Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation

  title={Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation},
  author={Xiao Liu and Spyridon Thermos and Alison Q. O'Neil and Sotirios A. Tsaftaris},
Generalising deep models to new data from new centres (termed here domains) remains a challenge. This is largely attributed to shifts in data statistics (domain shifts) between source and unseen domains. Recently, gradient-based meta-learning approaches where the training data are split into meta-train and meta-test sets to simulate and handle the domain shifts during training have shown improved generalisation performance. However, the current fully supervised meta-learning approaches are not… Expand

Figures and Tables from this paper

Causality-inspired Single-source Domain Generalization for Medical Image Segmentation
This work investigates the single-source domain generalization problem: training a deep network that is robust to unseen domains, under the condition that training data is only available from one source domain, which is common in medical imaging applications. Expand
A Tutorial on Learning Disentangled Representations in the Imaging Domain
This tutorial paper offers an overview of the disentangled representation learning, its building blocks and criteria, and discusses applications in computer vision and medical imaging, and presents the identified opportunities for the integration of recent machine learning advances into disentanglement. Expand
Domain and Content Adaptive Convolution for Domain Generalization in Medical Image Segmentation
The results indicate that the proposed DCAC model outperforms all competing methods on each segmentation task, and also demonstrate the effectiveness of the DAC. Expand
Weakly Supervised Volumetric Image Segmentation with Deformed Templates
This paper proposes an approach that is truly weakly-supervised in the sense that it only needs to provide a sparse set of 3D point on the surface of target objects, an easy task that can be quickly done. Expand


Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains
A novel shape-aware meta-learning scheme is presented to improve the model generalization in prostate MRI segmentation, and outperforms many state-of-the-art generalization methods consistently across all six settings of unseen domains. Expand
Domain Generalizer: A Few-shot Meta Learning Framework for Domain Generalization in Medical Imaging
The method learns a domain-agnostic feature representation to improve generalization of models to the unseen test distribution and employs few-shot learning, i.e. training the generalized model using very few examples from the unseen domain, to quickly adapt the model to new unseen data distribution. Expand
Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation
A deep stacked transformation approach for domain generalization that can be generalized to the design of highly robust deep segmentation models for clinical deployment and reaches the performance of state-of theart fully supervised models that are trained and tested on their source domains. Expand
Disentangled Representations for Domain-generalized Cardiac Segmentation
This paper proposes two data augmentation methods that focus on improving the domain adaptation and generalization abilities of state-to-the-art cardiac segmentation models, and generates more diverse data by rescaling images to different resolutions within a range spanning different scanner protocols. Expand
Domain Generalization via Model-Agnostic Learning of Semantic Features
This work investigates the challenging problem of domain generalization, i.e., training a model on multi-domain source data such that it can directly generalize to target domains with unknown statistics, and adopts a model-agnostic learning paradigm with gradient-based meta-train and meta-test procedures to expose the optimization to domain shift. Expand
Domain Generalization via Semi-supervised Meta Learning
The first method of domain generalization to leverage unlabeled samples is proposed, combining of meta learning's episodic training and semi-supervised learning, called DGSML, which employs an entropy-based pseudo-labeling approach to assign labels to unlabeling samples and utilizes a novel discrepancy loss. Expand
DIVA: Domain Invariant Variational Autoencoders
The Domain Invariant Variational Autoencoder (DIVA) is proposed, a generative model that tackles the problem of domain generalization by learning three independent latent subspaces, one for the domain,One for the class, and one for any residual variations. Expand
Self-Loop Uncertainty: A Novel Pseudo-Label for Semi-Supervised Medical Image Segmentation
A novel pseudo-label (namely self-loop uncertainty), generated by recurrently optimizing the neural network with a self-supervised task, is adopted as the ground-truth for the unlabeled images to augment the training set and boost the segmentation accuracy. Expand
Uncertainty-aware domain alignment for anatomical structure segmentation
An uncertainty-aware domain alignment framework to address the domain shift problem in the cross-domain Unsupervised Domain Adaptation (UDA) task is proposed and an Uncertainty Estimation and Segmentation Module (UESM) is designed to obtain the uncertainty map estimation. Expand
A Disentangled Latent Space for Cross-Site MRI Harmonization
A deep learning-based harmonization technique with limited supervision for use in standardization across scanners and sites and it is demonstrated that this allows cross-site harmonization without the need for paired data between sites. Expand