Graph Domain Adaptation for Alignment-Invariant Brain Surface Segmentation

  title={Graph Domain Adaptation for Alignment-Invariant Brain Surface Segmentation},
  author={Karthik Gopinath and Christian Desrosiers and H. Lombaert},
The varying cortical geometry of the brain creates numerous challenges for its analysis. Recent developments have enabled learning surface data directly across multiple brain surfaces via graph convolutions on cortical data. However, current graph learning algorithms do fail when brain surface data are misaligned across subjects, thereby affecting their ability to deal with data from multiple domains. Adversarial training is widely used for domain adaptation to improve the segmentation… 

Figures and Tables from this paper

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
This survey thoroughly review the different types of graph architectures and their applications in healthcare in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure, and electrical-based analysis.


Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
This work investigates unsupervised domain adaptation using adversarial neural networks to train a segmentation method which is more robust to differences in the input data, and which does not require any annotations on the test domain.
Graph Convolutions on Spectral Embeddings for Cortical Surface Parcellation
Constrained domain adaptation for segmentation
This work proposes to adapt segmentation networks with a constrained formulation, which embeds domain-invariant prior knowledge about the segmentation regions, based on a single loss in a single network, which simplifies adaptation by avoiding extra adversarial steps, while improving convergence and quality of training.
FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
This paper introduces the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems, and outperforms baselines across different settings on multiple large-scale datasets.
Learning to Adapt Structured Output Space for Semantic Segmentation
A multi-level adversarial network is constructed to effectively perform output space domain adaptation at different feature levels and it is shown that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.
Convolutional neural networks for mesh-based parcellation of the cerebral cortex
It is shown experimentally on the Human Connectome Project dataset that the proposed graph convolutional models outperform current state-ofthe-art and baselines, highlighting the potential and applicability of these methods to tackle neuroimaging challenges, paving the road towards a better characterization of brain diseases.
Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation
This study trained a CNN on legacy MR images of brain and evaluated the performance of the domain-adapted network on the same task with images from a different domain, substantially outperforming a similar network trained on the the same set of examples from scratch.
Domain adaptation for biomedical image segmentation using adversarial training
This work uses an adversarial based training approach to train CNNs to achieve good accuracy on the target domain and shows improvements on membrane detection between MIC-CAI 2016 CREMI challenge and ISBI2013 EM segmentation challenge datasets.
Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
A novel model framework for learning automatic X-ray image parsing from labeled CT scans is proposed and an added module leveraging the pre-trained DI2I to enforce segmentation consistency is introduced.
Spectral Forests: Learning of Surface Data, Application to Cortical Parcellation
The method, Spectral Forests, is shown to significantly improve the accuracy of cortical parcellations over standard Random Decision Forests over standard Dice overlaps, and produce accuracy equivalent to FreeSurfer in a fraction of its time 23 seconds versus 3 to 4 hours.