Brian G. Booth

Structural Network Analysis of Brain Development in Young Preterm Neonates

Preterm infants develop differently than those born at term and are at higher risk of brain pathology. Thus, an understanding of their development is of particular importance. Diffusion tensor imaging (DTI) of preterm infants offers a window into brain development at a very early age, an age at which that development is not yet fully understood. Recent works have used DTI to analyze structural connectome of the brain scans using network analysis. These studies have shown that, even from infancy, the brain exhibits small-world properties. Here we examine a cohort of 47 normal preterm neonates (i.e., without brain injury and with normal neurodevelopment at 18 months of age) scanned between 27 and 45 weeks post-menstrual age to further the understanding of how the structural connectome develops. We use full-brain tractography to find white matter tracts between the 90 cortical and sub-cortical regions defined in the University of North Carolina Chapel Hill neonatal atlas. We then analyze the resulting connectomes and explore the differences between weighting edges by tract count versus fractional anisotropy. We observe that the brain networks in preterm infants, much like infants born at term, show high efficiency and clustering measures across a range of network scales. Further, the development of many individual region-pair connections, particularly in the frontal and occipital lobes, is significantly correlated with age. Finally, we observe that the preterm infant connectome remains highly efficient yet becomes more clustered across this age range, leading to a significant increase in its small-world structure.

BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopment

Abstract We propose BrainNetCNN, a convolutional neural network (CNN) framework to predict clinical neurodevelopmental outcomes from brain networks. In contrast to the spatially local convolutions done in traditional image‐based CNNs, our BrainNetCNN is composed of novel edge‐to‐edge, edge‐to‐node and node‐to‐graph convolutional filters that leverage the topological locality of structural brain networks. We apply the BrainNetCNN framework to predict cognitive and motor developmental outcome scores from structural brain networks of infants born preterm. Diffusion tensor images (DTI) of preterm infants, acquired between 27 and 46 weeks gestational age, were used to construct a dataset of structural brain connectivity networks. We first demonstrate the predictive capabilities of BrainNetCNN on synthetic phantom networks with simulated injury patterns and added noise. BrainNetCNN outperforms a fully connected neural‐network with the same number of model parameters on both phantoms with focal and diffuse injury patterns. We then apply our method to the task of joint prediction of Bayley‐III cognitive and motor scores, assessed at 18 months of age, adjusted for prematurity. We show that our BrainNetCNN framework outperforms a variety of other methods on the same data. Furthermore, BrainNetCNN is able to identify an infants postmenstrual age to within about 2 weeks. Finally, we explore the high‐level features learned by BrainNetCNN by visualizing the importance of each connection in the brain with respect to predicting the outcome scores. These findings are then discussed in the context of the anatomy and function of the developing preterm infant brain. HighlightsFirst deep convolutional neural network architecture designed for connectomes.Novel convolutional layers for leveraging topological locality in brain networks.Prediction of neurodevelopmental outcomes in preterm infants.Visualization of brain connections learned to be important for prediction.

Prediction of Motor Function in Very Preterm Infants Using Connectome Features and Local Synthetic Instances

We propose a method to identify preterm infants at highest risk of adverse motor function identified at 18 months of age using connectome features from a diffusion tensor image DTI acquired shortly after birth. For each full-brain DTI, a connectome is constructed and network features are extracted. After further reducing the dimensionality of the feature vector via PCA, SVM is used to discriminate between normal and abnormal motor scores. We further introduce a novel method to produce realistic synthetic training data in order to reduce the effects of class imbalance. Our method is tested on a dataset of 168 DTIs of 115 very preterm infants, scanned between 27 and 45 weeks post-menstrual age. We show that using our synthesized training data can consistently improve classification accuracy while setting a baseline for this challenging prediction problem. This work presents the first image analysis approach to predicting impairment in motor function in preterm-born infants.

K-confidence: Assessing uncertainty in tractography using K optimal paths

Tractography algorithms are susceptible to errors due to poor image quality. As a result, having some measure of confidence in the anatomical accuracy of a tractography result is a desirable goal. We propose that such a measure of confidence can be obtained from the spatial distribution of likely paths between two fixed endpoints. We present for the first time a k optimal paths tractography algorithm for determining the k most likely fiber tract trajectories between two fixed regions. We further examine the spatial spread of the k optimal fiber paths to obtain a measure of confidence that two regions are connected by an axonal fiber. We show on both synthetic and real data that the uniformity of the spread of the k optimal paths shows good correspondence with anatomically known connectivity.

Multi-region competitive tractography via graph-based random walks

We propose a multi-region approach to tractography that not only allows for competition between seed regions, but also allows for the incorporation of knowledge beyond a local scale. By formulating tractography as a graph-based random walk, we are able to obtain a closed-form solution for connection probabilities. Results on synthetic data and thirty images from the MIDAS database show that the introduction of competition reduces erroneous connectivity to regions outside the seeded tracts.

STEAM — Statistical Template Estimation for Abnormality Mapping: A personalized DTI analysis technique with applications to the screening of preterm infants

We introduce the STEAM DTI analysis engine: a whole brain voxel-based analysis technique for the examination of diffusion tensor images (DTIs). Our STEAM analysis technique consists of two parts. First, we introduce a collection of statistical templates that represent the distribution of DTIs for a normative population. These templates include various diffusion measures from the full tensor, to fractional anisotropy, to 12 other tensor features. Second, we propose a voxel-based analysis (VBA) pipeline that is reliable enough to identify areas in individual DTI scans that differ significantly from the normative group represented in the STEAM statistical templates. We identify and justify choices in the VBA pipeline relating to multiple comparison correction, image smoothing, and dealing with non-normally distributed data. Finally, we provide a proof of concept for the utility of STEAM on a cohort of 134 very preterm infants. We generated templates from scans of 55 very preterm infants whose T1 MRI scans show no abnormalities and who have normal neurodevelopmental outcome. The remaining 79 infants were then compared to the templates using our VBA technique. We show: (a) that our statistical templates display the white matter development expected over the modeled time period, and (b) that our VBA results detect abnormalities in the diffusion measurements that relate significantly with both the presence of white matter lesions and with neurodevelopmental outcomes at 18months. Most notably, we show that STEAM produces personalized results while also being able to highlight abnormalities across the whole brain and at the scale of individual voxels. While we show the value of STEAM on DTI scans from a preterm infant cohort, STEAM can be equally applied to other cohorts as well. To facilitate this whole-brain personalized DTI analysis, we made STEAM publicly available at http://www.sfu.ca/bgb2/steam.

Exact integration of diffusion orientation distribution functions for graph-based diffusion MRI analysis

Graph-based image analysis methods are increasingly being applied to diffusion MRI (dMRI) analysis. Unfortunately, weighting the graph for these methods involves solving a complex integral of an orientation distribution function (ODF). To date, these integrals have been approximated numerically at high computational cost and have resulted in numerical approximation errors that degrade dMRI analysis results. By exploiting a spherical harmonic representation of the ODF, we derive for the first time an analytical solution to the edge weight integrals used in graph-based dMRI analysis. We further show that the computational efficiency of our analytical integration is over forty times faster than numerical approximation schemes on typical data sets. Further, we incorporate our exact integration scheme into an existing graph-based probabilistic tractography method and show a reduction in error accumulation in the resulting tractograms.

Predictive Subnetwork Extraction with Structural Priors for Infant Connectomes

We present a new method to identify anatomical subnetworks of the human white matter connectome that are predictive of neurodevelopmental outcomes. We employ our method on a dataset of 168 preterm infant connectomes, generated from diffusion tensor images (DTI) taken shortly after birth, to discover subnetworks that predict scores of cognitive and motor development at 18 months. Predictive subnetworks are extracted via sparse linear regression with weights on each connectome edge. By enforcing novel backbone network and connectivity based priors, along with a non-negativity constraint, the learned subnetworks are simultaneously anatomically plausible, well connected, positively weighted and reasonably sparse. Compared to other state-of-the-art subnetwork extraction methods, we found that our approach extracts subnetworks that are more integrated, have fewer noisy edges and that are also better predictive of neurodevelopmental outcomes.

Uncertainty in Tractography via Tract Confidence Regions

Tractography allows us to explore white matter connectivity in diffusion MR images of the brain. However, noise, artifacts and limited resolution introduce uncertainty into the results. We propose a statistical model that allows us to quantify and visualize the uncertainty of a neuronal pathway between any two fixed anatomical regions. Given a sample set of tract curves obtained via tractography, we use our statistical model to define a confidence region that exposes the location and magnitude of tract uncertainty. The approach is validated on both synthetic and real diffusion MR data and is shown to highlight uncertain regions that occur due to noise, fiber crossings, or pathology.

Consistent Information Content Estimation for Diffusion Tensor MR Images

We propose novel information content estimators for diffusion tensor images using binless approaches based on nearest-neighbour distances. Combining these estimators with existing tensor distance metrics allows us to generate entropy estimates that are consistent and accurate for diffusion tensor data. Further, we are able to obtain such estimators without having to reduce the dimensionality of the tensor data to the point where a binning estimator can be reliably used. We test our estimators in the context of noise estimation, image segmentation, and image registration. Results on 12 datasets from LBAM and 50 datasets from LONI show our estimators more accurately reflect the underlying DTI data and provide faster convergence rates for image segmentation and registration algorithms.