Less-Supervised Segmentation with CNNs: Scenarios, Models and Optimization reviews recent progress in deep learning for image segmentation under scenarios with limited supervision, with a focus on medical imaging. The book presents main approaches and state-of-the-art models and includes a broad array of applications in medical image segmentation, including healthcare, oncology, cardiology and neuroimaging. A key objective is to make this mathematical subject accessible to a broad engineering and computing audience by using a large number of intuitive graphical illustrations. The emphasis is on giving conceptual understanding of the methods to foster easier learning.
This book is highly suitable for researchers and graduate students in computer vision, machine learning and medical imaging.
1. Chapter 1: General introduction - p. 1 2. Part 1: Introduction to learning with limited supervision - p. 13 3. Chapter 2: A unified view of learning from both labeled and unlabeled data - p. 17 4. Chapter 3: Semi-supervised learning - p. 39 5. Chapter 4: Weakly supervised segmentation - p. 73 6. Chapter 5: Alternative learning scenarios - p. 97 7. Part 2: Use cases in medical image segmentation - p. 113 8. Chapter 6: Contrastive learning for unsupervised representation and semi-supervised learning for medical image segmentation - p. 117 9. Chapter 7: Boosting semi-supervised image segmentation with global and local mutual information regularization - p. 147 10. Chapter 8: Deep model adaptation without target labels on cross-domain medical images - p. 177 11. Chapter 9: Advancing medical image segmentation via exploiting limited annotations - p. 203 12. Chapter 10: Blending variational approaches and deep learning to enforce prior constraints in medical image segmentation - p. 217 13. Chapter 11: Self- and unsupervised learning for anomaly detection and localization - p. 237 14. Chapter 12: Learning from limited representation - p. 257 15. Chapter 13: Transductive few-shot adapters for medical image segmentation - p. 295 16. Chapter 14: AI methodologies for multimodal pathology applications - p. 311 17. Index - p. 321
Less-Supervised Segmentation with CNNs: Scenarios, Models and Optimization reviews recent progress in deep learning for image segmentation under scenarios with limited supervision, with a focus on medical imaging. The book presents main approaches and state-of-the-art models and includes a broad array of applications in medical image segmentation, including healthcare, oncology, cardiology and neuroimaging. A key objective is to make this mathematical subject accessible to a broad engineering and computing audience by using a large number of intuitive graphical illustrations. The emphasis is on giving conceptual understanding of the methods to foster easier learning.
This book is highly suitable for researchers and graduate students in computer vision, machine learning and medical imaging.
1. Chapter 1: General introduction - p. 1 2. Part 1: Introduction to learning with limited supervision - p. 13 3. Chapter 2: A unified view of learning from both labeled and unlabeled data - p. 17 4. Chapter 3: Semi-supervised learning - p. 39 5. Chapter 4: Weakly supervised segmentation - p. 73 6. Chapter 5: Alternative learning scenarios - p. 97 7. Part 2: Use cases in medical image segmentation - p. 113 8. Chapter 6: Contrastive learning for unsupervised representation and semi-supervised learning for medical image segmentation - p. 117 9. Chapter 7: Boosting semi-supervised image segmentation with global and local mutual information regularization - p. 147 10. Chapter 8: Deep model adaptation without target labels on cross-domain medical images - p. 177 11. Chapter 9: Advancing medical image segmentation via exploiting limited annotations - p. 203 12. Chapter 10: Blending variational approaches and deep learning to enforce prior constraints in medical image segmentation - p. 217 13. Chapter 11: Self- and unsupervised learning for anomaly detection and localization - p. 237 14. Chapter 12: Learning from limited representation - p. 257 15. Chapter 13: Transductive few-shot adapters for medical image segmentation - p. 295 16. Chapter 14: AI methodologies for multimodal pathology applications - p. 311 17. Index - p. 321
