To understand factors that affect brain connectivity and integrity, it is beneficial to automatically cluster white matter (WM) fibers into anatomically recognizable tracts. Whole brain tractography, based on diffusion-weighted MRI, generates vast sets of fibers throughout the brain; clustering them into consistent and recognizable bundles can be difficult as there are wide individual variations in the trajectory and shape of WM pathways. Here we introduce a novel automated tract clustering algorithm based on label fusion – a concept from traditional intensity-based segmentation. Streamline tractography generates many incorrect fibers, so our top-down approach extracts tracts consistent with known anatomy, by mapping multiple hand-labeled atlases into a new dataset. We fuse clustering results from different atlases, using a mean distance fusion scheme. We reliably extracted the major tracts from 105-gradient high angular resolution diffusion images (HARDI) of 198 young normal twins. To compute population statistics, we use a point-wise correspondence method to match, compare, and average WM tracts across subjects. We illustrate our method in a genetic study of white matter tract heritability in twins.

Alzheimer’s disease (AD) involves a gradual breakdown of brain connectivity, and network analyses offer a promising new approach to track and understand disease progression. Even so, our ability to detect degenerative changes in brain networks depends on the methods used. Here we compared several tractography and feature extraction methods to see which ones gave best diagnostic classification for 202 people with AD, mild cognitive impairment or normal cognition, scanned with 41-gradient diffusion-weighted magnetic resonance imaging as part of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) project. We computed brain networks based on whole brain tractography with nine different methods – four of them tensor-based deterministic (FACT, RK2, SL, and TL), two orientation distribution function (ODF)-based deterministic (FACT, RK2), two ODF-based probabilistic approaches (Hough and PICo), and one “ball-and-stick” approach (Probtrackx). Brain networks derived from different tractography algorithms did not differ in terms of classification performance on ADNI, but performing principal components analysis on networks helped classification in some cases. Small differences may still be detectable in a truly vast cohort, but these experiments help assess the relative advantages of different tractography algorithms, and different post-processing choices, when used for classification.

Traumatic brain injury (TBI) often results in traumatic axonal injury and white matter (WM) damage, particularly to the corpus callosum (CC).Damage to the CC can lead to impaired performance on neurocognitive tasks, but there is a high degree of heterogeneity in impairment following TBI. Here we examined the relation between CC microstructure and function in pediatric TBI. We used high angular resolution diffusion-weighted imaging (DWI) to evaluate the structural integrity of the CC in humans following brain injury in a sample of 32 children (23 males and 9 females) with moderate-to-severe TBI (msTBI) at 1-5 months postinjury, compared with well matched healthy control children. We assessed CC function through interhemispheric transfer time (IHTT) as measured using eventrelated potentials (ERPs), and related this to DWI measures of WM integrity. Finally, the relation between DWI and IHTT results was supported by additional results of neurocognitive performance assessed using a single composite performance scale. Half of the msTBI participants (16 participants) had significantly slower IHTTs than the control group. This slow IHTT group demonstrated lower CC integrity (lower fractional anisotropy and higher mean diffusivity) and poorer neurocognitive functioning than both the control group and the msTBI group with normal IHTTs. Lower fractional anisotropy-a common sign of impaired WM-and slower IHTTs also predicted poor neurocognitive function. This study reveals that there is a subset of pediatric msTBI patients during the post-acute phase of injury who have markedly impaired CC functioning and structural integrity that is associated with poor neurocognitive functioning. Key words: corpus callosum; DTI; ERP; interhemispheric transfer time; traumatic brain injury Significance StatementTraumatic brain injury (TBI) is the primary cause of death and disability in children and adolescents. There is considerable heterogeneity in postinjury outcome, which is only partially explained by injury severity. Imaging biomarkers may help explain some of this variance, as diffusion weighted imaging is sensitive to the white matter disruption that is common after injury. The corpus callosum (CC) is one of the most commonly reported areas of disruption. In this multimodal study, we discovered a divergence within our pediatric moderate-to-severe TBI sample 1-5 months postinjury. A subset of the TBI sample showed significant impairment in CC function, which is supported by additional results showing deficits in CC structural integrity. This subset also had poorer neurocognitive functioning. Our research sheds light on postinjury heterogeneity.

Traumatic brain injury (TBI) is the leading cause of death and disability in children and can lead to a wide range of impairments. Brain imaging methods such as DTI (diffusion tensor imaging) are uniquely sensitive to the white matter (WM) damage that is common in TBI. However, higher-level analyses using tractography are complicated by the damage and decreased FA (fractional anisotropy) characteristic of TBI, which can result in premature tract endings. We used the newly developed autoMATE (automated multi-atlas tract extraction) method to identify differences in WM integrity. 63 pediatric patients aged 8–19 years with moderate/severe TBI were examined with cross sectional scanning at one or two time points after injury: a post-acute assessment 1–5 months post-injury and a chronic assessment 13–19 months post-injury. A battery of cognitive function tests was performed in the same time periods. 56 children were examined in the first phase, 28 TBI patients and 28 healthy controls. In the second phase 34 children were studied, 17 TBI patients and 17 controls (27 participants completed both post-acute and chronic phases). We did not find any significant group differences in the post-acute phase. Chronically, we found extensive group differences, mainly for mean and radial diffusivity (MD and RD). In the chronic phase, we found higher MD and RD across a wide range of WM. Additionally, we found correlations between these WM integrity measures and cognitive deficits. This suggests a distributed pattern of WM disruption that continues over the first year following a TBI in children.

Cortical and subcortical nuclei degenerate in the dementias, but less is known about changes in the white matter tracts that connect them. To better understand white matter changes in behavioral variant frontotemporal dementia (bvFTD) and early-onset Alzheimer’s disease (EOAD), we used a novel approach to extract full 3D profiles of fiber bundles from diffusion-weighted MRI (DWI) and map white matter abnormalities onto detailed models of each pathway. The result is a spatially complex picture of tract-by-tract microstructural changes. Our atlas of tracts for each disease consists of 21 anatomically clustered and recognizable white matter tracts generated from whole-brain tractography in 20 patients with bvFTD, 23 with age-matched EOAD, and 33 healthy elderly controls. To analyze the landscape of white matter abnormalities, we used a point-wise tract correspondence method along the 3D profiles of the tracts and quantified the pathway disruptions using common diffusion metrics – fractional anisotropy, mean, radial, and axial diffusivity. We tested the hypothesis that bvFTD and EOAD are associated with preferential degeneration in specific neural networks. We mapped axonal tract damage that was best detected with mean and radial diffusivity metrics, supporting our network hypothesis, highly statistically significant and more sensitive than widely studied fractional anisotropy reductions. From white matter diffusivity, we identified abnormalities in bvFTD in all 21 tracts of interest but especially in the bilateral uncinate fasciculus, frontal callosum, anterior thalamic radiations, cingulum bundles and left superior longitudinal fasciculus. This network of white matter alterations extends beyond the most commonly studied tracts, showing greater white matter abnormalities in bvFTD versus controls and EOAD patients. In EOAD, network alterations involved more posterior white matter – the parietal sector of the corpus callosum and parahipoccampal cingulum bilaterally. Widespread but distinctive white matter alterations are a key feature of the pathophysiology of these two forms of dementia.

Autism spectrum disorder (ASD) is a wide range of disabilities that cause life-long cognitive impairment and social, communication, and behavioral challenges. Early diagnosis and medical intervention are important for improving the life quality of autistic patients. However, in the current practice, diagnosis often has to be delayed until the behavioral symptoms become evident during childhood. In this study, we demonstrate the feasibility of using machine learning techniques for identifying high-risk ASD infants at as early as six months after birth. This is based on the observation that ASD-induced abnormalities in white matter (WM) tracts and whole-brain connectivity have already started to appear within 24 months after birth. In particular, we propose a novel multikernel support vector machine classification framework by using the connectivity features gathered from WM connectivity networks, which are generated via multiscale regions of interest (ROIs) and multiple diffusion statistics such as fractional anisotropy, mean diffusivity, and average fiber length. Our proposed framework achieves an accuracy of 76% and an area of 0.80 under the receiver operating characteristic curve (AUC), in comparison to the accuracy of 70% and the AUC of 70% provided by the best single-parameter single-scale network. The improvement in accuracy is mainly due to the complementary information provided by multiparameter multiscale networks. In addition, our framework also provides the potential imaging connectomic markers and an objective means for early ASD diagnosis.

Alzheimer’s disease (AD) is an irreversible neurodegenerative disease and affects a large population in the world. Cognitive scores at multiple time points can be reliably used to evaluate the progression of the disease clinically. In recent studies, machine learning techniques have shown promising results on the prediction of AD clinical scores. However, there are multiple limitations in the current models such as linearity assumption and missing data exclusion. Here, we present a nonlinear supervised sparse regression–based random forest (RF) framework to predict a variety of longitudinal AD clinical scores. Furthermore, we propose a soft-split technique to assign probabilistic paths to a test sample in RF for more accurate predictions. In order to benefit from the longitudinal scores in the study, unlike the previous studies that often removed the subjects with missing scores, we first estimate those missing scores with our proposed soft-split sparse regression–based RF and then utilize those estimated longitudinal scores at all the previous time points to predict the scores at the next time point. The experiment results demonstrate that our proposed method is superior to the traditional RF and outperforms other state-of-art regression models. Our method can also be extended to be a general regression framework to predict other disease scores.

No abstract