Machine Learning in Medical Imaging: 12th International Workshop, MLMI 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, ... (Lecture Notes in Computer Science)

This book constitutes the proceedings of the 12th International Workshop on Machine Learning in Medical Imaging, MLMI 2021, held in conjunction with MICCAI 2021, in Strasbourg, France, in September 2021.* The 71 papers presented in this volume were carefully reviewed and selected from 92 submissions. They focus on major trends and challenges in the above-mentioned area, aiming to identify new-cutting-edge techniques and their uses in medical imaging. Topics dealt with are: deep learning, generative adversarial learning, ensemble learning, sparse learning, multi-task learning, multi-view learning, manifold learning, and reinforcement learning, with their applications to medical image analysis, computer-aided detection and diagnosis, multi-modality fusion, image reconstruction, image retrieval, cellular image analysis, molecular imaging, digital pathology, etc. *The workshop was held virtually. Preface Organization Contents Contrastive Representations for Continual Learning of Fine-Grained Histology Images*-8pt 1 Introduction 2 Methodology 2.1 Contrastive Learning 2.2 Contrastive Loss in Continual Learning 2.3 Collaborative Contrast in Continual Learning 3 Experiments and Results 3.1 Experimental Setup 3.2 Results and Analysis 4 Conclusion References Learning Transferable 3D-CNN for MRI-Based Brain Disorder Classification from Scratch: An Empirical Study 1 Introduction 2 Materials and Methodology 2.1 Studied Subjects and MR Image Pre-processing 2.2 Methodology 3 Transferability Vs. Different Network Architectures 4 Transferability Vs. Different Network Components 5 Transferability to Related Task 6 Conclusion and Future Work References Knee Cartilages Segmentation Based on Multi-scale Cascaded Neural Networks 1 Introduction 2 Method 2.1 The Overall Framework 2.2 The Two-Stage Cascaded Networks 2.3 Inception-Like Convolution Module 3 Experiments 3.1 Datasets and Implementation Details 3.2 Loss Function and Evaluation Metrics 3.3 Ablation Study 3.4 Comparsion with Other Methods 4 Conclusion References Deep PET/CT Fusion with Dempster-Shafer Theory for Lymphoma Segmentation 1 Introduction 2 Methods 2.1 Network Architecture 2.2 Evidential Fusion Strategy 2.3 Multi-task Loss Function 2.4 Implementation Details 3 Experiments and Analysis 3.1 Dataset and Preprocessing 3.2 Results and Discussion 4 Conclusion References Interpretable Histopathology Image Diagnosis via Whole Tissue Slide Level Supervision 1 Introduction 2 Methodology 2.1 WSI Input Module 2.2 Weight-Sharing CNN Module 2.3 Context-Capturing RNN Module 2.4 Feature Attention Module and Classification 3 Experiments 3.1 Dataset 3.2 Implementation Details 3.3 Performance Comparison 4 Conclusion References Variational Encoding and Decoding for Hybrid Supervision of Registration Network 1 Introduction 2 Method 3 Results 4 Conclusion References Multiresolution Registration Network (MRN) Hierarchy with Prior Knowledge Learning 1 Introduction 2 Method 2.1 Multiresolution Image Registration Hierarchy 2.2 Multiresolution Representation and Prior Knowledge Learning 2.3 Network Training Strategies 2.4 Algorithm Implementation 3 Results 3.1 Datasets and Experiment Setting 3.2 Algorithm Comparison 4 Conclusion References Learning to Synthesize 7 T MRI from 3 T MRI with Few Data by Deformable Augmentation 1 Introduction 2 Method 2.1 Dataset 2.2 Framework 2.3 Unlimited Data Augmentation 2.4 Synthesizing 7 T MRI with GAN 2.5 Disease Classification 2.6 Implement Details 3 Experiments and Results 3.1 Evaluation of Image Synthesis 3.2 Evaluation of Disease Classification 4 Conclusion References Rethinking Pulmonary Nodule Detection in Multi-view 3D CT Point Cloud Representation 1 Introduction 2 Methods 3 Experiments 3.1 Data and Training 3.2 Experiments on LUNA16 4 Discussions and Conclusions References End-to-End Lung Nodule Detection Framework with Model-Based Feature Projection Block 1 Introduction and Previous Work 2 Method 2.1 Overall Pipeline Description 2.2 Model-Based Feature Projection 2.3 Segmentation Network with Model-Based Feature Projection Blocks 3 Evaluation 3.1 Experiment on LUNA2016 3.2 Ablation Study 3.3 Real World Data Evaluation 4 Conclusion and Discussion References Learning Structure from Visual Semantic Features and Radiology Ontology for Lymph Node Classification on MRI 1 Introduction 2 Method 3 Experiments References Improving Joint Learning of Chest X-Ray and Radiology Report by Word Region Alignment 1 Introduction 2 Joint Image Text Representation Learning Network 2.1 Matching Images and Sentences 2.2 Aligning Image Regions and Report Phrases 2.3 Downstream Task 3 Experiments 3.1 Datasets 3.2 Implementation Details 3.3 Performances 4 Conclusion References Cell Counting by a Location-Aware Network 1 Introduction 1.1 Related Work 1.2 Motivation 1.3 Our Proposal and Contributions 2 Methodology 2.1 Network Architecture 2.2 Loss Function 3 Experiment and Results 3.1 Datasets and Evaluation Metric 3.2 Performance Comparison and Illustration 3.3 Ablation Study 4 Conclusion References Exploring Gyro-Sulcal Functional Connectivity Differences Across Task Domains via Anatomy-Guided Spatio-Temporal Graph Convolutional Networks 1 Introduction 2 Methods 2.1 Data Acquisition and Preprocessing 2.2 Anatomy-Guided Gyro-Sulcal Spatio-Temporal Graph Construction 2.3 AG-STGCN Modeling for Graph Classification 2.4 Gyro-Sulcal Functional Connectivity Difference Assessment Based on the Learned Edges of AG-STGCN 3 Results 3.1 Classification Performance Between Task Domain and Resting State 3.2 Functional Connectivity Differences Between Gyri and Sulci Within a Single Task Domain 3.3 Regularity and Variability of Functional Connectivity Differences Between Gyri and Sulci Across Task Domains 4 Conclusion References StairwayGraphNet for Inter- and Intra-modality Multi-resolution Brain Graph Alignment and Synthesis 1 Introduction 2 Proposed Method 3 Results and Discussion 4 Conclusion References Multi-Feature Semi-Supervised Learning for COVID-19 Diagnosis from Chest X-Ray Images 1 Introduction 2 Methods and Materials 3 Results 4 Conclusions References Transfer Learning with a Layer Dependent Regularization for Medical Image Segmentation 1 Introduction 2 Transfer Learning via Gradual Regularization 3 Network Implementation Details 4 Experiments and Results References Multi-scale Self-supervised Learning for Multi-site Pediatric Brain MR Image Segmentation with Motion/Gibbs Artifacts 1 Introduction 2 Dataset and Proposed M-SSL Method 2.1 The Proposed Method 2.2 Training Stage 2.3 Testing Stage 2.4 Implementation Details 3 Experimental Results 3.1 Ablation Study 3.2 Comparison Results on Pediatric Brain Images with Real Artifacts 3.3 Comparisons on Multi-site Infant Subjects in the ISeg-2019 Challenge 4 Conclusion References Deep Active Learning for Dual-View Mammogram Analysis 1 Introduction 2 Methods 2.1 Proposed Network Architectures 2.2 Dual-View Consistency 2.3 Active Learning Strategies 3 Experiments 3.1 Implementation Details 3.2 Results 4 Conclusion References Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound*-8pt 1 Introduction 2 Methodology 2.1 Multi-label Learning with Word Embeddings 2.2 GCN for Class Dependency Learning 2.3 Cluster Relabeled Contrastive Learning 3 Experimental Results 4 Conclusion References Semi-supervised Learning Regularized by Adversarial Perturbation and Diversity Maximization 1 Introduction 2 Method 3 Experiments and Results 4 Conclusion References TransforMesh: A Transformer Network for Longitudinal Modeling of Anatomical Meshes 1 Introduction 2 Method 2.1 Mesh Network 2.2 Transformer Network 2.3 Training Procedure 3 Experiments 3.1 Implementation Details 3.2 Longitudinal Shape Modeling 3.3 Results 3.4 Anomaly Visualization 4 Conclusion References A Recurrent Two-Stage Anatomy-Guided Network for Registration of Liver DCE-MRI 1 Introduction 2 Method 2.1 Network Structures 2.2 Recurrent Framework 2.3 The Training Strategy 3 Experiments 3.1 Dataset, Preprocessing and Implementation 3.2 Metrics for Evaluation 3.3 Comparison with Existing Methods 4 Conclusion References Learning Infant Brain Developmental Connectivity for Cognitive Score Prediction 1 Introduction 2 Dataset and Feature Extraction 3 CDC-Net 3.1 Region-Wise Development Module (RDM) 3.2 Inter-region Connectivity Module (ICM) 3.3 GCN-Based Score Predictor 4 Experiments 4.1 Ablation Study 4.2 Comparison with State-of-the-Art Methods 4.3 Illustration of Brain Region Developmental Connectivity 5 Conclusion References Hierarchical 3D Feature Learning for Pancreas Segmentation 1 Introduction 2 Related Work 3 Method 3.1 Volume Feature Encoding 3.2 Hierarchical Decoding 3.3 Pancreas Segmentation 4 Experiments 4.1 Dataset 4.2 Training and Evaluation Procedure 4.3 Results 5 Conclusion References Voxel-Wise Cross-Volume Representation Learning for 3D Neuron Reconstruction 1 Introduction 2 Method 2.1 Supervised Encoder-Decoder Neuron Segmentation 2.2 VCV-RL: Voxel-Wise Cross-Volume SimSiam Representation Learning 3 Experiments and Results 3.1 Dataset and Implementation Details 3.2 Results and Analysis 4 Conclusions References Diagnosis of Hippocampal Sclerosis from Clinical Routine Head MR Images Using Structure-constrained Super-Resolution Network 1 Introduction 2 Method 2.1 Overview of the Method 2.2 Proposed Deep Mapping Network (DMN) 2.3 Enhanced Loss Functions to Improve the SR Image Quality 2.4 Diagnosis for HS on Clinical Routine MR Images 3 Experiments 3.1 Data 3.2 Experimental Setting 3.3 Results 4 Conclusion References U-Net Transformer: Self and Cross Attention for Medical Image Segmentation 1 Introduction 2 The U-Transformer Network 2.1 Self-attention 2.2 Cross-attention 3 Experiments 3.1 U-Transformer Performances 3.2 U-Transformer Analysis and Properties 4 Conclusion References Pre-biopsy Multi-class Classification of Breast Lesion Pathology in Mammograms 1 Introduction 2 Methods 2.1 Dataset 2.2 Proposed Method 2.3 Model Training 3 Experiments and Results 4 Discussion References Co-segmentation of Multi-modality Spinal Image Using Channel and Spatial Attention 1 Introduction 2 Method 3 Experimental Results 4 Conclusion References Hetero-Modal Learning and Expansive Consistency Constraints for Semi-supervised Detection from Multi-sequence Data*-8pt 1 Introduction 2 Method 2.1 Hetero-Modal CenterNet 2.2 Semi-supervised Detection 3 Results 4 Conclusion References STRUDEL: Self-training with Uncertainty Dependent Label Refinement Across Domains 1 Introduction 1.1 Related Work 2 Methods 2.1 Problem Definition 2.2 STRUDEL: Self-training with Uncertainty 2.3 Uncertainty-Guided Pseudo Labels 2.4 Segmentation Backbone Architectures 3 Experiments and Results 3.1 Datasets 3.2 Implementation Details 3.3 Experiments 3.4 Results and Discussion 4 Conclusion References Deep Reinforcement Learning for L3 Slice Localization in Sarcopenia Assessment 1 Introduction 2 Background 3 Reinforcement Learning Strategy 3.1 Deep Q-Learning 3.2 Network Architecture 3.3 Training 4 Experiments and Results 4.1 Dataset 4.2 Results and Discussion 5 Conclusion References MIST GAN: Modality Imputation Using Style Transfer for MRI 1 Introduction 2 Proposed Framework 3 Results and Discussion 4 Conclusion References Biased Extrapolation in Latent Space for Imbalanced Deep Learning 1 Introduction 2 Biased Extrapolation 2.1 Probability Biased Sampling 2.2 Density Biased Sampling 2.3 Asymmetry Probability Biased Sampling 3 Experimental Evaluation 3.1 Ulcer Classification in Endoscopy Image 3.2 Cardiomegaly Detection from CXR 4 Conclusion References 3DMeT: 3D Medical Image Transformer for Knee Cartilage Defect Assessment 1 Introduction 2 Method 2.1 Transformer and ViT 2.2 Medical Image Transformer 2.3 ConvNet Teacher Mechanism 3 Experiment and Result 3.1 Dataset and Metrics 3.2 Efficiency and Performance: A Comparative Study with CNNs 3.3 Ablation Study 4 Conclusion References A Gaussian Process Model for Unsupervised Analysis of High Dimensional Shape Data 1 Introduction 2 Related Works 3 Methods 3.1 Gaussian Process Model 3.2 Optimization 4 Results 4.1 Legendre Data 4.2 Craniosynostosis Data 5 Conclusions References Standardized Analysis of Kidney Ultrasound Images for the Prediction of Pediatric Hydronephrosis Severity 1 Introduction 2 Materials 3 Methods 3.1 US Image Standardization 3.2 Prediction of Obstruction Severity 4 Experimental Results 5 Discussion 6 Conclusion References Automated Deep Learning-Based Detection of Osteoporotic Fractures in CT Images 1 Introduction 2 Methods 2.1 hNet: Vertebra Localization and Identification 2.2 fNet: Fracture Classification 2.3 Patient Level Aggregation 3 Experiments 3.1 hNet: Localization evaluation 3.2 fNet: Fracture Classifier Evaluation 3.3 Patient Level Evaluation 4 Discussion and Conclusions References GT U-Net: A U-Net Like Group Transformer Network for Tooth Root Segmentation 1 Introduction 2 Method 2.1 U-Net Like Group Transformer Network 2.2 Shape-Sensitive Fourier Descriptor Loss Function 3 Experiment 3.1 Tooth Root Segmentation Dataset 3.2 Implementation Details 3.3 Experimental Results 3.4 Performance on the Public DRIVE Dataset 4 Conclusion References Information Bottleneck Attribution for Visual Explanations of Diagnosis and Prognosis 1 Introduction 2 Related Work 3 Method 3.1 Information Bottleneck Attribution 4 Datasets 5 Experiments and Results 6 Discussion and Concluding Remarks References Stacked Hourglass Network with a Multi-level Attention Mechanism: Where to Look for Intervertebral Disc Labeling 1 Introduction 2 Literature Review 3 Proposed Method 3.1 Pre-processing 3.2 Proposed Model 3.3 Post-processing 4 Experimental Results 4.1 Metrics 4.2 Comparison Results 4.3 Effect of Attention Mechanism 5 Conclusion References TED-Net: Convolution-Free T2T Vision Transformer-Based Encoder-Decoder Dilation Network for Low-Dose CT Denoising 1 Introduction 2 Methods 2.1 Noise Model 2.2 Transformer Block 2.3 Token-to-Token Dilation Block 3 Experiments and Results 3.1 Ablation Study 4 Conclusion References Self-supervised Mean Teacher for Semi-supervised Chest X-Ray Classification 1 Introduction 2 Related Works 3 Method 3.1 Joint Contrastive Learning to Self-supervise the Mean-Teacher Pre-training 3.2 Fine-Tuning the Mean Teacher 4 Experiment 4.1 Dataset Setup 4.2 Implementation Details 4.3 Experimental Results 4.4 Ablation Study 5 Conclusion References VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning 1 Introduction 2 Methods 2.1 Cosine Embedding Based Instance Segmentation and Tracking 2.2 Voxel Embedding (Training Stage) 2.3 Voxel Embedding (Testing Stage) 2.4 3D Synchronization 3 Data and Implementation Details 4 Results 5 Conclusion References Using Spatio-Temporal Correlation Based Hybrid Plug-and-Play Priors (SEABUS) for Accelerated Dynamic Cardiac Cine MRI 1 Introduction 2 Method 2.1 Accelerated Dcc-MRI: FISTA Framework 2.2 The Hybrid P3 Based FISTA Framework: SEABUS-FCSA 3 Numerical Results 3.1 Experiment Setting 3.2 Reconstruction Performance 4 Conclusion References Window-Level Is a Strong Denoising Surrogate 1 Introduction 2 Methods 2.1 Denoising 2.2 Model Architecture and Training 3 Empirical Evaluation 3.1 Data 3.2 Implementation Details 3.3 Results and Discussion 4 Conclusions References Cardiovascular Disease Risk Improves COVID-19 Patient Outcome Prediction 1 Introduction 2 Materials and Methods 2.1 Datasets 2.2 Outcome Prediction Methods 2.3 Exploratory Statistical Analysis 2.4 Feature Selection 3 Results 3.1 Exploratory Analysis 3.2 Inclusion of CVD Risk Score in Patient Classification 4 Discussion and Conclusion References Self-supervision Based Dual-Transformation Learning for Stain Normalization, Classification and Segmentation 1 Introduction 2 Methods 3 Results 4 Conclusion References Deep Representation Learning for Image-Based Cell Profiling 1 Introduction 2 Methods 2.1 Framework Summary 2.2 Implementation Details 3 Experiments 3.1 Benchmark Methods 3.2 Benchmark Datasets 3.3 Evaluation Metrics 3.4 Evaluation Results 4 Conclusions References Detecting Extremely Small Lesions in Mouse Brain MRI with Point Annotations via Multi-task Learning 1 Introduction 2 Methods: Multi-task Learning 2.1 Distance Map Branch 2.2 Count Regression Branch 3 Experiments 3.1 Data Description 3.2 Preprocessing 3.3 Experimental Setup 3.4 Results 4 Conclusion References Morphology-Guided Prostate MRI Segmentation with Multi-slice Association 1 Introduction 2 Our Method 2.1 Morphology-Guided Coarse Segmentation 2.2 Fine Segmentation with Multi-slice Association 3 Implementation and Experiments 3.1 Data and Implementation Details 3.2 Experimental Results 4 Conclusion References Unsupervised Cross-modality Cardiac Image Segmentation via Disentangled Representation Learning and Consistency Regularization 1 Introduction 2 Method 2.1 Diverse Image Translation 2.2 Domain-Specific Segmentation 2.3 Implementation Details 3 Experiments and Results 4 Conclusion References Landmark-Guided Rigid Registration for Temporomandibular Joint MRI-CBCT Images with Large Field-of-View Difference 1 Introduction 2 Method 2.1 Overall Framework 2.2 Landmark Localization Network 2.3 Rigid Registration Network 3 Experiments 3.1 Data 3.2 Training Details 4 Conclusion References Spine-Rib Segmentation and Labeling via Hierarchical Matching and Rib-Guided Registration 1 Introduction 2 Method 2.1 Template Library Construction 2.2 Hierarchical Matching 2.3 Rib-Guided Registration 3 Experiments 3.1 Dataset and Evaluation Metrics 3.2 Implementation Details 3.3 Ablation Studies 3.4 Evaluation and Comparison 4 Conclusion References Multi-scale Segmentation Network for Rib Fracture Classification from CT Images 1 Introduction 2 Methods 2.1 Rib Fracture Detection 2.2 Rib Fracture Classification 3 Experiments 3.1 Dataset and Evaluation Metrics 3.2 Implementation Details 3.3 Results and Discussion 4 Conclusion References Knowledge-Guided Multiview Deep Curriculum Learning for Elbow Fracture Classification 1 Introduction 2 Related Work 3 Methods 3.1 Multiview Model Architecture 3.2 Transfer Learning from Pretrained Single-View Models 3.3 Knowledge-Guided Curriculum Learning 4 Experiments and Results 4.1 Experiment Settings 4.2 Results 5 Conclusion References Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification 1 Introduction 2 Methods 3 Datasets and Network Details 4 Experiments 5 Results 6 Conclusion References CorLab-Net: Anatomical Dependency-Aware Point-Cloud Learning for Automatic Labeling of Coronary Arteries 1 Introduction 2 Method 2.1 Anatomical Distance Field 2.2 Morphological Distance Field 2.3 Point-Cloud Deep Network 3 Experiments and Results 3.1 Dataset and Evaluation Metrics 3.2 Implementation Details 3.3 Comparison with Existing Methods 3.4 Ablation Study 4 Conclusion References A Hybrid Deep Registration of MR Scans to Interventional Ultrasound for Neurosurgical Guidance 1 Introduction 2 Material and Methods 2.1 Dataset 2.2 Proposed Workflow 3 Experimental Results 3.1 Experimental Setup 3.2 Registration Results 3.3 Comparison with the State-of-the-Art Methods 4 Conclusion References Segmentation of Peripancreatic Arteries in Multispectral Computed Tomography Imaging 1 Introduction 2 Method and Experiments 2.1 Dataset 2.2 Labeling Strategy 2.3 Training the Neural Network 2.4 Results 3 Discussion and Conclusion References SkullEngine: A Multi-stage CNN Framework for Collaborative CBCT Image Segmentation and Landmark Detection 1 Introduction 2 Methods 2.1 Scalable JSD Model for Coarse Segmentation and Global Landmark Detection 2.2 Bone Segmentation Refinement and Local Landmark Detection 3 Experiments and Results 3.1 Materials 3.2 Results 3.3 Implementation Details 4 Conclusion References Skull Segmentation from CBCT Images via Voxel-Based Rendering 1 Introduction 2 3D VoxelRend-Based U-Net 2.1 Memory Analysis of 3D U-Net 2.2 Network Architecture 2.3 Training and Inference 3 Experiments and Results 3.1 Dataset 3.2 Accuracy and Memory Usage Comparison 4 Conclusion References Alzheimer's Disease Diagnosis via Deep Factorization Machine Models 1 Introduction 2 Related Work 3 Methods 3.1 Embedding Layer 3.2 Factorization Machine 3.3 Deep Factorization Machine 4 Experiments 5 Results and Discussion 6 Conclusion References 3D Temporomandibular Joint CBCT Image Segmentation via Multi-directional Resampling Ensemble Learning Network 1 Introduction 2 Methods 2.1 Overview 2.2 Multi-directional Resampling Feature Extraction Network 2.3 Ensemble Learning Network 2.4 Loss Function 3 Experiments and Results 3.1 Dataset and Evaluation Metrics 3.2 Training Details 3.3 Ablation Study 3.4 Results Analysis 4 Conclusions References Vox2Surf: Implicit Surface Reconstruction from Volumetric Data 1 Introduction 2 Methods 2.1 Problem Formulation 2.2 Implicit Surface Reconstruction 2.3 Loss Function and Implementation Details 3 Experimental Results 3.1 Dataset and Preprocessing 3.2 Quantitative Evaluation 3.3 Qualitative Comparison 4 Conclusion References Clinically Correct Report Generation from Chest X-Rays Using Templates 1 Introduction 2 Background and Related Work 3 Template-Based Report Generation: CNN-TRG 4 Experiments 4.1 Datasets 4.2 Metrics 4.3 Baselines 5 Results 6 Limitations 7 Conclusions and Future Work References Extracting Sequential Features from Dynamic Connectivity Network with rs-fMRI Data for AD Classification*-8pt 1 Introduction 2 Method 2.1 Subjects and Data Preprocessing 2.2 Proposed RNN-Based Learning Framework 3 Experiment 3.1 Experimental Setting 3.2 Classification Performance 3.3 Visual Illustration of Discriminative Functional Connectivity 4 Conclusion References Integration of Handcrafted and Embedded Features from Functional Connectivity Network with rs-fMRI for Brain Disease Classification 1 Introduction 2 Method 2.1 Subjects 2.2 Image Preprocessing and Network Construction 2.3 Feature Learning 2.4 Classification 3 Experiment and Results 3.1 Experimental Setting 3.2 Methods for Comparison 3.3 Classification Performance 4 Conclusion References Detection of Lymph Nodes in T2 MRI Using Neural Network Ensembles 1 Introduction 2 Methods 3 Results and Discussion 4 Conclusion References Seeking an Optimal Approach for Computer-Aided Pulmonary Embolism Detection 1 Introduction 2 Materials 3 Methods 3.1 Image-Level Classification 3.2 Exam-Level Classification 4 Results and Discussion 5 Conclusion References Correction to: Machine Learning in Medical Imaging Correction to: C. Lian et al. (Eds.): Machine Learning in Medical Imaging, LNCS 12966, https://doi.org/10.1007/978-3-030-87589-3 Correction to: A Gaussian Process Model for Unsupervised Analysis of High Dimensional Shape Data Correction to: Chapter “A Gaussian Process Model for Unsupervised Analysis of High Dimensional Shape Data” in: C. Lian et al. (Eds.): Machine Learning in Medical Imaging, LNCS 12966, https://doi.org/10.1007/978-3-030-87589-3_37 Author Index