heart Malformation Focused on Topology
			15.1.1	 Introduction
			15.1.2	 Acquisition of Three-Dimensional Images of Congenital Heart Malformations
				15.1.2.1	 Acquisition of Microscopic Images
				15.1.2.2	 Acquisition of Macroscopic Images
				15.1.2.3	 Archiving of Images
			15.1.3	 Analysis of Heart Morphology and Topology
				15.1.3.1	 Segmentation and Visualization from Volume Data
				15.1.3.2	 Interactive Extraction of Graph-like Structure from Volume Data
			15.1.4	 Ontology of Congenital Heart Malformations
			15.1.5	 Conclusion
		References
Part VI: New Frontier of Technology in Clinical Applications Based on MCA Models: Tumor Growth
	16: A Technique for Measuring the 3D Deformation of a Multiphase Structure to Elucidate the Mechanism of Tumor Invasion
		16.1	 Introduction
		16.2	 Biomechanical Interaction between a Single Cancer Cell and the ECM
		16.3	 Biomechanical Interaction between Cancer Spheroids and the ECM
		16.4	 Conclusion
		References
	17: Construction of Classifier of Tumor Cell Types of Pancreas Cancer Based on Pathological Images Using Deep Learning
		17.1	 Introduction
		17.2	 Methods of Unsupervised Image Classification
		17.3	 Results
		17.4	 Discussion
		References
Part VII: New Frontier of Technology in Clinical Applications Based on MCA Models: Cranial Nervous System
	18: Multi-Modal and Multi-Scale Image Registration for Property Analysis of Brain Tumor
		18.1	 Introduction
		18.2	 Materials
		18.3	 Modality Conversion from Pathological Image to Ultrasonic Image
			18.3.1	 Construction of the Conversion Model
			18.3.2	 Studies of Modality Conversion and Image Registration
		18.4	 Property Analysis
			18.4.1	 Investigation of Effective Properties
			18.4.2	 Pathological Properties from Acoustic Characteristics
		18.5	 Conclusion
		References
	19: Brain MRI Image Analysis Technologies and its Application to Medical Image Analysis of Alzheimer’s Diseases
		19.1	 Introduction
		19.2	 Age Estimation Methods from T1-Weighted Images
		19.3	 Brain Local Features
		19.4	 Age Estimation Using 2D-CNN
		19.5	 Age Estimation Using 3D CNN
		19.6	 Performance Evaluation Using a Large-Scale Dataset
		19.7	 Analysis
		19.8	 Application to AD Identification
		19.9	 Conclusion
		References
	20: A Computer-Aided Support System for Deep Brain Stimulation by Multidisciplinary Brain Atlas Database
		20.1	 Introduction
		20.2	 Patient Brain Atlas Estimation by Deep Neural Networks
		20.3	 Brain Atlas Database Construction
			20.3.1	 Volumetric Self-Organizing Deformable Mode (vSDM)
		20.4	 Conclusion
		References
	21: Integrating Bio-metabolism and Structural Changes for the Diagnosis of Dementia
		21.1	 Introduction
		21.2	 Specific Points to Diagnose Dementia
		21.3	 Feature Values in a Functional Image
		21.4	 Statistical Modeling and Training Images
		21.5	 Conclusion
		References
	22: Normalized Brain Datasets with Functional Information Predict the Glioma Surgery
		22.1	 Introduction
		22.2	 Methods
		22.3	 Result
		22.4	 Discussion
			22.4.1	 Cortical Brain Mapping
			22.4.2	 Conversion of Digitized Information to Normalized Brain Data Format
			22.4.3	 Predictive Glioma Surgery Based on Database
		22.5	 Conclusion
		References
Part VIII: New Frontier of Technology in Clinical Applications Based on MCA Models: Cardio-respiratory System
	23: MCA Analysis for the Change in the Cardiac Fiber Orientation Under Congestive Heart Failure
		23.1	 Introduction
		23.2	 Materials and Methods
		23.3	 Results
		23.4	 Discussion
		23.5	 Conclusion
		References
	24: Computerized Evaluation of Pulmonary Function Based on the Rib and Diaphragm Motion by Dynamic Chest Radiography
		24.1	 Introduction
		24.2	 Dynamic Chest Radiography (DCR)
		24.3	 What Is Reflected on Dynamic Chest Radiographs?
			24.3.1	 Diaphragm Motion
			24.3.2	 Rib Motion
			24.3.3	 Pulmonary Ventilation and Circulation
		24.4	 Pulmonary Function Evaluation Based on MAC
		References
	25: Computer-Aided Diagnosis of Interstitial Lung Disease on High-Resolution CT Imaging Parallel to the Chest
		25.1	 Introduction
		25.2	 3D-cHRCT
		25.3	 Visual Assessment of ILDs
		25.4	 Visual Assessment of Lung Cancer
		25.5	 Quantification of Emphysema and IP by CAD
		25.6	 Conclusion
		References
	26: Postoperative Prediction of Pulmonary Resection Based on MCA Model by Integrating the Temporal Responses and Biomechanical Functions
		26.1	 Introduction
		26.2	 Methods
		26.3	 Results
		26.4	 Conclusion
		References
Part IX: New Frontier of Technology in Clinical Applications Based on MCA Models: Abdominal Organs
	27: Analysis in Three-Dimensional Morphologies of Hepatic Microstructures in Hepatic Disease
		27.1	 Morphology of 3D Microstructures in Hepatic Lobules
		27.2	 Reaction–Diffusion Algorithm for Segmentation of 3D Sinusoidal Networks
		27.3	 Developing an Index of Liver Disease Progression
		27.4	 Two-Layer Reaction–Diffusion Model for an Evaluation of Two Types of Networks
		27.5	 Future Outlook
		References
	28: Quantitative Evaluation of Fatty Metamorphosis and Fibrosis of Liver Based on Models of Ultrasound and Light Propagation and Its Application to Hepatic Disease Diagnosis
		28.1	 Introduction
		28.2	 Evaluation of Viscoelasticity Related to Fibrosis Structure
			28.2.1	 Evaluation of Shear Wave Dispersion
			28.2.2	 Mechanical Model Analysis of Liver Fibrosis
			28.2.3	 Analysis of Shear Wave Dispersion by Fibrous Structure
			28.2.4	 Tissues Viscoelasticity Evaluation by Shear Wave Propagation
		28.3	 Tissue Characterization of Fatty Liver Using Photoacoustic Imaging
		28.4	 Conclusion
		References
	29: MCA Analysis for Hepatology: Establishment of the In Situ Visualization System for Liver Sinusoid Analysis
		29.1	 Introduction
		29.2	 Animal Preparation
		29.3	 Structure of the In Situ Video Microscopic System
		29.4	 Observation of the Sinusoidal Flow
		29.5	 Examples of Sinusoidal Flow Analysis
		29.6	 Conclusion
		References
	30: Simulation Surgery for Hepatobiliary-Pancreatic Surgery
		30.1	 Introduction
		30.2	 Progress of 3D Medical Image Processing and 3D Surgical Simulation
		30.3	 3D Surgical Simulation for Liver Surgery
			30.3.1	 Liver Resection Simulation Using SYNAPSE VINCENT
			30.3.2	 Utilization of Our Original 3D Printing for Surgery
		30.4	 Development of Our Original Hepatectomy Simulation Software
			30.4.1	 3D Virtual Hepatectomy Simulation Combined with Real-Time Deformation, “Liversim”
			30.4.2	 Intraoperative Navigation Using Liversim
		30.5	 Movement to Navigation Surgery
		30.6	 Development of Our Original Hepatectomy Navigation System
			30.6.1	 Original 3D Reconstruction of Surgical Field and Development of Surgical Navigation System
			30.6.2	 Configuration of the Novel 3D Captured Liver Resection Navigation System
			30.6.3	 Clinical Application of the Novel 3D Captured Liver Resection Navigation System
		30.7	 Development of Our Original Simulation for Biliary-Pancreatic Surgery
			30.7.1	 Surgical Simulation for Biliary-Pancreatic Surgery
			30.7.2	 Surgical Simulation for Biliary-Pancreatic Surgery
			30.7.3	 Usefulness of 3D Simulation in Pancreatic Resection
			30.7.4	 Deformable Pancreatectomy Simulation
		30.8	 Conclusion
		References
Part X: New Frontier of Technology in Clinical Applications Based on MCA Models: Musculoskeletal System
	31: Development of Multiple Skeletal Muscle Recognition Technique in the Thoracoabdominal Region for Respiratory Muscle Function Analysis
		31.1	 Introduction
		31.2	 Model Generation for Respiratory Muscle Function Analysis
		31.3	 Automated Segmentation of the Erector Spinae Muscle in Torso CT Images and Its Segmentation Based on Muscle Bundle Model
		31.4	 Current Status and Future Issues in Thoracoabdominal Skeletal Muscle Recognition
		31.5	 Conclusion
		References
	32: Morphometric Analysis for the Morphogenesis of the Craniofacial Structures and the Evolution of the Nasal Protrusion in Humans
		32.1	 Introduction
			32.1.1	 Nasal Protrusion in Humans
			32.1.2	 Nasal Septum Development in Human Ontogeny
			32.1.3	 Two-Dimensional Morphometric Analysis for Nasal Septum Growth Allometry
			32.1.4	 Nasal Protrusion
			32.1.5	 Morphogenesis of the Mid-Face
			32.1.6	 Traditional Morphometric Studies for the Mid-Facial Development
			32.1.7	 Three-Dimensional Morphometric Analysis for the Mid-Facial Development
			32.1.8	 Ontogenetic Allometry of the Face
		References
	33: Development of Bone Strength Prediction Method by Using MCA with Damage Mechanics
		33.1	 Introduction
		33.2	 Deformation Analysis of μ-CT Image-Based Cancellous Bone Model
		33.3	 Comparison of CT-FEA with Cadaveric Experiment
		33.4	 Analysis of Correlation Between Vertebra Strength and Lumbar YAM
		33.5	 Conclusions
		References
Part XI: New Frontier of Technology in Clinical Applications Based on MCA Models: Emerging Innovasive Imaging Technology
	34: Development of a Generation Method for Local Appearance Models of Normal Organs by DCNN
		34.1	 Introduction
		34.2	 Detection of Abnormalities in Head CT Volumes
			34.2.1	 Methods
				34.2.1.1	 Construction of Our Autoencoder
				34.2.1.2	 Patch Extraction
				34.2.1.3	 Training Process
				34.2.1.4	 Evaluation Process
				34.2.1.5	 Dataset
			34.2.2	 Results
			34.2.3	 Discussion
			34.2.4	 Conclusion
		34.3	 Abnormality Detection System for Chest FDG-PET-CT Images
		34.4	 Residual Network–Based Unsupervised Temporal Image Subtraction For Highlighting Bone Metastases
			34.4.1	 Purpose
			34.4.2	 Methods
			34.4.3	 Results
			34.4.4	 Conclusion
		References
	35: Comprehensive Modeling of Neonatal Brain Image Generation for Disorder Development Onset Prediction Based on Generative Adversarial Networks
		35.1	 Introduction
		35.2	 Preliminary
			35.2.1	 Generated Adversarial Network
		35.3	 Method
			35.3.1	 Data Preprocessing
			35.3.2	 PGGAN Implementation
		35.4	 Experiment
			35.4.1	 Experimental Settings
			35.4.2	 Result
		35.5	 Conclusion
		References
	36: Prediction of Personalized Postoperative Implanted Knee Kinematics with Statistical Temporal Modeling
		36.1	 Introduction
		36.2	 Kinematics Measurement Using CT-Free Navigation System
		36.3	 Method
			36.3.1	 Feature Extraction
			36.3.2	 Machine Learning Algorithms
				36.3.2.1	 Generalized Linear Regression
				36.3.2.2	 Artificial Neural Network (ANN)
				36.3.2.3	 Support Vector Regression
			36.3.3	 Postoperative Kinematics Prediction
		36.4	 Experimental Study
			36.4.1	 Subjects and Dataset
			36.4.2	 Experiments
		36.5	 Results and Discussion
		36.6	 Concluding Remarks
		References
	37: Sparse Modeling in Analysis for Multidisciplinary Medical Data
		37.1	 Introduction
		37.2	 Sparse Modeling-Based BoVW
		37.3	 Tensor Sparse Modeling-Based BoVW
			37.3.1	 Tensor Codebook Learning
			37.3.2	 FLL Spatiotemporal Feature Extraction Using Tensor Sparse Modeling
			37.3.3	 Results
		37.4	 Conclusion
		References
	38: Super Computing: Creation of  Large-Scale and High-Performance Technology for Processes of MCA by Utilizing Supercomputers
		38.1	 Introduction
		38.2	 LDDMM Code
		38.3	 Parallelization Method
			38.3.1	 MPI Process Parallelization
		38.4	 OpenMP Thread Parallelization and Loop Collapses for Code Optimization
		38.5	 Performance Evaluation
			38.5.1	 Computer Environments
			38.5.2	 Problem Size and Estimated Execution Time for Final Target
			38.5.3	 Results and Discussion
		38.6	 Conclusion
		References
	39: MRI: Quantitative Evaluation of Diseased Tissue by Viscoelastic Imaging Systems
		39.1	 Introduction
			39.1.1	 Development of a Tissue-Mimicking Viscoelastic Phantom for Quantitative Assessment of MRE
			39.1.2	 Ultrasound-Based Shear-Wave Speed Measurement on a Highly Viscous Embedded Phantom
		39.2	 Results
			39.2.1	 Development of a Tissue-Mimicking Viscoelastic Phantom for Quantitative Assessment of MRE
			39.2.2	 Ultrasound-Based Shear-Wave Speed Measurement on a Highly Viscous Embedded Phantom
		39.3	 Conclusion
		References
	40: US: Development of General Biophysical Model for Realization of Ultrasonic Qualitative Real-Time Pathological Diagnosis
		40.1	 Introduction
		40.2	 SoS Evaluation in High Resolution and High Region Using New SAM
		40.3	 Evaluation of Frequency Dependency and Tissue Structure Dependency of SoS
		40.4	 Conclusion
		References
	41: OCT: Ultrahigh Resolution Optical Coherence Tomography at Visible to Near-Infrared Wavelength Region
		41.1	 Introduction
		41.2	 Time and Fourier-Domain OCT
		41.3	 Ultrahigh-Resolution OCT in the 0.8 μm Wavelength Window and Retinal Imaging
		41.4	 Ultrahigh-Resolution OCT in the 1.7 μm Wavelength Window
		41.5	 Future Direction
		References
	42: MRI: Magnetic Resonance Q-Space Imaging Using Generating Function and Bayesian Inference
		42.1	 Introduction
		42.2	 Theory
			42.2.1	 DKI Algorithm
			42.2.2	 Maximum Likelihood (ML) Estimation
			42.2.3	 Bayesian Estimation
			42.2.4	 Statistic Signal Errors and Prior Distribution
			42.2.5	 Updating of Prior Distribution and Successive Estimation
		42.3	 Method
			42.3.1	 Human Data Study
			42.3.2	 Numerical Phantom Study
		42.4	 Results
		42.5	 Discussion
		42.6	 Conclusions
		References
	43: Micro-CT and Lungs
		43.1	 Micro-CT and Lungs
		43.2	 Motivation and Findings of Study
		43.3	 Precision of Images
		43.4	 Histological Diagnosis of Lung Cancer Using Micro-CT Imaging
		43.5	 Micro-CT Playing a Role in Filling the Gap Between HRCT Images and Histopathological Images
			43.5.1	 Future of Micro-CT and the Lungs
		43.6	 Conclusion
		References
	44: Real-Time Endoscopic Computer Vision Technologies and Their Applications That Help Improve the Level of Autonomy of Surgical Assistant Robots
		44.1	 Introduction
		44.2	 Technology I: Calculation of Depths
		44.3	 Technology II: Instrument Tracking
		44.4	 Application I: Controlling a Surgical Instrument-Holding Robot
		44.5	 Application II: A Tip Load Calculation System for Surgical Instruments
		44.6	 Conclusion
		References
	45: Endoscopy: Computer-Aided Diagnostic System Based on Deep Learning Which Supports Endoscopists’ Decision-Making on the Treatment of Colorectal Polyps
		45.1	 Interpretation of Endoscopic Images: Challenging!
		45.2	 AI Tools in Colonoscopy
			45.2.1	 Automated Polyp Detection
			45.2.2	 Prediction of Polyp Pathology
				45.2.2.1	 AI Designed for Magnified Endoscopy
				45.2.2.2	 AI Designed for Endocytoscopy
				45.2.2.3	 AI for Autofluorescence Endoscopy
				45.2.2.4	 AI Designed for Conventional Endoscopy
			45.2.3	 Predicting Invasion Depth
		45.3	 Regulatory Approval of AI Tools in Colonoscopy
		45.4	 Role of the Research Topic in the Concept of Multidisciplinary Computational Anatomy (MCA)
		45.5	 Summary
		References
	46: Endoscopy: Application of MCA Modeling to Abnormal Nerve Plexus in the GI Tract
		46.1	 Introduction
		46.2	 ENS Visualization with CV-Assisted CLE
		46.3	 ENS Visualization of Hirschsprung’s Disease
		46.4	 Existing Technical Limitations and Future Perspectives for the ENS Observation with CLE
		46.5	 Conclusion
		References
	47: Optical Fluorescence: Application of Structured Light Illumination and Compressed Sensing to High-speed Laminar Optical Fluorescence Tomography
		47.1	 Introduction
		47.2	 Methods
			47.2.1	 Compressed Laminar Optical Tomography (CLOT)
			47.2.2	 Simulation Study
			47.2.3	 Experimental System of CLOT for Optical Phantom Study [10]
		47.3	 Results and Discussion
			47.3.1	 Simulation Study
			47.3.2	 Optical Phantom Study
		47.4	 Conclusion
		References
	48: Magneto-stimulation System for Brain Based on Medical Images
		48.1	 Introduction
		48.2	 Modeling Methods
			48.2.1	 Development of Human Head Models
			48.2.2	 Computational Electromagnetic Method
			48.2.3	 Experimental Protocol
		48.3	 Evaluation of TMS Coils
		48.4	 High-Accurate TMS Localization
			48.4.1	 Localization Method
			48.4.2	 Localization in Healthy Hemisphere
			48.4.3	 Localization in Hemisphere Containing Tumor
		48.5	 Conclusion
		References
	49: AI: A Machine-Learning-Based Framework for Developing Various Computer-Aided Detection Systems with Generated Image Features
		49.1	 Introduction
		49.2	 Generalized Framework for Developing CADe Systems
		49.3	 Feature Generation Using Multiple Deep Convolutional Autoencoders
		49.4	 Feature Extraction Using the Deep Convolutional Neural Network Pretrained with Local Anatomical Structures in Medical Images
		49.5	 Conclusion
		References
	50: Radiomics: Artificial Intelligence-Based Radiogenomic Diagnosis of Gliomas
		50.1	 The Necessity of Radiomics in Glioma Treatment
		50.2	 IDH Mutation and 1p19q Co-deletion as Prognostic Biomarkers in Lower-Grade Gliomas
		50.3	 Radiological Determination of IDH Mutation and 1p19q Co-deletion in LrGG
		50.4	 Radiomics for Gliomas; the Basic Methods
		50.5	 Current Limitation and Future Direction of Radiogenomics
		References
	51: 4D—Four-Dimensional Dynamic Images: Principle and Future Application
		51.1	 4D imaging
		51.2	 Trial for Measurement of 4D Phenomenon
		51.3	 Development of a 4D Human Body Model with Dynamic Deformation
		51.4	 4D Observation of Human Body Motion by DSVC
		51.5	 4D Visualization of Body Surface and Skeleton Dynamics by DSVC
		51.6	 Understanding the 4D Change that Occurs Over a Long Period of Time
		51.7	 Conclusion
		References
	52: Cloud XR (Extended Reality: Virtual Reality, Augmented Reality, Mixed Reality) and 5G Mobile Communication System for Medical Image-Guided Holographic Surgery and Telemedicine
		52.1	 Introduction
		52.2	 Methods
		52.3	 Results and Discussions
			52.3.1	 XR in Spatial Diagnostic Imaging and Image-Guided Surgery
			52.3.2	 Online Telemedicine and Remote Space Sharing Using Cloud XR and 5G
			52.3.3	 Medical Education and Training Through XR
		52.4	 Prospects for Cloud XR Medicine
		52.5	 Conclusion
		References
	53: Smart Cyber Operating Theater (SCOT): Strategy for Future OR
		53.1	 Introduction
		53.2	 Smart Cyber Operating Theater (SCOT)
			53.2.1	 Overview and Development Requirements
			53.2.2	 The Predecessor Intelligent Operating Room and Packaged Basic Smart Treatment Room (Basic SCOT)
			53.2.3	 Networked Standard SCOT
			53.2.4	 Robotized High-performance Smart Treatment Room Hyper-SCOT
		53.3	 Internet of Things and Artificial Intelligence Utilization in SCOT
		53.4	 Summary
		References
Supplement