Medical Image Computing and Computer Assisted Intervention – MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, ... VI (Lecture Notes in Computer Science, 13436)

✍ Scribed by Linwei Wang; Qi Dou; P. Thomas Fletcher; Stefanie Speidel; Shuo Li

• Tongue: English
• Leaves: 841
• Category: Library

✦ Table of Contents

Preface
Organization
Contents – Part VI
Image Registration
SVoRT: Iterative Transformer for Slice-to-Volume Registration in Fetal Brain MRI
1 Introduction
2 Methods
2.1 Transformation Update
2.2 Volume Estimation
2.3 Training
3 Experiments and Results
3.1 Experiment Setup
3.2 Simulated Data
3.3 Real Fetal MR Data
4 Conclusion
References
Double-Uncertainty Guided Spatial and Temporal Consistency Regularization Weighting for Learning-Based Abdominal Registration
1 Introduction
2 Methods
2.1 Mean-Teacher Based Temporal Consistency Regularization
2.2 Double-Uncertainty Guided Adaptive Weighting
3 Experiments and Results
4 Conclusion
References
Unsupervised Deformable Image Registration with Absent Correspondences in Pre-operative and Post-recurrence Brain Tumor MRI Scans
1 Introduction
2 Methods
2.1 Bidirectional Deformable Image Registration
2.2 Forward-Backward Consistency Constraint
2.3 Inverse Consistency
2.4 Objective Function
3 Experiments
4 Conclusion
References
On the Dataset Quality Control for Image Registration Evaluation
1 Introduction
2 Method
2.1 Constructing the Variogram
2.2 Potential FLEs
2.3 Atypical Variogram Patterns
3 Experiments
4 Discussion
References
Dual-Branch Squeeze-Fusion-Excitation Module for Cross-Modality Registration of Cardiac SPECT and CT
1 Introduction
2 Methods
2.1 Dataset and Preprocessing
2.2 Dual-Branch Squeeze-Fusion-Excitation Module
2.3 Deep Registration and Fully Connected Layers
2.4 Implementation Details
2.5 Quantitative Evaluations
3 Results
4 Conclusion
References
Embedding Gradient-Based Optimization in Image Registration Networks
1 Introduction
2 Method
3 Experiments
4 Conclusion
References
ContraReg: Contrastive Learning of Multi-modality Unsupervised Deformable Image Registration
1 Introduction
2 Related Work
3 Methods
4 Experiments
5 Discussion
References
Swin-VoxelMorph: A Symmetric Unsupervised Learning Model for Deformable Medical Image Registration Using Swin Transformer
1 Introduction
2 Method
2.1 Network Structures
2.2 Loss Function
3 Experiments
3.1 Datasets, Preprocessing and Evaluation Criteria
3.2 Results
4 Conclusions
References
Non-iterative Coarse-to-Fine Registration Based on Single-Pass Deep Cumulative Learning
1 Introduction
2 Method
2.1 Selectively-Propagated Feature Learning (SFL)
2.2 Single-Pass Deep Cumulative Learning (SDCL)
2.3 Unsupervised Training
3 Experimental Setup
3.1 Datasets
3.2 Implementation Details
3.3 Comparison Methods
3.4 Experimental Settings
4 Results and Discussion
5 Conclusion
References
DSR: Direct Simultaneous Registration for Multiple 3D Images
1 Introduction
2 Methodology
2.1 Direct Bundle Adjustment
2.2 Simultaneous Registration Without Intensity Optimization
3 Experiments and Results
3.1 Simulated Experiments
3.2 In-Vivo Experiments
4 Conclusion
References
Multi-modal Retinal Image Registration Using a Keypoint-Based Vessel Structure Aligning Network
1 Introduction
2 Methods
2.1 Synthetic Augmentations for Multi-modal Retinal Images
2.2 Multi-modal Retinal Keypoint Detection and Description Network
2.3 Keypoint Matching Using a Graph Convolutional Neural Network
3 Experiments
3.1 Multi-modal Retinal Datasets
3.2 Implementation and Experimental Details
3.3 Results
4 Conclusion
References
A Deep-Discrete Learning Framework for Spherical Surface Registration
1 Introduction
2 Method
2.1 Rotation Architecture
2.2 Deep-Discrete Networks
3 Experiments
4 Conclusions
References
Privacy Preserving Image Registration
1 Introduction
2 Problem Statement
3 Methods
3.1 Secure Computation
3.2 PPIR: Privacy Preserving Image Registration
4 Experimental Results
5 Conclusion
References
Deformer: Towards Displacement Field Learning for Unsupervised Medical Image Registration
1 Introduction
2 Method
3 Experiments and Discussion
4 Conclusion
References
End-to-End Multi-Slice-to-Volume Concurrent Registration and Multimodal Generation
1 Introduction
2 Methods
2.1 Synthetic CT Generation from MR
2.2 Multi-Slice-to-Volume Registration
3 Experiments and Results
3.1 Dataset and Preprocessing
3.2 Implementation Details
3.3 Baseline Methods
3.4 Results for MR-to-CT Translation
3.5 Results for Multi-Slice-to-Volume Registration
4 Conclusion
References
Fast Spherical Mapping of Cortical Surface Meshes Using Deep Unsupervised Learning
1 Introduction
2 Method
2.1 Overall Design and Conception
2.2 Coarse-to-Fine Multi-resolution Framework
2.3 Loss Functions
3 Experiments and Results
3.1 Experimental Setting
3.2 Results
4 Conclusion
References
Learning-Based US-MR Liver Image Registration with Spatial Priors
1 Introduction
2 Methods
3 Results and Discussion
4 Conclusion
References
Unsupervised Deep Non-rigid Alignment by Low-Rank Loss and Multi-input Attention
1 Introduction
2 Deep Non-rigid Alignment Using Low-Rank Loss
3 Experiments
4 Conclusion
References
Transformer Lesion Tracker
1 Introduction
2 Related Work
3 Method
3.1 Feature Extractor and Sparse Selection Strategy
3.2 Cross Attention-Based Transformer
3.3 Center Predictor and Training Loss
4 Experiments and Experimental Results
4.1 Dataset and Experiment Setup
4.2 Experimental Results and Discussion
5 Conclusion
References
LiftReg: Limited Angle 2D/3D Deformable Registration
1 Introduction
2 Problem Formulation
3 Method
3.1 PCA-Based Deformation Vector Field Subspace
3.2 Network Structure
3.3 Network Training
4 Experiments
4.1 Data Preparation
4.2 Evaluation Metrics
4.3 Validation of the DVF Subspace
4.4 Pairwise 2D/3D Deformable Image Registration
5 Conclusion
References
XMorpher: Full Transformer for Deformable Medical Image Registration via Cross Attention
1 Introduction
2 Methodology
2.1 XMorpher for Efficient and Multi-level Semantic Feature Representation in Registration
2.2 Cross Attention Transformer Block for Corresponding Atention
2.3 Multi-size Window Partitions for Local-Wise Correspondence
3 Experiment
3.1 Experiment Protocol
3.2 Results and Analysis
4 Conclusion
References
Weakly-Supervised Biomechanically-Constrained CT/MRI Registration of the Spine
1 Introduction
2 Method
3 Experiments
4 Conclusion and Discussion
References
Collaborative Quantization Embeddings for Intra-subject Prostate MR Image Registration
1 Introduction
2 Method
2.1 Preliminary: Deep Vector Quantization
2.2 Model Overview
2.3 Vanilla Quantization
2.4 Hierarchical Quantization
2.5 Collaborative Quantization
2.6 Training
3 Experiment
3.1 Experimental Settings
3.2 Ablation Study
3.3 Comparison with Existing Methods
4 Conclusion
References
Mesh-Based 3D Motion Tracking in Cardiac MRI Using Deep Learning
1 Introduction
2 Method
2.1 Mesh Displacement Estimation
2.2 Mesh Prediction
2.3 Differentiable Mesh-to-Image Rasterizer
2.4 Optimization
3 Experiments and Results
4 Conclusion
References
Data-Driven Multi-modal Partial Medical Image Preregistration by Template Space Patch Mapping
1 Introduction
2 Method
2.1 Template-Space Patch Mapping (TSPM)
2.2 Pipeline Execution
3 Experiments
4 Conclusion
References
Global Multi-modal 2D/3D Registration via Local Descriptors Learning
1 Introduction
2 Approach
2.1 Challenges of Local Feature Extraction for Medical Images
2.2 Detector-Free Local Feature Networks
2.3 Multiple Frames
3 Experiments
3.1 Datasets
3.2 Baselines and Main Results
3.3 Ablation Studies
3.4 Similarity Visualization
4 Conclusions
References
Adapting the Mean Teacher for Keypoint-Based Lung Registration Under Geometric Domain Shifts
1 Introduction
2 Methods
2.1 Problem Statement
2.2 Baseline Model
2.3 Domain-Adaptive Registration with the Mean Teacher
3 Experiments
3.1 Experimental Setup
3.2 Results
4 Conclusion
References
DisQ: Disentangling Quantitative MRI Mapping of the Heart
1 Introduction
2 Methodology
2.1 Overall Framework: Disentangling Latent Spaces
2.2 Bootstrapping Disentangled Representations
3 Experiments
3.1 Dataset
3.2 Implementation
3.3 Results
4 Conclusion
References
Learning Iterative Optimisation for Deformable Image Registration of Lung CT with Recurrent Convolutional Networks
1 Introduction
1.1 Related Work
1.2 Adam Optimisation
1.3 Our Contribution
2 Methods
2.1 Pre-registration
2.2 Extraction of Optimisation Inputs
2.3 Optimiser Network
2.4 Comparison to Feed-Forward Nets and Adam Optimisation
3 Experiments and Results
4 Discussion
References
Electron Microscope Image Registration Using Laplacian Sharpening Transformer U-Net
1 Introduction
2 Methods
2.1 Displacement Field Generation
2.2 Feature Enhancement
2.3 Cascaded Registration
2.4 Loss Function
3 Experiments and Results
3.1 Dataset and Evaluation
3.2 Results
4 Conclusion
References
Image Reconstruction
Undersampled MRI Reconstruction with Side Information-Guided Normalisation
1 Introduction
2 Methods
2.1 Problem Formulation
2.2 Side Information-Guided Normalisation (SIGN) Module
2.3 Reconstruction with D5C5 and OUCR Backbones
3 Experiments and Results
3.1 Datasets and Network Configuration
3.2 Results
3.3 Further Analysis
4 Conclusion
References
Noise2SR: Learning to Denoise from Super-Resolved Single Noisy Fluorescence Image
1 Introduction
2 Proposed Method
2.1 Problem Formulation
2.2 Sub-sampler Module
2.3 Model Optimization
2.4 Clean Image Reconstruction
3 Experiment
3.1 Setup
3.2 Results
4 Conclusion
References
RPLHR-CT Dataset and Transformer Baseline for Volumetric Super-Resolution from CT Scans
1 Introduction
2 Dataset and Methodology
2.1 RPLHR-CT Dataset
2.2 Network Architecture
3 Experiments and Results
3.1 Results and Analysis
3.2 Domain Gap Analysis
3.3 Ablation Study
4 Conclusion
References
A Learnable Variational Model for Joint Multimodal MRI Reconstruction and Synthesis
1 Introduction
2 Proposed Method
2.1 Model
2.2 Efficient Learnable Optimization Algorithm
2.3 Bilevel Optimization Algorithm for Network Training
3 Experiments
3.1 Initialization Networks
3.2 Experiment Setup
3.3 Experimental Results and Evaluation
4 Conclusion
References
Autofocusing+: Noise-Resilient Motion Correction in Magnetic Resonance Imaging
1 Introduction
2 Methods
3 Experiments
4 Results
5 Discussion
References
Tagged-MRI Sequence to Audio Synthesis via Self Residual Attention Guided Heterogeneous Translator
1 Introduction
2 Methodology
2.1 Asymmetric Fully-CNN Translator with Self Residual Attention
2.2 Pair-Wise Disentanglement Training
2.3 Adversarial Loss and Overall Training Protocol
3 Experiments and Results
4 Discussion and Conclusion
References
Only-Train-Once MR Fingerprinting for Magnetization Transfer Contrast Quantification
1 Introduction
2 Methods
2.1 Signal Model: Transient-State MTC-MRF
2.2 Proposed Model
3 Experiments
3.1 Digital Phantom Study: Bloch Simulation
3.2 In Vivo Experiments
3.3 Results and Discussion
4 Conclusion
References
AutoGAN-Synthesizer: Neural Architecture Search for Cross-Modality MRI Synthesis
1 Introduction
2 Proposed Method
2.1 NAS-Based Generator Search
2.2 GAN-Based Perceptual Loss Function
2.3 K-space Learning
2.4 Implementation Details
3 Experimental Results
3.1 Experimental Settings
3.2 Comparisons with State-of-the-Art Methods
3.3 Ablation Study
4 Conclusion
References
Multi-scale Super-Resolution Magnetic Resonance Spectroscopic Imaging with Adjustable Sharpness
1 Introduction
2 Methods
2.1 Multi-scale Super-Resolution
2.2 Metabolite-Awareness
2.3 Adjustable Sharpness
3 Experiments and Results
3.1 Data Acquisition and Preprocessing
3.2 Implementation Details
3.3 Results and Discussion
4 Conclusion
References
Progressive Subsampling for Oversampled Data - Application to Quantitative MRI
1 Introduction
2 Related Work and Preliminaries
3 Methods
3.1 Scoring-Reconstruction Networks
3.2 Constructing the Mask to Subsample the Measurements
4 Experiments and Results
5 Future Work
References
Deep-Learning Based T1 and T2 Quantification from Undersampled Magnetic Resonance Fingerprinting Data to Track Tracer Kinetics in Small Laboratory Animals
1 Introduction
2 Method
2.1 Parametric Quantification by Template Matching Algorithm
2.2 Deep-Learning Method for Parametric Quantification
3 Experiments
3.1 Dataset and Experimental Setting
3.2 Results and Discussion
4 Conclusions
References
NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction
1 Introduction
2 Method
2.1 Pipeline
2.2 Neural Attenuation Fields
2.3 Model Optimization and Output
3 Experiments
3.1 Experimental Settings
3.2 Results
4 Conclusion
References
UASSR: Unsupervised Arbitrary Scale Super-Resolution Reconstruction of Single Anisotropic 3D Images via Disentangled Representation Learning
1 Introduction
2 Methodology
2.1 The UASSR Architecture
2.2 Super-Resolution Reconstruction from Anisotropic 3D Images with Arbitrary Slice Spacings
3 Experiments
3.1 Experimental Setup
3.2 Experimental Results
4 Conclusion
References
WavTrans: Synergizing Wavelet and Cross-Attention Transformer for Multi-contrast MRI Super-Resolution
1 Introduction
2 Methodology
2.1 Overall Architecture
2.2 Objective Function
3 Experiments
4 Conclusion
References
DuDoCAF: Dual-Domain Cross-Attention Fusion with Recurrent Transformer for Fast Multi-contrast MR Imaging
1 Introduction
2 Methods
2.1 Network Architecture
2.2 Cross-Attention Fusion
2.3 Residual Reconstruction Transformer
2.4 Dual-Domain Recurrent Learning
3 Experiments
4 Conclusion
References
Weakly Supervised MR-TRUS Image Synthesis for Brachytherapy of Prostate Cancer
1 Introduction
2 Methods
2.1 Network Architecture
2.2 Prostate Segmentation
2.3 MR Image Pattern Extraction
2.4 Joint Optimization Objective
3 Experiments
3.1 Dataset Preparation
3.2 Experiment Design and Results
4 Conclusion
References
Domain-Adaptive 3D Medical Image Synthesis: An Efficient Unsupervised Approach
1 Introduction
2 Methodology
3 Experiments
4 Results
4.1 Comparison of Methods
4.2 Analysis of Parameters
5 Discussion
References
What Can We Learn About a Generated Image Corrupting Its Latent Representation?
1 Introduction
2 Methodology
3 Experiments and Results
3.1 Network Architectures and Implementation Details
3.2 Can We Use the Noise Injections to Identify Uncertain Parts of a Synthesized Image?
3.3 Can We Use the Noise Injections to Improve the Quality of a Synthesized Image?
3.4 Can We Correlate Our Confidence Score with the Quality of Downstream Task, E.g., Segmentation, on the Synthesized Image?
3.5 How Does the Noise Injection Method Compare to Other Uncertainty Estimation Techniques?
4 Conclusion
References
3D CVT-GAN: A 3D Convolutional Vision Transformer-GAN for PET Reconstruction
1 Introduction
2 Methodology
2.1 Generator
2.2 Discriminator
2.3 Objective Function
2.4 Details of Implementation
3 Experiments and Results
4 Conclusion
References
Classification-Aided High-Quality PET Image Synthesis via Bidirectional Contrastive GAN with Shared Information Maximization
1 Introduction
2 Methodology
2.1 Master Network
2.2 Auxiliary Network
2.3 Domain Alignment Module
2.4 Implementation Details
3 Experiments and Results
3.1 Ablation Studies
3.2 Comparison with Existing State-of-the-Art Methods
4 Conclusion
References
Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRI
1 Introduction
2 Methods
2.1 U-Net Based Transformer
2.2 Shifted Windows Deformable Attention
2.3 Loss Function
3 Experimental Settings and Results
3.1 Implementation Details and Evaluation Methods
3.2 Comparison Studies
3.3 Ablation Studies
4 Discussion and Conclusion
References
Low-Dose CT Reconstruction via Dual-Domain Learning and Controllable Modulation
1 Introduction
2 Method
2.1 Main Branch (MB)
2.2 Controller Branch (CB) and Fusion Branch (FB)
2.3 Controllable Learning Strategy
3 Experiments
4 Conclusion
References
Graph-Based Compression of Incomplete 3D Photoacoustic Data
1 Introduction
2 Incomplete PA Data Compression
2.1 Overall Framework
2.2 Graph-Based Coding
2.3 Coding Mode Selection
3 Experiment
3.1 Experimental Setting
3.2 Objective Evaluation
3.3 Subjective Assessment
4 Conclusion
References
DS3-Net: Difficulty-Perceived Common-to-T1ce Semi-supervised Multimodal MRI Synthesis Network
1 Introduction
2 Methodology
2.1 Difficulty-Perceived Attention Map
2.2 Difficulty-Perceived Pixelwise and Patchwise Constraints
2.3 Difficulty-Perceived Dual-Level Distillation
3 Experiments and Results
3.1 Dataset
3.2 Training Strategy
3.3 Results
4 Conclusion
References
Invertible Sharpening Network for MRI Reconstruction Enhancement
1 Introduction
2 Methods
2.1 Problem Formulation
2.2 Backward Training
2.3 Network Architecture
3 Experiments
3.1 Datasets
3.2 Results
4 Conclusion
References
Analyzing and Improving Low Dose CT Denoising Network via HU Level Slicing
1 Introduction
2 Method
3 Experimental Details
4 Result and Discussion
4.1 Sensitivity Analysis
4.2 Comparison with SOTA Method
5 Conclusion
References
Spatio-Temporal Motion Correction and Iterative Reconstruction of In-Utero Fetal fMRI
1 Introduction
2 Method
2.1 The Reconstruction Problem
2.2 Optimization
3 Experiments and Results
3.1 Data
3.2 Experimental Setting and Low-Rank Representation
3.3 Evaluation of Image Reconstruction
3.4 Functional Connectivity Analysis
4 Conclusion
References
Deep Filter Bank Regression for Super-Resolution of Anisotropic MR Brain Images
1 Introduction
2 Methods
3 Experiments and Results
4 Discussion and Conclusions
References
Towards Performant and Reliable Undersampled MR Reconstruction via Diffusion Model Sampling
1 Introduction
2 DiffuseRecon
3 Experiments
4 Conclusion
References
Patch-Wise Deep Metric Learning for Unsupervised Low-Dose CT Denoising
1 Introduction
2 Method
2.1 Overview of the Proposed Method
2.2 Patch-Wise Deep Metric Learning
2.3 Network Architecture
3 Experiments
3.1 AAPM Dataset
3.2 Temporal CT Scans
4 Conclusion
References
BMD-GAN: Bone Mineral Density Estimation Using X-Ray Image Decomposition into Projections of Bone-Segmented Quantitative Computed Tomography Using Hierarchical Learning
1 Introduction
2 Method
2.1 Overview of the Proposed Method
2.2 Dataset Construction
2.3 Paired Image Translation from an X-Ray Image to a PF-DRR
2.4 Generator Backbone
3 Experiments and Results
3.1 Experimental Materials, Setting, and Evaluation Metrics
3.2 Results of X-Ray Image Decomposition
3.3 Results of BMD Estimation
3.4 Implementation Details
4 Discussion and Conclusion
References
Measurement-Conditioned Denoising Diffusion Probabilistic Model for Under-Sampled Medical Image Reconstruction
1 Introduction
2 Background
2.1 Denoising Diffusion Probabilistic Model
2.2 Under-Sampled Medical Image Reconstruction
3 Method: Measurement-Conditioned DDPM
4 Experiments
4.1 Experimental Setting
4.2 Experimental Results
4.3 Discussion
5 Conclusion
References
Orientation-Shared Convolution Representation for CT Metal Artifact Learning
1 Introduction
2 Preliminary Knowledge
3 Orientation-Shared Convolution Model for MAR
4 Network Design and Implementation Details
5 Experiments
6 Conclusion and Future Work
References
MRI Reconstruction by Completing Under-sampled K-space Data with Learnable Fourier Interpolation
1 Introduction
2 Method
3 Experiments
3.1 Results
3.2 Ablation Study
4 Conclusions
References
Learning-Based and Unrolled Motion-Compensated Reconstruction for Cardiac MR CINE Imaging
1 Introduction
2 Methods
2.1 Motion-Compensated Image Reconstruction Framework
2.2 Motion Estimation Network
3 Experiments
4 Results and Discussion
5 Conclusion
References
Accelerated Pseudo 3D Dynamic Speech MR Imaging at 3T Using Unsupervised Deep Variational Manifold Learning
1 Introduction
2 Methods
3 Experiments and Results
3.1 In-vivo MRI Data Acquisition
3.2 Implementation of the Reconstruction Algorithms
3.3 Vocal Tract Area Function (VAF) Extraction
4 Results
5 Discussion and Conclusion
References
FSE Compensated Motion Correction for MRI Using Data Driven Methods
1 Introduction
1.1 Related Works
2 Methods
2.1 Image Simulations
3 Results and Discussion
4 Conclusion
References
Personalized dMRI Harmonization on Cortical Surface
1 Introduction
2 Method
2.1 Diffusion MRI Harmonization and Linear RISH Framework
2.2 Personalized dMRI Harmonization on Cortical Surface
3 Experiments and Results
3.1 Implementation Details
3.2 Results
4 Discussion and Conclusions
References
A Projection-Based K-space Transformer Network for Undersampled Radial MRI Reconstruction with Limited Training Subjects
1 Introduction
2 Projection-Based K-space Transformer (PKT)
2.1 The Overall Framework
2.2 Data Augmentation
2.3 Transformer Network
3 Experiments and Results
3.1 Dataset
3.2 Implementation Details
3.3 Performance Evaluation
3.4 Results
4 Conclusion
References
Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction
1 Introduction
2 Related Work
3 Background and Preliminaries
3.1 Accelerated MRI Reconstruction
3.2 Unrolled Proximal Gradient Descent Networks
3.3 Equivariance
4 Methods
4.1 Learned Iterative Scale-Equivariant Reconstruction Networks
4.2 Implementation
5 Experiments and Results
6 Conclusion
References
DDPNet: A Novel Dual-Domain Parallel Network for Low-Dose CT Reconstruction
1 Introduction
2 Methodology
2.1 Dual-Domain Parallel Architecture
2.2 Unified Fusion Block
2.3 Coupled Patch-Discriminators
3 Experiments
3.1 Materials and Configurations
3.2 Results and Analysis
4 Conclusion
References
Mapping in Cycles: Dual-Domain PET-CT Synthesis Framework with Cycle-Consistent Constraints
1 Introduction
2 Method
2.1 Proposed Framework
2.2 Training Strategy and Objectives
3 Experiments and Results
3.1 Dataset and Evaluation Metrics
3.2 Implement Details
3.3 Comparison with State-of-the-Art (SOTA) Methods
3.4 Ablation Study
4 Conclusion
References
Optimal MRI Undersampling Patterns for Pathology Localization
1 Introduction
2 Methods
2.1 Iterative Gradients Sampling
3 Experiments
4 Discussion
5 Conclusions
References
Sensor Geometry Generalization to Untrained Conditions in Quantitative Ultrasound Imaging
1 Introduction
2 Method
2.1 Synthetic Multi-sensor Dataset Generation
2.2 Data Augmentation
2.3 Deformable Sensor Generalization Model
2.4 Meta-learned Spatial Deformation
3 Experiments
3.1 Numerical Simulation
3.2 In-vivo Measurements
4 Conclusion
References
A Transformer-Based Iterative Reconstruction Model for Sparse-View CT Reconstruction
1 Introduction
2 Methodology
2.1 Preliminary Knowledge
2.2 The Proposed RegFormer
3 Experiments
4 Conclusions
References
Author Index