Segmentation of the Aorta. Towards the Automatic Segmentation, Modeling, and Meshing of the Aortic Vessel Tree from Multicenter Acquisition (Lecture Notes in Computer Science)

Preface
Organization
Contents
M3F: Multi-Field-of-View Feature Fusion Network for Aortic Vessel Tree Segmentation in CT Angiography
	1 Introduction
	2 Materials and Methods
		2.1 Dataset Description
		2.2 Image Preprocessing
		2.3 M3F: Multi-Field-of-View Feature Fusion Network
		2.4 Network Training
		2.5 Sliding Window Inference
	3 Experiments
		3.1 Implementation Details
		3.2 Results
	4 Discussion
	References
Aorta Segmentation from 3D CT in MICCAI SEG.A. 2023 Challenge
	1 Introduction
	2 Methods
		2.1 SegResNet
		2.2 Optimization
	3 Results
	4 Conclusion
	References
A Data-Centric Approach for Segmenting the Aortic Vessel Tree: A Solution to SEG.A. Challenge 2023 Segmentation Task
	1 Introduction
		1.1 Segmentation of the Aorta Challenge 2023
		1.2 Related Work
	2 Methods
		2.1 Challenge Dataset
		2.2 System Architecture
		2.3 Preprocessing
		2.4 Augmentations
		2.5 Training
		2.6 Postprocessing
		2.7 Inference
		2.8 Assessment Methods
	3 Results
		3.1 Quantitative Analysis
		3.2 Qualitative Analysis
		3.3 Challenge Submission
		3.4 Selected Teams
	4 Conclusion
	References
Automatic Aorta Segmentation with Heavily Augmented, High-Resolution 3-D ResUNet: Contribution to the SEG.A Challenge
	1 Introduction
		1.1 Overview
		1.2 Related Work
		1.3 Design Choices
		1.4 Contribution
	2 Method
		2.1 Preprocessing
		2.2 Augmentation
		2.3 Deep Network
		2.4 Objective Function and Training
		2.5 Inference and Postprocessing
		2.6 Meshing
		2.7 Dataset
		2.8 Experimental Setup
		2.9 Source Code
	3 Results
		3.1 Aorta Segmentation
		3.2 Surface Meshing
		3.3 Volumetric Meshing
	4 Discussion
	References
Position-Encoded Pixel-to-Prototype Contrastive Learning for Aortic Vessel Tree Segmentation
	1 Introduction
	2 Problem Definition
	3 Methods
		3.1 Framework
		3.2 First Stage: Coarse Segmentation
		3.3 Second Stage: Fine Segmentation
	4 Experiment and Results
		4.1 Setup
		4.2 Results
		4.3 Leaderboard
	5 Discussion
	6 Conclusion
	References
Misclassification Loss for Segmentation of the Aortic Vessel Tree
	1 Introduction
	2 Methods
		2.1 nnUNet Architecture
		2.2 Misclassification Loss
	3 Experiments
		3.1 Ablation Studies
		3.2 Results and Discussions
	4 Limitations
	5 Conclusion
	References
Deep Learning-Based Segmentation and Mesh Reconstruction of the Aortic Vessel Tree from CTA Images
	1 Introduction
	2 Related Works
	3 Methodology
		3.1 Preprocessing
		3.2 Segmentation Method
		3.3 Mesh Construction Method
	4 Experiments and Results
		4.1 Dataset
		4.2 Evaluation Scheme and Metrics
		4.3 Ablation Study
		4.4 Learning Curves
		4.5 Qualitative Results
		4.6 Quantitative Results
		4.7 Interpretation in Mesh Quality and Plots
	5 Conclusion
	References
RASNet: U-Net-Based Robust Aortic Segmentation Network for Multicenter Datasets
	1 Introduction
	2 Methodology
		2.1 Preprocessing
		2.2 Network
		2.3 Loss Function
		2.4 Postprocess
	3 Experiments
		3.1 The Dataset and Evaluation Method
		3.2 Implementation Details
		3.3 The HU Features Before and After Preprocess
	4 Experiment Results
		4.1 Results on Validation Set 1
		4.2 Results on Validation Set 2
		4.3 Results on Test Set
		4.4 Limitation and Future Work
	5 Conclusion
	References
Optimizing Aortic Segmentation with an Innovative Quality Assessment: The Role of Global Sensitivity Analysis
	1 Introduction
	2 Materials and Methods
		2.1 Image and Statistical Data Acquisition
		2.2 Augmented Dataset Creation
		2.3 Global Sensitivity Analysis
		2.4 Quality Assessment Metrics
	3 Discussion and Conclusion
	References
A Mini Guide on Mesh Generation of Blood Vessels for CFD Applications
	1 Introduction
	2 Unstructured Mesh Generation with Gmsh
	3 Structured Mesh Generation for Blood Vessels
	4 Conclusions
	References
Aortic Segmentations and Their Possible Clinical Benefits
	1 Introduction
		1.1 Aortic Anatomy
		1.2 Aortic Diseases
		1.3 Aortic Procedures
	2 Manual Aortic Segmentation
	3 Possible Clinical Benefits of Automated Aortic Segmentations
	4 Conclusion and Perspective
	References
Author Index