Holiday book sale: Save up to 30% on print and eBooks. No promo code needed.
Save up to 30% on print and eBooks.
Biomedical Image Synthesis and Simulation
Methods and Applications
1st Edition - June 18, 2022
Editors: Ninon Burgos, David Svoboda
Paperback ISBN:9780128243497
9 7 8 - 0 - 1 2 - 8 2 4 3 4 9 - 7
eBook ISBN:9780128243503
9 7 8 - 0 - 1 2 - 8 2 4 3 5 0 - 3
Biomedical Image Synthesis and Simulation: Methods and Applications presents the basic concepts and applications in image-based simulation and synthesis used in medical and… Read more
Purchase options
LIMITED OFFER
Save 50% on book bundles
Immediately download your ebook while waiting for your print delivery. No promo code is needed.
Biomedical Image Synthesis and Simulation: Methods and Applications presents the basic concepts and applications in image-based simulation and synthesis used in medical and biomedical imaging. The first part of the book introduces and describes the simulation and synthesis methods that were developed and successfully used within the last twenty years, from parametric to deep generative models. The second part gives examples of successful applications of these methods. Both parts together form a book that gives the reader insight into the technical background of image synthesis and how it is used, in the particular disciplines of medical and biomedical imaging. The book ends with several perspectives on the best practices to adopt when validating image synthesis approaches, the crucial role that uncertainty quantification plays in medical image synthesis, and research directions that should be worth exploring in the future.
Gives state-of-the-art methods in (bio)medical image synthesis
Explains the principles (background) of image synthesis methods
Presents the main applications of biomedical image synthesis methods
Graduate students and researchers in medical imaging
Cover image
Title page
Table of Contents
Copyright
Contributors
Preface
Chapter 1: Introduction to medical and biomedical image synthesis
Abstract
Part 1: Methods and principles
Chapter 2: Parametric modeling in biomedical image synthesis
Abstract
Acknowledgements
2.1. Introduction
2.2. Parametric modeling paradigm
2.3. On learning the parameters
2.4. Use cases
2.5. Future directions
2.6. Summary
References
Chapter 3: Monte Carlo simulations for medical and biomedical applications
Abstract
3.1. Introduction
3.2. Underlying theory and principles
3.3. Particle transport through matter
3.4. Monte Carlo simulation structure
3.5. Running a Monte Carlo simulation
3.6. Improving Monte Carlo simulation efficiency
3.7. Examples of Monte Carlo simulation applications in medical physics
3.8. Monte Carlo simulation for computational biology
3.9. Summary
References
Chapter 4: Medical image synthesis using segmentation and registration
Abstract
Acknowledgements
4.1. Introduction
4.2. Segmentation-based image synthesis
4.3. Registration-based image synthesis
4.4. Hybrid approaches combining segmentation and registration
4.5. Future directions and research challenges
4.6. Summary
References
Chapter 5: Dictionary learning for medical image synthesis
Abstract
Acknowledgements
5.1. Introduction
5.2. Sparse coding
5.3. Dictionary learning
5.4. Medical image synthesis with dictionary learning
5.5. Future directions and research challenges
5.6. Summary
References
Chapter 6: Convolutional neural networks for image synthesis
Abstract
6.1. Convolutional neural networks for image synthesis
6.2. Neural network building blocks
6.3. Training a convolutional neural network
6.4. Practical aspects
6.5. Commonly known networks
6.6. Conclusion
References
Chapter 7: Generative adversarial networks for medical image synthesis
Abstract
Disclosures
7.1. Introduction
7.2. Generative adversarial networks
7.3. Conditional GANs
7.4. Cycle GAN
7.5. Practical aspects
7.6. CGAN and Cycle-GAN applications
7.7. Summary and discussion
References
Chapter 8: Autoencoders and variational autoencoders in medical image analysis
Abstract
8.1. Introduction
8.2. Autoencoders
8.3. Variational autoencoders
8.4. Example applications
8.5. Future directions and research challenges
8.6. Summary
References
Part 2: Applications
Chapter 9: Optimization of the MR imaging pipeline using simulation
Abstract
9.1. Overview
9.2. History of MRI simulation
9.3. The POSSUM simulation framework
9.4. Applications
9.5. Future directions and research challenges
References
Chapter 10: Synthesis for image analysis across modalities
Abstract
10.1. General motivation
10.2. Registration
10.3. Segmentation
10.4. Other directions and perspectives
References
Chapter 11: Medical image harmonization through synthesis
Abstract
11.1. Introduction
11.2. Supervised techniques
11.3. Unsupervised techniques
References
Chapter 12: Medical image super-resolution with deep networks
Abstract
12.1. Introduction to super-resolution
12.2. SR methods with deep networks
12.3. Applications of super-resolution in medical images
12.4. Conclusions
References
Chapter 13: Medical image denoising
Abstract
13.1. Introduction
13.2. Denoising approaches
13.3. Evaluation metrics
13.4. Examples of applications
13.5. Summary
References
Chapter 14: Data augmentation for medical image analysis
Abstract
14.1. Introduction
14.2. Traditional methods for augmentation
14.3. Synthesis-based methods
14.4. Case study: data augmentation for retinal vessel segmentation
14.5. Research challenges and future work
14.6. Summary
References
Chapter 15: Unsupervised abnormality detection in medical images with deep generative methods
Abstract
15.1. Overview
15.2. Generative methods for unsupervised abnormality detection
15.3. Application on real-world abnormalities
15.4. Discussion
References
Chapter 16: Regularizing disentangled representations with anatomical temporal consistency
Abstract
Acknowledgements
16.1. Introduction
16.2. Related work
16.3. Methods
16.4. Experiments
16.5. Results and discussion
16.6. Conclusion
References
Chapter 17: Image imputation in cardiac MRI and quality assessment
Abstract
Acknowledgements
17.1. Introduction
17.2. Image imputation strategies
17.3. Image imputation via conditional GAN
17.4. Evaluation
17.5. Research challenges and future directions
17.6. Summary
References
Chapter 18: Image synthesis for low-count PET acquisitions: lower dose, shorter time
Abstract
18.1. Introduction to low-count imaging
18.2. Significance of low-count imaging
18.3. Overview of methods and examples
18.4. Future directions and research challenges
18.5. Summary
References
Chapter 19: PET/MRI attenuation correction
Abstract
19.1. Correction of photon attenuation
19.2. Implications of inaccurate attenuation correction
19.3. History of PET/MRI attenuation correction
19.4. Comparison of attenuation correction methods
Chapter 20: Image synthesis for MRI-only radiotherapy treatment planning
Abstract
20.1. Introduction
20.2. External beam radiation therapy summary
20.3. Planning CT image acquisition
20.4. Planning MRI acquisition
20.5. Methods used for sCT generation
20.6. Validation (with matching CT)
20.7. Quality control (without matching CT)
20.8. Deployment
20.9. Summary
References
Chapter 21: Review of cell image synthesis for image processing
Abstract
Acknowledgements
21.1. Introduction
21.2. History
21.3. Contemporary applications
21.4. Summary
21.5. Future work
References
Chapter 22: Generative models for synthesis of colorectal cancer histology images
Abstract
22.1. Introduction
22.2. Literature review
22.3. Colorectal cancer tissue structure
22.4. Model of spatial tumor heterogeneity
22.5. Deep learning based colorectal pathology image generation
22.6. Comparison
22.7. Research challenges & future directions
References
Chapter 23: Spatiotemporal image generation for embryomics applications
Abstract
Acknowledgements
23.1. Introduction
23.2. Spatiotemporal simulation of virtual agents with realistic movement behavior
23.3. Example applications
23.4. Future directions and research challenges
23.5. Summary
References
Further reading
Chapter 24: Biomolecule trafficking and network tomography-based simulations
Abstract
Acknowledgement
24.1. Motivation
24.2. Simulation for biomolecule trafficking analysis
24.3. Applications
24.4. Conclusion, future directions, and new challenges
24.5. Summary
References
Further reading
Part 3: Perspectives
Chapter 25: Validation and evaluation metrics for medical and biomedical image synthesis
Abstract
Acknowledgement
25.1. Introduction
25.2. Expert knowledge
25.3. Pairwise comparison
25.4. Dataset comparison
25.5. Conclusion
References
Chapter 26: Uncertainty quantification in medical image synthesis
Abstract
26.1. Introduction
26.2. Troublesome uncertainty landscape
26.3. Tools for modeling uncertainty
26.4. Open challenges
26.5. Concluding remarks
References
Chapter 27: Future trends in medical and biomedical image synthesis
Abstract
Index
No. of pages: 674
Language: English
Published: June 18, 2022
Imprint: Academic Press
Paperback ISBN: 9780128243497
eBook ISBN: 9780128243503
NB
Ninon Burgos
Ninon Burgos is a CNRS researcher at the Paris Brain Institute, in the ARAMIS Lab, and a fellow of PR[AI]RIE, the Paris Artificial Intelligence Research Institute, France. She completed her PhD at University College London, UK, with a thesis on image synthesis for the attenuation correction and analysis of hybrid positron emission tomography/magnetic resonance imaging data. In 2019, she received the ERCIM Cor Baayen Young Researcher Award. Her research focuses on the processing and analysis of medical images, the use of images to guide the diagnosis of neurological diseases, and the application of these methods to the clinic.
Affiliations and expertise
CNRS Researcher, Brain and Spine Institute (ICM), ARAMIS Lab, Paris, France
DS
David Svoboda
David Svoboda is an associate professor at the Department of visual computing of the Faculty of Informatics, Masaryk University, Brno, Czech Republic. He completed his PhD in computer science with a thesis on segmentation of volumetric histopathological images. He spent a half-year research visit at Manchester Metropolitan University, Manchester, UK, in the signal processing group, where he focused on the problems on edge detection using the statistics-based filtering. Since 2006, he has been with the Centre for Biomedical Image Analysis at Masaryk University. His current research fields include the manipulation of huge image data and the generation of synthetic microscopy image data, both static and time-lapse sequences.
Affiliations and expertise
Associate Professor of informatics MU Brno, Czech Republic