
Medical Image Computing and Computer Assisted Intervention - MICCAI 2024
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The 12-volume set LNCS 15001 - 15012 constitutes the proceedings of the 27th International Conferenc on Medical Image Computing and Computer Assisted Intervention, MICCAI 2024, which took place in Marrakesh, Morocco, during October 6-10, 2024.
MICCAI accepted 857 full papers from 2781 submissions. They focus on neuroimaging; image registration; computational pathology; computer aided diagnosis, treatment response, and outcome prediction; image guided intervention; visualization; surgical planning, and surgical data science; image reconstruction; image segmentation; machine learning; etc.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- MICCAI 2024 Organization
- Contents - Part VII
- Image Reconstruction
- 3DDX: Bone Surface Reconstruction from a Single Standard-Geometry Radiograph via Dual-Face Depth Estimation
- 1 Introduction
- 2 Method
- 2.1 Depth Maps Estimation
- 2.2 Surface Reconstruction and 3D Shape Completion
- 3 Experiment and Result
- 3.1 3D Shape Results Without Shape Completion
- 3.2 3D Shape Results with Shape Completion
- 3.3 Depth Map Results
- 4 Conclusion and Summary
- References
- 3DGR-CAR: Coronary Artery Reconstruction from Ultra-sparse 2D X-Ray Views with a 3D Gaussians Representation
- 1 Introduction
- 2 Methods
- 2.1 3D Gaussians Representation Reconstruction
- 2.2 Gaussian Center Predictor Training
- 3 Experiments
- 3.1 Setup
- 3.2 Comparison with Existing Methods
- 3.3 Ablation Study
- 4 Conclusion
- References
- 3DPX: Progressive 2D-to-3D Oral Image Reconstruction with Hybrid MLP-CNN Networks
- 1 Introduction
- 2 Method
- 2.1 Progressive Guided Reconstruction
- 2.2 3DPX with Hybrid MLP-CNN Block
- 2.3 Evaluation Metric
- 3 Experiments and Results
- 3.1 Dataset and Augmentation
- 3.2 Experiments
- 4 Conclusion
- References
- 7T MRI Synthesization from 3T Acquisitions
- 1 Introduction
- 2 Method
- 3 Experimental Design
- 4 Results
- 4.1 Our V-Net Based Model for 7T MRI Synthesization Archives State-of-the-Art Performance
- 4.2 Qualitative Evaluation of Pathological Tissue Enhancement via Synthetic 7T Generation
- 4.3 Model Generalizability to Low-resolution MRI Input
- 5 Conclusion and Future Work
- References
- A Graph-Embedded Latent Space Learning and Clustering Framework for Incomplete Multimodal Multiclass Alzheimer's Disease Diagnosis
- 1 Introduction
- 2 Method
- 2.1 Multimodal Reconstruction
- 2.2 Subject-Similarity Graph Embedding
- 2.3 AD-Oriented Latent Clustering
- 3 Experiments
- 3.1 Materials and Experimental Setup
- 3.2 Performance of Proposed Method
- 3.3 Comparison with Other Methods
- 3.4 Ablation Study
- 4 Conclusions
- References
- Accelerated Multi-contrast MRI Reconstruction via Frequency and Spatial Mutual Learning
- 1 Introduction
- 2 Methodology
- 2.1 Frequency-Spatial Feature Extraction
- 2.2 Cross-Modal Frequency-Spatial Feature Fusion
- 2.3 Loss Function
- 3 Experiments
- 3.1 Datasets and Implementation Details
- 3.2 Experimental Results
- 4 Conclusion
- References
- All-In-One Medical Image Restoration via Task-Adaptive Routing
- 1 Introduction
- 2 Method
- 2.1 Network Architecture
- 2.2 Task-Adaptive Routing
- 2.3 Loss Function
- 3 Experiments and Results
- 3.1 Dataset
- 3.2 Implementation
- 3.3 Comparative Experiment
- 3.4 Ablation Study
- 4 Conclusion
- References
- An Evaluation of State-of-the-Art Projectors in the Presence of Noise and Nonlinearity in the Beer-Lambert Law
- 1 Introduction
- 2 Sensitivity Analysis of the Forward Model
- 3 Fast Projectors
- 4 Experiment and Results
- 4.1 Sensitivity to Perturbations of the Forward Model
- 4.2 Reconstruction Error
- 4.3 Reconstruction Error in Presence of Poisson Noise
- 4.4 Reconstruction Result
- 5 Conclusion
- References
- Anatomically-Controllable Medical Image Generation with Segmentation-Guided Diffusion Models
- 1 Introduction
- 2 Method
- 2.1 A Brief Review of Diffusion Models
- 2.2 Adding Segmentation Guidance to Diffusion Models
- 2.3 Mask-Ablated Training and Sampling
- 3 Datasets
- 4 Experiments
- 4.1 Comparison to Existing Image Generation Models
- 4.2 Advantages of Mask-Ablated-Training
- 5 Conclusion
- References
- APS-USCT: Ultrasound Computed Tomography on Sparse Data via AI-Physic Synergy
- 1 Introduction
- 2 Method
- 3 Experiment
- 3.1 Dataset, Implementation, and Evaluation Protocol
- 3.2 Main Results
- 3.3 Ablation Studies
- 4 Conclusion
- References
- AutoSkull: Learning-Based Skull Estimation for Automated Pipelines
- 1 Introduction
- 2 Method
- 2.1 Preprocessing for Training
- 2.2 MLP-Based Learning
- 2.3 Skull Inference from Face Scan
- 2.4 Adding a Teeth Prior
- 3 Evaluation and Results
- 3.1 Evaluation Setup
- 3.2 Comparisons
- 3.3 Ablation Study
- 3.4 Application Example
- 4 Discussion and Conclusion
- References
- Baikal: Unpaired Denoising of Fluorescence Microscopy Images Using Diffusion Models
- 1 Introduction
- 2 Methods
- 2.1 Generative Backbone on Clean Images
- 2.2 Conditional Samplers as Denoisers
- 3 Experiments
- 3.1 Dataset and Training
- 3.2 Quantitative Results
- 3.3 Ablations
- 3.4 Qualitative Results
- 4 Conclusion
- References
- Blind Proximal Diffusion Model for Joint Image and Sensitivity Estimation in Parallel MRI
- 1 Introduction
- 2 Methodology
- 2.1 Model Optimization
- 2.2 BPDM-PMRI
- 3 Experiments
- 4 Conclusion
- References
- Brain Cortical Functional Gradients Predict Cortical Folding Patterns via Attention Mesh Convolution
- 1 Introduction
- 2 Related Works
- 2.1 Mesh Convolution
- 2.2 Predicting Gyro-Sulcus From fMRI
- 3 Method
- 3.1 Channel Attention Block
- 3.2 Mesh CNN with U-Net Architecture and Loss Function
- 4 Experiments
- 4.1 Dataset, Preprocessing and Implementation
- 4.2 Results and Methods Comparison
- 4.3 Ablation Study
- 5 Discussion
- 6 Conclusion
- References
- CAPTURE-GAN: Conditional Attribute Preservation Through Unveiling Realistic GAN for Artifact Removal in Dual-Energy CT Imaging
- 1 Introduction
- 2 Method
- 2.1 CAPTURE-GAN
- 2.2 Pre-trained Classifier and Mask Creator
- 2.3 Loss Function
- 2.4 Model Training
- 3 Experimental Results
- 3.1 Dataset
- 3.2 Evaluation
- 3.3 Qualitative and Quantitative Comparison Results
- 3.4 Ablation Study Results
- 4 Conclusion
- References
- CAVM: Conditional Autoregressive Vision Model for Contrast-Enhanced Brain Tumor MRI Synthesis
- 1 Introduction
- 2 Methodology
- 2.1 Problem Formulation and Method Overview
- 2.2 Model Architecture
- 2.3 Model Training
- 3 Experiments and Results
- 3.1 Experimental Setups
- 3.2 Performance Evaluation
- 3.3 Ablation Study
- 4 Conclusion
- References
- Center-to-Edge Denoising Diffusion Probabilistic Models with Cross-domain Attention for Undersampled MRI Reconstruction
- 1 Introduction
- 2 Method
- 2.1 Conditional DDPM by Undersampled Measurements
- 2.2 C2E Denoising Diffusion Strategy
- 2.3 Ag-Cd-J for Dual Domain Integration
- 3 Experiment and Results
- 4 Conclusion
- References
- Contrast Representation Learning from Imaging Parameters for Magnetic Resonance Image Synthesis
- 1 Introduction
- 2 Method
- 2.1 Problem Definition
- 2.2 Contrast Representation Learning
- 3 Experiments
- 3.1 Data Acquisition
- 3.2 Implementation Details
- 3.3 Comparison with State-of-the-Art Methods
- 3.4 Modulating Contrast Across All Sequences
- 4 Conclusion
- References
- Convolutional Implicit Neural Representation of Pathology Whole-Slide Images
- 1 Introduction
- 2 Method
- 2.1 Position Encoding
- 2.2 Convolutional Implicit Neural Representation
- 3 Results
- 3.1 Experiments
- 3.2 Reconstruction Results
- 4 Conclusion
- References
- Cross-conditioned Diffusion Model for Medical Image to Image Translation
- 1 Introduction
- 2 Method
- 2.1 Representation Learning for Target Modalities
- 2.2 Cross-conditioned UNet (C-UNet)
- 3 Experiments
- 3.1 Datasets and Implementation
- 3.2 Comparison with SOTA Methods
- 3.3 Ablation Study
- 4 Conclusion
- References
- Cycle-Consistent Learning for Fetal Cortical Surface Reconstruction
- 1 Introduction
- 2 Method
- 3 Experiments
- 4 Conclusion
- References
- DCDiff: Dual-Domain Conditional Diffusion for CT Metal Artifact Reduction
- 1 Introduction
- 2 Revisiting Diffusion Models
- 3 Methodology
- 3.1 Model Architecture and Training
- 3.2 Model Inference with Diffusion Interpolation
- 4 Experiments and Results
- 4.1 Datasets and Experiment Settings
- 4.2 Performance Evaluation
- 4.3 Ablation Study
- 5 Conclusion
- References
- Death by Retrospective Undersampling - Caveats and Solutions for Learning-Based MRI Reconstructions
- 1 Introduction
- 2 Methods
- 2.1 Simulation Setup
- 2.2 Unrolled Variational Network
- 2.3 Training and Evaluation
- 3 Results
- 4 Discussion
- 5 Conclusion
- References
- Deform-Mamba Network for MRI Super-Resolution
- 1 Introduction
- 2 Method
- 2.1 Preliminaries
- 2.2 Proposed Architecture
- 3 Experiments
- 3.1 Datasets and Evaluation Metrics
- 3.2 Experimental Details
- 3.3 Ablation Study
- 3.4 Comparison with State-of-the-Art Methods
- 4 Conclusion and Future Work
- References
- Differentiable Score-Based Likelihoods: Learning CT Motion Compensation from Clean Images
- 1 Introduction
- 2 Methods
- 2.1 Score-Based Diffusion Models
- 2.2 Likelihood Computation
- 2.3 Neural ODEs and Likelihood Target Function
- 2.4 Motion Compensation
- 3 Experiments and Results
- 4 Discussion
- 5 Conclusion
- References
- Dynamic Hybrid Unrolled Multi-scale Network for Accelerated MRI Reconstruction
- 1 Introduction
- 2 Problem Formulation
- 3 Method
- 4 Experiments
- 4.1 Datasets and Experimental Setting
- 4.2 Ablation Study
- 4.3 Comparison Study
- 5 Conclusions
- References
- Dynamic Single-Pixel Imaging on an Extended Field of View Without Warping the Patterns
- 1 Introduction
- 2 Single-Pixel Imaging
- 2.1 Forward Model
- 2.2 Image Reconstruction
- 3 Method
- 3.1 Dynamic Forward Model with Extended FOV
- 3.2 Dynamic System Matrix Without Warping the Patterns
- 4 Results
- 5 Conclusion
- References
- EchoNet-Synthetic: Privacy-Preserving Video Generation for Safe Medical Data Sharing
- 1 Introduction
- 2 Method
- 3 Experiments
- 4 Conclusion
- References
- EndoUIC: Promptable Diffusion Transformer for Unified Illumination Correction in Capsule Endoscopy
- 1 Introduction
- 2 Methodology
- 2.1 Preliminaries
- 2.2 Proposed Method: EndoUIC
- 3 Experiments
- 3.1 Dataset
- 3.2 Implementation Details
- 3.3 Results
- 4 Conclusion
- References
- Estimating Neural Orientation Distribution Fields on High Resolution Diffusion MRI Scans
- 1 Introduction
- 2 Related Work
- 3 Method
- 3.1 Background and Notation
- 3.2 Grid-Hash-Encoding of Harmonic Coefficient Fields
- 4 Experimental Setup
- 5 Results
- 5.1 Comparison with Current Methods
- 5.2 Ablation Studies
- 6 Discussion and Conclusion
- References
- Explanation-Driven Cyclic Learning for High-Quality Brain MRI Reconstruction from Unknown Degradation
- 1 Introduction
- 2 Methods
- 2.1 Front-End Image Classification
- 2.2 Back-End Image Reconstruction
- 2.3 Cross-Attention-Gradient Interpreting
- 3 Experiments and Results
- 3.1 Dataset Description and Data Partition
- 3.2 Experimental Settings
- 3.3 Experimental Results on Simulated Data
- 3.4 Experimental Results on Real Motion Data
- 3.5 Ablation Study
- 4 Conclusion
- References
- Fetal MRI Reconstruction by Global Diffusion and Consistent Implicit Representation
- 1 Introduction
- 2 Methods
- 2.1 Consistency Implicit Neural Network
- 2.2 Global Diffusion Discriminative Generation
- 2.3 Loss Functions
- 3 Experiments and Results
- 3.1 Datasets
- 3.2 Compared with Results of Different Methods
- 3.3 Simulated Fetal Brain Data
- 3.4 Reconstructing Volumes at Different Gestational Ages
- 3.5 Ablation Study
- 3.6 Downstream Task Analysis
- 4 Conclusion
- References
- Fine-Grained Context and Multi-modal Alignment for Freehand 3D Ultrasound Reconstruction
- 1 Introduction
- 2 Methods
- 2.1 ReMamba with Multi-directional State Space Model
- 2.2 Adaptive Fusion Strategy
- 2.3 Online Alignment Strategy
- 3 Experiments
- 4 Conclusion
- References
- Free-SurGS: SfM-Free 3D Gaussian Splatting for Surgical Scene Reconstruction
- 1 Introduction
- 2 Methodology
- 2.1 Preliminary: 3D Gaussian Splatting
- 2.2 Initialization from Monocular Depth
- 2.3 Flow-Induced Pose Estimation
- 2.4 3D Gaussians Optimization
- 3 Experiments
- 3.1 Implementation Details
- 3.2 Quantitative and Qualitative Results
- 4 Conclusion
- References
- HeartBeat: Towards Controllable Echocardiography Video Synthesis with Multimodal Conditions-Guided Diffusion Models
- 1 Introduction
- 2 Methodology
- 2.1 Preliminaries of T2V DDPMs
- 2.2 HeartBeat
- 3 Experimental Results
- 4 Conclusion
- References
- HF-ResDiff: High-Frequency-Guided Residual Diffusion for Multi-dose PET Reconstruction
- 1 Introduction
- 2 Methodology
- 2.1 Pre-train CNN for Predicting Low-Frequency Information
- 2.2 HF-ResDiff Model
- 2.3 Multi-dose PET Reconstruction
- 2.4 Implementation Details
- 3 Experiments
- 3.1 Dataset
- 3.2 Comparative Experiments
- 3.3 Ablation Study
- 4 Conclusion
- References
- IM-MoCo: Self-supervised MRI Motion Correction Using Motion-Guided Implicit Neural Representations
- 1 Introduction
- 2 Materials and Methods
- 2.1 Physical Model and Motion Simulation
- 2.2 IM-MoCo
- 3 Experimental Results
- 3.1 Datasets and Motion Simulation
- 3.2 Experimental Setup
- 3.3 Results
- 4 Discussion and Outlook
- 5 Conclusion
- References
- Inject Backdoor in Measured Data to Jeopardize Full-Stack Medical Image Analysis System
- 1 Introduction
- 2 Methodology
- 2.1 Problem Statement
- 2.2 Learnable Trigger Generation Method
- 3 Experiment
- 3.1 Experiment Settings
- 3.2 Experimental Results
- 4 Conclusion
- References
- Joint EM Image Denoising and Segmentation with Instance-Aware Interaction
- 1 Introduction
- 2 Instance-Aware Interaction Framework
- 2.1 Overview
- 2.2 Instance-Aware Embedding Module
- 2.3 Joint Training Mechanism
- 3 Experiments
- 3.1 Experimental Settings
- 3.2 Quantitative and Qualitative Evaluations
- 3.3 Generalization Evaluation
- 3.4 Ablation Study
- 4 Conclusion
- References
- k-t Self-consistency Diffusion: A Physics-Informed Model for Dynamic MR Imaging
- 1 Introduction
- 2 Method
- 2.1 TSPIRiT
- 2.2 k-t Self-consistency Diffusion
- 3 Experiments and Results
- 3.1 Dataset
- 3.2 Implementation Details
- 3.3 Comparison with State-of-the-Art Methods
- 3.4 Ablation Study
- 3.5 Performance on Temporally-Frame-Shuffled Data
- 4 Conclusion and Discussion
- References
- Learning 3D Gaussians for Extremely Sparse-View Cone-Beam CT Reconstruction
- 1 Introduction
- 2 Methods
- 2.1 Problem Formulation
- 2.2 DIF-Gaussian: Learning 3D Gaussians
- 2.3 Test-Time Optimization (TTO)
- 3 Experiments
- 3.1 Experimental Settings
- 3.2 Results
- 4 Conclusion
- References
- LiverUSRecon: Automatic 3D Reconstruction and Volumetry of the Liver with a Few Partial Ultrasound Scans
- 1 Introduction
- 2 Methodology
- 3 Experiments and Results
- 4 Conclusion
- References
- LSSNet: A Method for Colon Polyp Segmentation Based on Local Feature Supplementation and Shallow Feature Supplementation
- 1 Introduction
- 2 Method
- 2.1 Convolutional Branch
- 2.2 Multiscale Feature Extraction Module
- 2.3 Semantic Gap Reduction Module
- 2.4 Interlayer Attention Fusion Module
- 2.5 Shallow Feature Supplementation Module
- 3 Experiments
- 3.1 Datasets and Evaluation Metrics
- 3.2 Implementation Details
- 3.3 Results
- 3.4 Ablation Experiments
- 4 Conclusion
- References
- Material Decomposition in Photon-Counting CT: A Deep Learning Approach Driven by Detector Physics and ASIC Modeling
- 1 Introduction
- 2 Method
- 2.1 Physics Simulation Model and Dataset Construction
- 2.2 Detector Net and ASIC Net
- 2.3 Calibration
- 2.4 Material Decomposition
- 3 Experiment
- 3.1 Compared Methods
- 3.2 Calibration Results
- 3.3 Material Decomposition Results
- 4 Conclusion
- References
- MCAD: Multi-modal Conditioned Adversarial Diffusion Model for High-Quality PET Image Reconstruction
- 1 Introduction
- 2 Methodology
- 2.1 Adversarial Diffusive Network
- 2.2 Multi-modal Conditional Encoder (Mc-Encoder)
- 2.3 Multi-modal Masked Text Reconstruction (M3TRec)
- 2.4 Sampling
- 2.5 Objective Function
- 3 Experiments
- 3.1 Experimental Settings
- 3.2 Comparison with State-of-the-Art Methods
- 3.3 Ablation Studies
- 4 Conclusion
- References
- Memory-Efficient High-Resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models
- 1 Introduction
- 2 Methodology
- 2.1 Non-Holistic Autoencoders
- 2.2 Cascaded Diffusion Processes
- 3 Experiments and Results
- 4 Conclusion
- References
- MiHATP:A Multi-hybrid Attention Super-Resolution Network for Pathological Image Based on Transformation Pool Contrastive Learning
- 1 Introduction
- 2 Method
- 2.1 Reversible and Irreversible Transformation Pool
- 2.2 Multi-hybrid Attention
- 2.3 Loss Function
- 3 Experiment and Result Discussion
- 3.1 Dataset and Implementation
- 3.2 Experimental Results
- 4 Conclusion
- References
- Noise Level Adaptive Diffusion Model for Robust Reconstruction of Accelerated MRI-4pt
- 1 Introduction
- 2 Methodology
- 3 Experiments
- 4 Conclusion
- References
- On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction
- 1 Introduction
- 2 Related Works
- 2.1 DL-Based End-to-End Solution
- 2.2 Bayesian Image Reconstruction
- 2.3 Reconstructing MRI Using Diffusion Prior and Posterior Sampling
- 3 Worst-Case Instabilities in MRI Reconstruction
- 4 Experiments and Results
- 4.1 Data
- 4.2 Supervised Baselines
- 4.3 Denoising Diffusion Reconstruction
- 4.4 Experimental Design
- 4.5 Quantitative and Visual Evaluation
- 5 Conclusion
- References
- Parameter Efficient Fine Tuning for Multi-scanner PET to PET Reconstruction
- 1 Introduction
- 2 Methodology
- 2.1 PEFT for PET Scan-Time Reduction
- 2.2 PETITE: Optimal Effectiveness of Mix-PEFT
- 3 Experiments and Results
- 3.1 Evaluation Results
- 4 Conclusions
- References
- PASTA: Pathology-Aware MRI to PET CroSs-modal TrAnslation with Diffusion Models
- 1 Introduction
- 2 Proposed Method
- 3 Experiments
- 4 Results
- 5 Conclusion
- References
- PET Image Denoising Based on 3D Denoising Diffusion Probabilistic Model: Evaluations on Total-Body Datasets
- 1 Introduction
- 2 Methodology
- 2.1 Diffusion Models
- 2.2 Conditional PET Image Denoising Based on 3D DDPM
- 3 Experiments and Results
- 3.1 Dataset and Implementation Details
- 3.2 Evaluation Metrics
- 3.3 Results
- 4 Conclusion
- References
- Physical-Priors-Guided Aortic Dissection Detection Using Non-Contrast-Enhanced CT Images
- 1 Introduction
- 2 Method
- 2.1 3D Aorta Segmentation
- 2.2 Blood Flow Parameter Calculation
- 2.3 3D Physical-Guided Model
- 3 Experiments
- 3.1 Datasets and Experiment Details
- 3.2 Results
- 3.3 Ablation Studies
- 4 Conclusion and Discussion
- References
- Physics-Informed Deep Learning for Motion-Corrected Reconstruction of Quantitative Brain MRI*-12pt
- 1 Introduction
- 2 Background
- 2.1 Motion During MR Image Acquisition
- 2.2 T2* Quantification from Multi-echo GRE MRI
- 3 Methods
- 3.1 PHIMO
- 3.2 Data
- 3.3 Evaluation
- 4 Experiments and Results
- 5 Discussion and Conclusion
- References
- Pixel2Mechanics: Automated Biomechanical Simulations of High-Resolution Intervertebral Discs from Anisotropic MRIs
- 1 Introduction
- 2 Methods
- 2.1 MRI2Mesh
- 2.2 Differentiable Rendering Optimization
- 2.3 Objective Function
- 2.4 Biomechanical Simulation
- 3 Experiments
- 4 Results
- 4.1 IVD Reconstruction
- 4.2 Biomechanical Simulation
- 5 Discussion and Conclusion
- References
- Privacy Protection in MRI Scans Using 3D Masked Autoencoders
- 1 Introduction
- 2 Related Work
- 3 Method
- 4 Experiments and Conclusion
- References
- Reference-Free Axial Super-Resolution of 3D Microscopy Images Using Implicit Neural Representation with a 2D Diffusion Prior
- 1 Introduction
- 2 Method
- 2.1 Implicit Neural Representations for Isotropic Volume Reconstruction
- 2.2 Diffusion Models and Score Distillation Sampling
- 3 Experiments
- 3.1 Datasets and Implementation Details
- 3.2 Simulation Studies on FIB25
- 3.3 Real World Anisotropic Volumes
- 4 Conclusion and Future Work
- References
- Region Attention Transformer for Medical Image Restoration
- 1 Introduction
- 2 Method
- 2.1 Region Attention Transformer Block
- 2.2 Focal Region Loss
- 3 Experiments and Results
- 3.1 Dataset
- 3.2 Implementation
- 3.3 Comparison Experiment
- 3.4 Ablation Study
- 3.5 Conclusion
- References
- Self-supervised k-Space Regularization for Motion-Resolved Abdominal MRI Using Neural Implicit k-Space Representations
- 1 Introduction
- 2 Methods
- 2.1 k-Space Interpolation Using GRAPPA
- 2.2 From GRAPPA to PISCO
- 2.3 Dynamic MRI Reconstruction Using NIK with PISCO
- 3 Experimental Setup
- 3.1 Data
- 3.2 Training and Inference
- 3.3 Evaluation
- 4 Results
- 5 Discussion and Conclusion
- References
- Simulation Based Inference for PET Iterative Reconstruction
- 1 Introduction
- 2 Continuous Surrogate Projector
- 2.1 Conditional Density Estimation
- 3 Stochastic Simulator
- 4 Experiments Setup
- 4.1 Reconstruction Settings
- 4.2 Projector Binning (System Matrix)
- 4.3 Iterative Reconstruction (EM)
- 4.4 Evaluation Methodology
- 5 Results and Discussion
- 5.1 Discussion
- References
- Simultaneous Tri-Modal Medical Image Fusion and Super-Resolution Using Conditional Diffusion Model
- 1 Introduction
- 2 Method
- 2.1 Overall Architecture
- 2.2 Tri-Modal Fusion Attention (TMFA) Block
- 2.3 Fusion Super-Resolution Joint Loss Function
- 3 Experiments
- 3.1 Experimental Detail
- 3.2 Objective Evaluation Metric
- 3.3 Comparison with SOTA Methods
- 3.4 Ablation Study
- 4 Conclusion
- References
- SinoSynth: A Physics-Based Domain Randomization Approach for Generalizable CBCT Image Enhancement
- 1 Introduction
- 2 Method
- 2.1 Preliminaries
- 2.2 Domain-Randomized CBCT Simulation
- 2.3 Structural Guidance for Generative Networks
- 3 Experiments
- 3.1 Datasets and Pre-processing
- 3.2 Comparisons with Actual CBCT-CT Data
- 3.3 Comparisons with Other Augmentation Methods
- 3.4 Ablation Studies
- 4 Conclusion
- References
- Slice-Consistent 3D Volumetric Brain CT-to-MRI Translation with 2D Brownian Bridge Diffusion Model
- 1 Introduction
- 2 Methods
- 2.1 Preliminaries: 2D Brownian Bridge Diffusion Model
- 2.2 Training Multi-slice 2D BBDM with Style Key Conditioning
- 2.3 Target Volume Sampling with Inter-Slice Trajectory Alignment
- 3 Experiments
- 3.1 Evaluations
- 4 Conclusion and Discussion
- References
- Spatial-Division Augmented Occupancy Field for Bone Shape Reconstruction from Biplanar X-Rays
- 1 Introduction
- 2 Methodology
- 2.1 Occupancy Field Network
- 2.2 Spatial-Division Augmentation
- 2.3 Teacher Occupancy Field Network
- 2.4 Spatial-Division Augmented Occupancy Field Network
- 3 Experiments
- 3.1 Experimental Settings
- 3.2 Results
- 4 Conclusion
- References
- SRE-CNN: A Spatiotemporal Rotation-Equivariant CNN for Cardiac Cine MR Imaging
- 1 Introduction
- 2 Method
- 2.1 Accelerated MRI Reconstruction Model
- 2.2 Spatiotemporal Rotation-Equivariant CNN Design
- 2.3 Filter Parametrization
- 3 Data and Experiments
- 4 Results and Discussion
- 5 Conclusion
- References
- Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis
- 1 Introduction
- 2 Method
- 3 Experimental Results
- 4 Conclusion
- References
- Tagged-to-Cine MRI Sequence Synthesis via Light Spatial-Temporal Transformer
- 1 Introduction
- 2 Methodology
- 2.1 Light Spatial-Temporal Transformer (LiST2)
- 2.2 Recurrent Sliding Fine-Tuning (ReST)
- 3 Experiments and Results
- 4 Conclusions
- References
- TeethDreamer: 3D Teeth Reconstruction from Five Intra-Oral Photographs
- 1 Introduction
- 2 Method
- 2.1 Multiview Cross-Domain Diffusion Model
- 2.2 3D-Aware Feature Attention
- 2.3 Geometry-Aware Teeth Reconstruction
- 3 Experiments
- 3.1 Experimental Settings
- 3.2 Experimental Results
- 3.3 Ablation Study
- 4 Conclusion
- References
- Two Projections Suffice for Cerebral Vascular Reconstruction
- 1 Introduction
- 2 Method
- 2.1 Disambiguating Reconstructor
- 2.2 Refinement of 3D Vasculature with MAP Estimate
- 3 Experiments and Results
- 3.1 Dataset and Preprocessing
- 3.2 Implementation Details
- 3.3 Results and Discussion
- 4 Conclusion and Future Work
- References
- UnWave-Net: Unrolled Wavelet Network for Compton Tomography Image Reconstruction
- 1 Introduction and Related Works
- 2 Modelling of the Non-collimated Circular CST
- 3 Methodology
- 3.1 Related Theories
- 3.2 The Proposed UnWave-Net
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Comparison with State-of-the-Art Methods
- 4.3 Ablation Study
- 5 Conclusion
- References
- VolumeNeRF: CT Volume Reconstruction from a Single Projection View
- 1 Introduction
- 2 Related Works
- 3 Method
- 3.1 Prior Anatomical Knowledge Incorporation
- 3.2 3D Representation Generation
- 3.3 Volume Rendering
- 3.4 Overall Objective
- 4 Experiments and Results
- 4.1 Data and Settings
- 4.2 Results
- 5 Conclusion
- References
- Volumetric Conditional Score-Based Residual Diffusion Model for PET/MR Denoising
- 1 Introduction
- 2 Method
- 2.1 Score-Based Diffusion Model for Residuals
- 2.2 Patch-Wise Training of Volumetric Conditional Score-Based Diffusion Model
- 3 Experiments
- 3.1 Dataset Description
- 3.2 Implementation Details
- 4 Results
- 5 Conclusion and Discussion
- References
- WIA-LD2ND: Wavelet-Based Image Alignment for Self-supervised Low-Dose CT Denoising
- 1 Introduction
- 2 Method
- 2.1 Analysis of LDCT Denoising From Frequency Perspective
- 2.2 Wavelet-Based Image Alignment
- 2.3 Frequency-Aware Multi-scale Loss
- 3 Experiments
- 3.1 Dataset and Training Details
- 3.2 Experiments Results
- 4 Discussion and Conclusion
- References
- Zero-Shot Low-Field MRI Enhancement via Denoising Diffusion Driven Neural Representation
- 1 Introduction
- 2 Method
- 2.1 Problem Formulation
- 2.2 Data-Prior Sub-problem Solved by Diffusion Model
- 2.3 Data-Fidelity Sub-problem Solved by INR
- 3 Experiments
- 3.1 Setup
- 3.2 Results
- 4 Conclusion
- References
- Correction to: Noise Level Adaptive Diffusion Model for Robust Reconstruction of Accelerated MRI
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.