Daniel Moyer

Continuous representations of brain connectivity using spatial point processes

HighlightsGeneralizes traditional connectome count matrices to spatial process of tracts.Provides fast estimator, with efficient hyper parameter tuning.Provides results showing improved reliability (as measured by ICC score).Includes demonstration analysis using analogous “degree” function.Significant differences in example analysis between sexes. Graphical abstract No Caption available. Abstract We present a continuous model for structural brain connectivity based on the Poisson point process. The model treats each streamline curve in a tractography as an observed event in connectome space, here the product space of the gray matter/white matter interfaces. We approximate the model parameter via kernel density estimation. To deal with the heavy computational burden, we develop a fast parameter estimation method by pre‐computing associated Legendre products of the data, leveraging properties of the spherical heat kernel. We show how our approach can be used to assess the quality of cortical parcellations with respect to connectivity. We further present empirical results that suggest that “discrete” connectomes derived from our model have substantially higher test‐retest reliability compared to standard methods. In this, the expanded form of this paper for journal publication, we also explore parcellation free analysis techniques that avoid the use of explicit partitions of the cortical surface altogether. We provide an analysis of sex effects on our proposed continuous representation, demonstrating the utility of this approach.

Evaluating 35 Methods to Generate Structural Connectomes Using Pairwise Classification

There is no consensus on how to construct structural brain networks from diffusion MRI. How variations in pre-processing steps affect network reliability and its ability to distinguish subjects remains opaque. In this work, we address this issue by comparing 35 structural connectome-building pipelines. We vary diffusion reconstruction models, tractography algorithms and parcellations. Next, we classify structural connectome pairs as either belonging to the same individual or not. Connectome weights and eight topological derivative measures form our feature set. For experiments, we use three test-retest datasets from the Consortium for Reliability and Reproducibility (CoRR) comprised of a total of 105 individuals. We also compare pairwise classification results to a commonly used parametric test-retest measure, Intraclass Correlation Coefficient (ICC) (Code and results are available at https://github.com/lodurality/35_methods_MICCAI_2017).

Alzheimer’s Disease Classification with Novel Microstructural Metrics from Diffusion-Weighted MRI

Alzheimer’s disease (AD) deficits may be due in part to declining white matter (WM) integrity and disrupted connectivity. Numerous diffusion-weighted MRI (dMRI) studies of AD report WM deficits based on tensor model metrics. New microstructural measures derived from additional dMRI models may carry different information about WM microstructure including the geometry of diffusion anisotropy, diffusivity, complexity, estimated number of distinguishable fiber compartments, number of crossing fibers and neurite dispersion. Here we aimed to find the most helpful dMRI metrics and brain regions from a set of 17 dMRI-derived feature maps, to predict diagnostic group (AD or healthy control). The best metrics for classification were non-tensor metrics in the hippocampus and temporal lobes, areas consistently implicated in AD.

Blockmodels for connectome analysis

In the present work we study a family of generative network model and its applications for modeling the human connectome. We introduce a minor but novel variant of the Mixed Membership Stochastic Blockmodel and apply it and two other related model to two human connectome datasets (ADNI and a Bipolar Disorder dataset) with both control and diseased subjects. We further provide a simple generative classifier that, alongside more discriminating methods, provides evidence that blockmodels accurately summarize tractography count networks with respect to a disease classification task.

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

One of the primary objectives of human brain mapping is the division of the cortical surface into functionally distinct regions, i.e. parcellation. While it is generally agreed that at macro-scale different regions of the cortex have different functions, the exact number and configuration of these regions is not known. Methods for the discovery of these regions are thus important, particularly as the volume of available information grows. Towards this end, we present a parcellation method based on a Bayesian non-parametric mixture model of cortical connectivity.

Connectivity-Driven Brain Parcellation via Consensus Clustering

We present two related methods for deriving connectivity-based brain atlases from individual connectomes. The proposed methods exploit a previously proposed dense connectivity representation, termed continuous connectivity, by first performing graph-based hierarchical clustering of individual brains, and subsequently aggregating the individual parcellations into a consensus parcellation. The search for consensus minimizes the sum of cluster membership distances, effectively estimating a pseudo-Karcher mean of individual parcellations. We assess the quality of our parcellations using (1) Kullback-Liebler and Jensen-Shannon divergence with respect to the dense connectome representation, (2) inter-hemispheric symmetry, and (3) performance of the simplified connectome in a biological sex classification task. We find that the parcellation based-atlas computed using a greedy search at a hierarchical depth 3 outperforms all other parcellation-based atlases as well as the standard Dessikan-Killiany anatomical atlas in all three assessments.

Unsupervised record matching with noisy and incomplete data

We consider the problem of duplicate detection in noisy and incomplete data: Given a large data set in which each record has multiple entries (attributes), detect which distinct records refer to the same real-world entity. This task is complicated by noise (such as misspellings) and missing data, which can lead to records being different, despite referring to the same entity. Our method consists of three main steps: creating a similarity score between records, grouping records together into “unique entities”, and refining the groups. We compare various methods for creating similarity scores between noisy records, considering different combinations of string matching, term frequency-inverse document frequency methods, and n-gram techniques. In particular, we introduce a vectorized soft term frequency-inverse document frequency method, with an optional refinement step. We also discuss two methods to deal with missing data in computing similarity scores. We test our method on the Los Angeles Police Department Field Interview Card data set, the Cora Citation Matching data set, and two sets of restaurant review data. The results show that the methods that use words as the basic units are preferable to those that use 3-grams. Moreover, in some (but certainly not all) parameter ranges soft term frequency-inverse document frequency methods can outperform the standard term frequency-inverse document frequency method. The results also confirm that our method for automatically determining the number of groups typically works well in many cases and allows for accurate results in the absence of a priori knowledge of the number of unique entities in the data set.

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 Gaussian components. This model provides a mechanism to share information across subjects while still including explicit mixture distributions of connections for each subject. It further uses mixture components defined directly on the surface of the brain, eschewing the usual graph-theoretic framework of structural connectivity in favor of a continuous model that avoids a priori assumptions of parcellation configuration. The results of two experiments on a test-retest dataset are presented, to validate the method. We also provide an example analysis of the components.

Cortical connectome registration using spherical demons

We present an algorithm to align cortical surface models based on structural connectivity. We follow the continuous connectivity approach,1, 2 assigning a dense connectivity to every surface point-pair. We adapt and modify an approach for aligning low-rank functional networks based on eigenvalue decomposition of individual connectomes.3 The spherical demons framework then provides a natural setting for inter-subject connectivity alignment, enforcing a smooth, anatomically plausible correspondence, and allowing us to incorporate anatomical as well as connectivity information. We apply our algorithm to 98 diffusion MRI images in an Alzheimers Disease study, and 731 healthy subjects from the Human Connectome Project. Our method consistently reduces connectome variability due to misalignment. Further, the approach reveals subtle disease effects on structural connectivity which are not seen when registering only cortical anatomy.