Linked e-resources
Details
Table of Contents
Intro
Editor biographies
Varut Vardhanabhuti
Ka-Wai Kwok
Jason Y K Chan
Qi Dou
List of contributors
Chapter Machine learning in medicine-focus on radiology
1.1 Artificial intelligence in radiology imaging
1.1.1 Object segmentation
1.1.2 Abnormality detection
1.1.3 Abnormality characterisation
1.1.4 Outcome prediction
1.1.5 Challenges and opportunities
1.2 AI in learning radiology reports
1.2.1 Automatic data mining on text report
1.2.2 Automatically radiology report generation system
1.3 AI in radiology practice
1.3.1 Improving radiographic workflow
1.3.2 Improving radiology workflow
1.3.3 Improving radiology education
1.3.4 Challenges, risks, and future of AI in radiology
References
Chapter Machine learning: applications in ophthalmology
2.1 Introduction
2.2 Convolutional neural networks-basic architecture
2.2.1 Convolution layers
2.2.2 Pooling layers
2.2.3 Fully connected layers
2.2.4 Network training
2.3 Current applications of DL in ophthalmology
2.3.1 Retinal disorders/fundus images
2.3.2 Optical coherence tomography images
2.4 Conclusions
References
Chapter Artificial intelligence clinical applications of wearable technologies
3.1 Wearable devices: healthcare sensors blended into everyday life
3.2 Deep learning enables artificial intelligence applications of wearable devices
3.3 Federated and transfer learning boost performance of health AI applications
3.4 Current healthcare applications of AI and wearable technology
3.5 Practical considerations, challenges, and future of wearable technologies in healthcare
Acknowledgment
References
Chapter Artificial intelligence in dentistry and oral health
4.1 Automatic tooth segmentation
4.2 AI in designing dental crown and dental inlay surface.
4.3 AI in dental implant planning
4.4 Predicting the lifespan of dental implants
4.5 AI to identify marginal bone loss prediction
4.6 AI for early diagnosis of oral cancer
4.7 AI in cariology and endodontics
4.8 AI in orthodontics
4.9 Prosthesis color matching
4.10 Predicting facial changes
4.11 Discussion and limitation
References
Chapter Artificial intelligence applications in pathology
5.1 Histopathology and cytopathology-new era in image analysis
5.1.1 What are histopathology and cytology?
5.1.2 Whole slide imaging as a new form of medical image
5.1.3 Common image processing techniques used in WSI analysis
5.1.4 Application in clinical pathology
5.1.5 Limitations and concerns
5.2 Chemical pathology-treasures within high dimension structured data
5.2.1 What is chemical pathology?
5.2.2 Application of AI in general chemistry
5.2.3 AI in the diagnosis of metabolic diseases
5.2.4 AI in the field of genetics
5.2.5 Ending remarks
5.3 Clinical microbiology-application in the management of infectious diseases
5.3.1 What is clinical microbiology?
5.3.2 Integration of AI in clinical microbiology
5.3.3 Applications of AI in microscopy
5.3.4 Applications of AI in culture plate reading and microbial identification
5.3.5 Applications of AI in susceptibility testing
5.3.6 Insights in future deployment
References
Chapter Artificial intelligence-powered imaging-based diagnostic tools for ageing and longevity
6.1 Introduction-healthspan, lifespan, and longevity concept
6.2 Diagnostics aspects of ageing
6.3 The need for more specificity-organ or region-based ageing clocks
6.3.1 Organ-based information
6.3.2 Region-based assessment for ageing
6.3.3 Physical activity and wearables devices
6.4 Concluding remarks
References.
Chapter Intra-operative image-guided interventional robotics-where are we now and where are we going?
7.1 Introduction
7.2 Medical imaging advances
7.2.1 CT
7.2.2 MRI
7.2.3 Ultrasound
7.3 State-of-the-art in surgical treatments
7.3.1 Stereotactic neurosurgery
7.3.2 Biopsy in prostate and breast
7.3.3 Abdominopelvic treatment
7.3.4 Cardiovascular catheterization
7.4 Key advanced technologies
7.4.1 Localization and tracking of robots
7.4.2 Surgical robot mounting and actuation mechanisms
7.5 Discussion and conclusion
7.6 Disclosure statements
References
Chapter Surgical applications in medical artificial intelligence
8.1 Introduction
8.1.1 What is artificial intelligence?
8.1.2 The short but splendid history of AI in medicine
8.2 AI subfields and their applications in clinical medicine
8.2.1 Machine learning
8.2.2 Deep learning and artificial neural network
8.2.3 Natural language processing
8.2.4 Computer vision
8.3 AI in endoscopy
8.3.1 Alleviate the experience inequity of the endoscopists
8.3.2 Improve the detection and differentiation ability
8.3.3 How to further modify computer-assisted systems?
8.4 AI in surgery for optimization
8.4.1 Preoperative: comprehensive evaluation leads to the optimized strategies
8.4.2 Intraoperative: leaps and bounds in surgery
8.4.3 Postoperative: prescient care and surgical education in the future
8.5 Future of AI in surgery: Integration of images, surgeons, and robots for autonomous robotic surgery
8.5.1 Start with the operation room
8.5.2 The valley of death between the trials and clinical work
8.6 Conclusion
References
Chapter Technical innovations to improve artificial intelligence generalizability of automated medical image diagnosis for clinical practice
9.1 Introduction.
9.2 Clinical application areas of model generalizability in current literature
9.3 Technical tasks in medical image analysis prone to data heterogeneity
9.4 Technical approaches for AI model adaptation and generalization
9.5 Distributed privacy-preserving techniques with data heterogeneity
9.5.1 Federated model training under internal data heterogeneity
9.5.2 Federated domain generalization for testing under external data heterogeneity
9.6 Discussion and summary
Acknowledgments
References.
Editor biographies
Varut Vardhanabhuti
Ka-Wai Kwok
Jason Y K Chan
Qi Dou
List of contributors
Chapter Machine learning in medicine-focus on radiology
1.1 Artificial intelligence in radiology imaging
1.1.1 Object segmentation
1.1.2 Abnormality detection
1.1.3 Abnormality characterisation
1.1.4 Outcome prediction
1.1.5 Challenges and opportunities
1.2 AI in learning radiology reports
1.2.1 Automatic data mining on text report
1.2.2 Automatically radiology report generation system
1.3 AI in radiology practice
1.3.1 Improving radiographic workflow
1.3.2 Improving radiology workflow
1.3.3 Improving radiology education
1.3.4 Challenges, risks, and future of AI in radiology
References
Chapter Machine learning: applications in ophthalmology
2.1 Introduction
2.2 Convolutional neural networks-basic architecture
2.2.1 Convolution layers
2.2.2 Pooling layers
2.2.3 Fully connected layers
2.2.4 Network training
2.3 Current applications of DL in ophthalmology
2.3.1 Retinal disorders/fundus images
2.3.2 Optical coherence tomography images
2.4 Conclusions
References
Chapter Artificial intelligence clinical applications of wearable technologies
3.1 Wearable devices: healthcare sensors blended into everyday life
3.2 Deep learning enables artificial intelligence applications of wearable devices
3.3 Federated and transfer learning boost performance of health AI applications
3.4 Current healthcare applications of AI and wearable technology
3.5 Practical considerations, challenges, and future of wearable technologies in healthcare
Acknowledgment
References
Chapter Artificial intelligence in dentistry and oral health
4.1 Automatic tooth segmentation
4.2 AI in designing dental crown and dental inlay surface.
4.3 AI in dental implant planning
4.4 Predicting the lifespan of dental implants
4.5 AI to identify marginal bone loss prediction
4.6 AI for early diagnosis of oral cancer
4.7 AI in cariology and endodontics
4.8 AI in orthodontics
4.9 Prosthesis color matching
4.10 Predicting facial changes
4.11 Discussion and limitation
References
Chapter Artificial intelligence applications in pathology
5.1 Histopathology and cytopathology-new era in image analysis
5.1.1 What are histopathology and cytology?
5.1.2 Whole slide imaging as a new form of medical image
5.1.3 Common image processing techniques used in WSI analysis
5.1.4 Application in clinical pathology
5.1.5 Limitations and concerns
5.2 Chemical pathology-treasures within high dimension structured data
5.2.1 What is chemical pathology?
5.2.2 Application of AI in general chemistry
5.2.3 AI in the diagnosis of metabolic diseases
5.2.4 AI in the field of genetics
5.2.5 Ending remarks
5.3 Clinical microbiology-application in the management of infectious diseases
5.3.1 What is clinical microbiology?
5.3.2 Integration of AI in clinical microbiology
5.3.3 Applications of AI in microscopy
5.3.4 Applications of AI in culture plate reading and microbial identification
5.3.5 Applications of AI in susceptibility testing
5.3.6 Insights in future deployment
References
Chapter Artificial intelligence-powered imaging-based diagnostic tools for ageing and longevity
6.1 Introduction-healthspan, lifespan, and longevity concept
6.2 Diagnostics aspects of ageing
6.3 The need for more specificity-organ or region-based ageing clocks
6.3.1 Organ-based information
6.3.2 Region-based assessment for ageing
6.3.3 Physical activity and wearables devices
6.4 Concluding remarks
References.
Chapter Intra-operative image-guided interventional robotics-where are we now and where are we going?
7.1 Introduction
7.2 Medical imaging advances
7.2.1 CT
7.2.2 MRI
7.2.3 Ultrasound
7.3 State-of-the-art in surgical treatments
7.3.1 Stereotactic neurosurgery
7.3.2 Biopsy in prostate and breast
7.3.3 Abdominopelvic treatment
7.3.4 Cardiovascular catheterization
7.4 Key advanced technologies
7.4.1 Localization and tracking of robots
7.4.2 Surgical robot mounting and actuation mechanisms
7.5 Discussion and conclusion
7.6 Disclosure statements
References
Chapter Surgical applications in medical artificial intelligence
8.1 Introduction
8.1.1 What is artificial intelligence?
8.1.2 The short but splendid history of AI in medicine
8.2 AI subfields and their applications in clinical medicine
8.2.1 Machine learning
8.2.2 Deep learning and artificial neural network
8.2.3 Natural language processing
8.2.4 Computer vision
8.3 AI in endoscopy
8.3.1 Alleviate the experience inequity of the endoscopists
8.3.2 Improve the detection and differentiation ability
8.3.3 How to further modify computer-assisted systems?
8.4 AI in surgery for optimization
8.4.1 Preoperative: comprehensive evaluation leads to the optimized strategies
8.4.2 Intraoperative: leaps and bounds in surgery
8.4.3 Postoperative: prescient care and surgical education in the future
8.5 Future of AI in surgery: Integration of images, surgeons, and robots for autonomous robotic surgery
8.5.1 Start with the operation room
8.5.2 The valley of death between the trials and clinical work
8.6 Conclusion
References
Chapter Technical innovations to improve artificial intelligence generalizability of automated medical image diagnosis for clinical practice
9.1 Introduction.
9.2 Clinical application areas of model generalizability in current literature
9.3 Technical tasks in medical image analysis prone to data heterogeneity
9.4 Technical approaches for AI model adaptation and generalization
9.5 Distributed privacy-preserving techniques with data heterogeneity
9.5.1 Federated model training under internal data heterogeneity
9.5.2 Federated domain generalization for testing under external data heterogeneity
9.6 Discussion and summary
Acknowledgments
References.