Multivariate mixture model for myocardium segmentation combining multi-source images

Abstract

This paper proposes a method for simultaneous segmentation of multi-source images, using the multivariate mixture model (MvMM) and maximum of log-likelihood (LL) framework. The segmentation is a procedure of texture classification, and the MvMM is used to model the joint intensity distribution of the images. Specifically, the method is applied to the myocardial segmentation combining the complementary texture information from multi-sequence (MS) cardiac magnetic resonance (CMR) images. Furthermore, there exist inter-image mis-registration and intra-image misalignment of slices in the MS CMR images. Hence, the MvMM is formulated with transformations, which are embedded into the LL framework and optimized simultaneously with the segmentation parameters. The proposed method is able to correct the inter- and intra-image misalignment by registering each slice of the MS CMR to a virtual common space, as well as to delineate the indistinguishable boundaries of myocardium consisting of pathologies. Results have shown statistically significant improvement in the segmentation performance of the proposed method with respect to the conventional approaches which can solely segment each image separately. The proposed method has also demonstrated better robustness in the incongruent data, where some images may not fully cover the region of interest and the full coverage can only be reconstructed combining the images from multiple sources.

References in corpus (4)

• A Survey on Deep Learning in Medical Image Analysis
• Markov Random Field Segmentation of Brain MR Images
• Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features
• Three-Dimensional Segmentation of the Left Ventricle in Late Gadolinium Enhanced MR Images of Chronic Infarction Combining Long- and Short-Axis Information

Cited by in corpus (38)

• Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels
• Recent Progress in Transformer-based Medical Image Analysis
• Learning Disentangled Representations in the Imaging Domain
• Disentangle, align and fuse for multimodal and semi-supervised image segmentation
• Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation
• MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images
• $\mathcal{X}$-Metric: An N-Dimensional Information-Theoretic Framework for Groupwise Registration and Deep Combined Computing
• QMaxViT-Unet+: A Query-Based MaxViT-Unet with Edge Enhancement for Scribble-Supervised Segmentation of Medical Images
• Automated Multi-sequence Cardiac MRI Segmentation Using Supervised Domain Adaptation
• Domain generalization in deep learning for contrast-enhanced imaging
• Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation
• Cutting-edge 3D Medical Image Segmentation Methods in 2020: Are Happy Families All Alike?
• A Systematic Collection of Medical Image Datasets for Deep Learning
• Error correcting 2D-3D cascaded network for myocardial infarct scar segmentation on late gadolinium enhancement cardiac magnetic resonance images
• Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review
• Recent Advances in Fibrosis and Scar Segmentation from Cardiac MRI: A State-of-the-Art Review and Future Perspectives
• Extreme Cardiac MRI Analysis under Respiratory Motion: Results of the CMRxMotion Challenge
• Segmentation of Multimodal Myocardial Images Using Shape-Transfer GAN
• Brain Tumor Segmentation Network Using Attention-based Fusion and Spatial Relationship Constraint
• Cascaded Framework for Automatic Evaluation of Myocardial Infarction from Delayed-Enhancement Cardiac MRI
• Adversarial Convolutional Networks with Weak Domain-Transfer for Multi-Sequence Cardiac MR Images Segmentation
• Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information
• Anatomy Prior Based U-net for Pathology Segmentation with Attention
• Augmentation-based Domain Generalization and Joint Training from Multiple Source Domains for Whole Heart Segmentation
• Max-Fusion U-Net for Multi-Modal Pathology Segmentation with Attention and Dynamic Resampling
• Unsupervised Landmark Detection Based Spatiotemporal Motion Estimation for 4D Dynamic Medical Images
• MvMM-RegNet: A new image registration framework based on multivariate mixture model and neural network estimation
• Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration
• Multi-Modality Pathology Segmentation Framework: Application to Cardiac Magnetic Resonance Images
• Anatomically-Informed Deep Learning on Contrast-Enhanced Cardiac MRI for Scar Segmentation and Clinical Feature Extraction
• Recognition and standardization of cardiac MRI orientation via multi-tasking learning and deep neural networks
• Fully automated deep learning based segmentation of normal, infarcted and edema regions from multiple cardiac MRI sequences
• Synthetic Data Generation for 3D Myocardium Deformation Analysis
• DyABD: The Abdominal Muscle Segmentation in Dynamic MRI Benchmark
• Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation
• Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation
• Measure Anatomical Thickness from Cardiac MRI with Deep Neural Networks