Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 : 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part VI / edited by Linwei Wang, Qi Dou, P. Thomas Fletcher, Stefanie Speidel, Shuo Li.

Format:

Book

Contributor:

Wang, Linwei, editor.

Series:

Lecture Notes in Computer Science, 1611-3349 ; 13436

Language:

English

Subjects (All):

Image processing.

Image Processing.

Local Subjects:

Image Processing.

Physical Description:

1 online resource (841 pages)

Edition:

1st ed. 2022.

Place of Publication:

Cham : Springer Nature Switzerland : Imprint: Springer, 2022.

Summary:

The eight-volume set LNCS 13431, 13432, 13433, 13434, 13435, 13436, 13437, and 13438 constitutes the refereed proceedings of the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022, which was held in Singapore in September 2022. The 574 revised full papers presented were carefully reviewed and selected from 1831 submissions in a double-blind review process. The papers are organized in the following topical sections: Part I: Brain development and atlases; DWI and tractography; functional brain networks; neuroimaging; heart and lung imaging; dermatology; Part II: Computational (integrative) pathology; computational anatomy and physiology; ophthalmology; fetal imaging; Part III: Breast imaging; colonoscopy; computer aided diagnosis; Part IV: Microscopic image analysis; positron emission tomography; ultrasound imaging; video data analysis; image segmentation I; Part V: Image segmentation II; integration of imaging with non-imaging biomarkers; Part VI: Image registration; image reconstruction; Part VII: Image-Guided interventions and surgery; outcome and disease prediction; surgical data science; surgical planning and simulation; machine learning – domain adaptation and generalization; Part VIII: Machine learning – weakly-supervised learning; machine learning – model interpretation; machine learning – uncertainty; machine learning theory and methodologies. .

Contents:

Intro

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

2.1 Mean-Teacher Based Temporal Consistency Regularization

2.2 Double-Uncertainty Guided Adaptive Weighting

Unsupervised Deformable Image Registration with Absent Correspondences in Pre-operative and Post-recurrence Brain Tumor MRI Scans

2.1 Bidirectional Deformable Image Registration

2.2 Forward-Backward Consistency Constraint

2.3 Inverse Consistency

2.4 Objective Function

3 Experiments

On the Dataset Quality Control for Image Registration Evaluation

2 Method

2.1 Constructing the Variogram

2.2 Potential FLEs

2.3 Atypical Variogram Patterns

4 Discussion

Dual-Branch Squeeze-Fusion-Excitation Module for Cross-Modality Registration of Cardiac SPECT and CT

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

Embedding Gradient-Based Optimization in Image Registration Networks

References.

ContraReg: Contrastive Learning of Multi-modality Unsupervised Deformable Image Registration

2 Related Work

3 Methods

4 Experiments

5 Discussion

Swin-VoxelMorph: A Symmetric Unsupervised Learning Model for Deformable Medical Image Registration Using Swin Transformer

2.1 Network Structures

2.2 Loss Function

3.1 Datasets, Preprocessing and Evaluation Criteria

3.2 Results

4 Conclusions

Non-iterative Coarse-to-Fine Registration Based on Single-Pass Deep Cumulative Learning

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

DSR: Direct Simultaneous Registration for Multiple 3D Images

2 Methodology

2.1 Direct Bundle Adjustment

2.2 Simultaneous Registration Without Intensity Optimization

3.1 Simulated Experiments

3.2 In-Vivo Experiments

Multi-modal Retinal Image Registration Using a Keypoint-Based Vessel Structure Aligning Network

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

3.1 Multi-modal Retinal Datasets

3.2 Implementation and Experimental Details

3.3 Results

A Deep-Discrete Learning Framework for Spherical Surface Registration

2.1 Rotation Architecture.

2.2 Deep-Discrete Networks

Privacy Preserving Image Registration

2 Problem Statement

3.1 Secure Computation

3.2 PPIR: Privacy Preserving Image Registration

4 Experimental Results

Deformer: Towards Displacement Field Learning for Unsupervised Medical Image Registration

3 Experiments and Discussion

End-to-End Multi-Slice-to-Volume Concurrent Registration and Multimodal Generation

2.1 Synthetic CT Generation from MR

2.2 Multi-Slice-to-Volume Registration

3.1 Dataset and Preprocessing

3.3 Baseline Methods

3.4 Results for MR-to-CT Translation

3.5 Results for Multi-Slice-to-Volume Registration

Fast Spherical Mapping of Cortical Surface Meshes Using Deep Unsupervised Learning

2.1 Overall Design and Conception

2.2 Coarse-to-Fine Multi-resolution Framework

2.3 Loss Functions

3.1 Experimental Setting

Learning-Based US-MR Liver Image Registration with Spatial Priors

3 Results and Discussion

Unsupervised Deep Non-rigid Alignment by Low-Rank Loss and Multi-input Attention

2 Deep Non-rigid Alignment Using Low-Rank Loss

Transformer Lesion Tracker

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

LiftReg: Limited Angle 2D/3D Deformable Registration

2 Problem Formulation

3.1 PCA-Based Deformation Vector Field Subspace

3.2 Network Structure

3.3 Network Training

4.1 Data Preparation

4.2 Evaluation Metrics

4.3 Validation of the DVF Subspace

4.4 Pairwise 2D/3D Deformable Image Registration

XMorpher: Full Transformer for Deformable Medical Image Registration via Cross Attention

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

Weakly-Supervised Biomechanically-Constrained CT/MRI Registration of the Spine

4 Conclusion and Discussion

Collaborative Quantization Embeddings for Intra-subject Prostate MR Image Registration

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

3.1 Experimental Settings

3.2 Ablation Study

3.3 Comparison with Existing Methods

Mesh-Based 3D Motion Tracking in Cardiac MRI Using Deep Learning

2.1 Mesh Displacement Estimation

2.2 Mesh Prediction

2.3 Differentiable Mesh-to-Image Rasterizer

2.4 Optimization

Data-Driven Multi-modal Partial Medical Image Preregistration by Template Space Patch Mapping

2.1 Template-Space Patch Mapping (TSPM)

2.2 Pipeline Execution

Global Multi-modal 2D/3D Registration via Local Descriptors Learning

2 Approach

2.1 Challenges of Local Feature Extraction for Medical Images

2.2 Detector-Free Local Feature Networks

2.3 Multiple Frames

3.2 Baselines and Main Results

3.3 Ablation Studies

3.4 Similarity Visualization

Adapting the Mean Teacher for Keypoint-Based Lung Registration Under Geometric Domain Shifts

2.1 Problem Statement

2.2 Baseline Model

2.3 Domain-Adaptive Registration with the Mean Teacher

3.1 Experimental Setup

DisQ: Disentangling Quantitative MRI Mapping of the Heart

2.1 Overall Framework: Disentangling Latent Spaces

2.2 Bootstrapping Disentangled Representations

3.1 Dataset

3.2 Implementation

Learning Iterative Optimisation for Deformable Image Registration of Lung CT with Recurrent Convolutional Networks

1.1 Related Work

1.2 Adam Optimisation

1.3 Our Contribution

2.1 Pre-registration

2.2 Extraction of Optimisation Inputs

2.3 Optimiser Network

2.4 Comparison to Feed-Forward Nets and Adam Optimisation

Electron Microscope Image Registration Using Laplacian Sharpening Transformer U-Net

2.1 Displacement Field Generation

2.2 Feature Enhancement.

2.3 Cascaded Registration.

Notes:

Includes bibliographical references and index.

Other Format:

Print version: Wang, Linwei Medical Image Computing and Computer Assisted Intervention - MICCAI 2022

ISBN:

9783031164460

3031164466

OCLC:

1345279906