A Restaurant Process Mixture Model for Connectivity Based Parcellation of the Cortex

@inproceedings{Moyer2017ARP,
  title={A Restaurant Process Mixture Model for Connectivity Based Parcellation of the Cortex},
  author={Daniel Moyer and Boris Gutman and Neda Jahanshad and Paul M. Thompson},
  booktitle={IPMI},
  year={2017}
}
One of the primary objectives of human brain mapping is the division of the cortical surface into functionally distinct regions, i.e. parcellation. [] Key Method Towards this end, we present a parcellation method based on a Bayesian non-parametric mixture model of cortical connectivity.
Product Space Decompositions for Continuous Representations of Brain Connectivity
We develop a method for the decomposition of structural brain connectivity estimates into locally coherent components, leveraging a non-parametric Bayesian hierarchical mixture model with tangent
Optimizing Connectivity-Driven Brain Parcellation Using Ensemble Clustering
TLDR
Ensemble parcellation was found to be highly stable with respect to subject sampling, outperforming anatomical atlases and other connectome-based parcellations in classification as well as preserving global connectome properties.

References

SHOWING 1-10 OF 28 REFERENCES
Tractography-Driven Groupwise Multi-scale Parcellation of the Cortex
TLDR
A groupwise parcellation method of the cortex based on diffusion MR images (dMRI) is proposed that borrows ideas from the area of cosegmentation in computer vision and directly estimate a consistentParcellation across different subjects and scales through a spectral clustering approach.
Connectivity‐based parcellation: Critique and implications
TLDR
This broad overview critically discusses the current state as well as the commonalities and idiosyncrasies of the main CBP methods to target frequent concerns faced by novices and veterans to provide a reference for the investigation and review of CBP studies.
A Continuous Model of Cortical Connectivity
TLDR
A continuous model for structural brain connectivity based on the Poisson point process is presented and it is shown how the approach can be used to assess the quality of cortical parcellations with respect to connectivty.
A Framework for Using Diffusion Weighted Imaging to Improve Cortical Parcellation
TLDR
This work introduces a framework to investigate the relationship between structure and function, with no a-priori knowledge of specific regions of interest, to better match connectivity information derived from diffusion weighted imaging.
Parcellating connectivity in spatial maps
TLDR
The parcellation method is specifically designed to respect spatial layout and identify locally-connected clusters, corresponding to plausible coherent units such as strings of adjacent DNA base pairs, subregions of the brain, animal communities, or geographic ecosystems.
Probabilistic Clustering of the Human Connectome Identifies Communities and Hubs
TLDR
A probabilistic model for connectivity-based parcellation of the human brain is introduced that allows quantification of the uncertainty in cluster assignments and shows that, while most clusters are clearly delineated, some regions are more difficult to assign.
...
...