Fibernet 2.0: An Automatic Neural Network Based Tool for Clustering White Matter Fibers in the Brain

ABSTRACTThe brain’s white matter fiber tracts are impaired in a range of common and devastating conditions, from Alzheimer’s disease to brain trauma, and in developmental disorders such as autism and neurogenetic syndromes. Many studies now examine the connectivity and microstructure of the brain’s neural pathways, spurring the development of algorithms to extract and measure tracts and fiber bundles. Clustering white matter (WM) fibers, from whole-brain tractography, into anatomically meaningful bundles is still a challenging problem. Existing tract segmentation methods use atlases or regions of interest (ROI) or unsupervised spectral clustering. Even so, atlas-based segmentation does not always partition the brain into a set of recognizable fiber bundles. Deep learning techniques can be applied to automatically segment and cluster white matter fibers. Here we propose a robust approach using convolutional neural networks (CNNs) to learn shape features of the fiber bundles, which we then exploit to cluster WM fibers into bundles. In a range of tests across diverse fiber bundles, we illustrate the accuracy of our method, and its ability to suppress false positive fibers.

Download Full-text

FiberNET: An ensemble deep learning framework for clustering white matter fibers

10.1101/141036 ◽

2017 ◽

Author(s):

Vikash Gupta ◽

Sophia I. Thomopoulos ◽

Faisal M. Rashid ◽

Paul M. Thompson

Keyword(s):

Deep Learning ◽

White Matter ◽

Structural Integrity ◽

Region Of Interest ◽

Fiber Bundles ◽

Anatomical Connectivity ◽

Learning Framework ◽

Fiber Clustering ◽

Learning Techniques ◽

The Brain

AbstractWhite matter tracts are commonly analyzed in studies of micro-structural integrity and anatomical connectivity in the brain. Over the last decade, it has been an open problem as to how best to cluster white matter fibers, extracted from whole-brain tractography, into anatomically meaningful groups. Some existing techniques use region of interest (ROI) based clustering, atlas-based labeling, or unsupervised spectral clustering. ROI-based clustering is popular for analyzing anatomical connectivity among a set of ROIs, but it does not always partition the brain into recognizable fiber bundles. Here we propose an approach using convolutional neural networks (CNNs) to learn shape features of the fiber bundles, which are then exploited to cluster white matter fibers. To achieve such clustering, we first need to re-parameterize the fibers in an intrinsic space. The clustering is performed in induced parameterized coordinates. To our knowledge, this is one of the first approaches for fiber clustering using deep learning techniques. The results show strong accuracy - on a par with or better than other state-of-the-art methods.

Download Full-text

Spreading of multiple Listeria monocytogenes abscesses via central nervous system fiber tracts: case report

Journal of Neurosurgery ◽

10.3171/2014.12.jns142100 ◽

2015 ◽

Vol 123 (6) ◽

pp. 1593-1599 ◽

Cited By ~ 9

Author(s):

Michel W. Bojanowski ◽

Romuald Seizeur ◽

Khaled Effendi ◽

Patrick Bourgouin ◽

Elsa Magro ◽

...

Keyword(s):

Central Nervous System ◽

Nervous System ◽

Listeria Monocytogenes ◽

White Matter ◽

Animal Studies ◽

Distinct Pattern ◽

Similar Process ◽

Fiber Tracts ◽

White Matter Fiber Tracts ◽

The Brain

Animal studies have shown that Listeria monocytogenes can probably access the brain through a peripheral intraneural route, and it has been suggested that a similar process may occur in humans. However, thus far, its spreading through the central nervous system (CNS) has not been completely elucidated. The authors present a case of multiple L. monocytogenes cerebral abscesses characterized by a pattern of distribution that suggested spread along white matter fiber tracts and reviewed the literature to identify other cases for analysis. They elected to include only those cases with 3 or more cerebral abscesses to make sure that the distribution was not random, but rather followed a pattern. In addition, they included those cases with abscesses in both the brainstem and the cerebral hemispheres, but excluded cases in which abscesses were located solely in the brainstem. Of 77 cases of L. monocytogenes CNS abscesses found in the literature, 17 involved multiple abscesses. Of those, 6 were excluded for lack of imaging and 3 because they involved only the brainstem. Of the 8 remaining cases from the literature, one was a case of bilateral abscesses that did not follow a fiber tract; another was also bilateral, but with lesions appearing to follow fiber tracts on one side; and in the remaining 6, to which the authors added their own case for a total of 7, all the abscesses were located exclusively in the same hemisphere and distributed along white matter fiber tracts. The findings suggest that after entering the CNS, L. monocytogenes travels within the axons, resulting in a characteristic pattern of distribution of multiple abscesses along the white matter fiber tracts in the brain. This report is the first description suggesting intraaxonal CNS spread of L. monocytogenes infection in humans following its entry into the brain. This distinct pattern is clearly seen on imaging and its recognition may be valuable in the diagnosis of listeriosis. This finding may allow for earlier diagnosis, which may improve outcome.

Download Full-text

White matter fiber tracts of the human brain: Three-dimensional mapping at microscopic resolution, topography and intersubject variability

NeuroImage ◽

10.1016/j.neuroimage.2005.08.040 ◽

2006 ◽

Vol 29 (4) ◽

pp. 1092-1105 ◽

Cited By ~ 276

Author(s):

Uli Bürgel ◽

Katrin Amunts ◽

Lars Hoemke ◽

Hartmut Mohlberg ◽

Joachim M. Gilsbach ◽

...

Keyword(s):

White Matter ◽

Human Brain ◽

Three Dimensional ◽

Intersubject Variability ◽

Fiber Tracts ◽

Three Dimensional Mapping ◽

White Matter Fiber Tracts ◽

Dimensional Mapping

Download Full-text

Fiber tractography bundle segmentation depends on scanner effects, acquisition, diffusion sensitization, and bundle segmentation workflow

10.1101/2021.03.17.435872 ◽

2021 ◽

Author(s):

Kurt Schilling ◽

Chantal M.W. Tax ◽

Francois Rheault ◽

Colin B Hansen ◽

Qi Yang ◽

...

Keyword(s):

White Matter ◽

Mean Diffusivity ◽

B Value ◽

Fiber Tractography ◽

Acquisition Protocol ◽

Segmentation Methods ◽

Combining Data ◽

Potential Sources ◽

Sources Of Variation ◽

The Brain

When investigating connectivity and microstructure of white matter pathways of the brain using diffusion tractography bundle segmentation, it is important to understand potential confounds and sources of variation in the process. While cross-scanner and cross-protocol effects on diffusion microstructure measures are well described (in particular fractional anisotropy and mean diffusivity), it is unknown how potential sources of variation effect bundle segmentation results, which features of the bundle are most affected, where variability occurs, nor how these sources of variation depend upon the method used to reconstruct and segment bundles. In this study, we investigate four potential sources of variation, or confounds, for bundle segmentation: variation (1) across scan repeats, (2) across scanners, (3) across acquisition protocol, and (4) across diffusion sensitization. We employ four different bundle segmentation workflows on two benchmark multi-subject cross-scanner and cross-protocol databases, and investigate reproducibility and biases in volume overlap, shape geometry features of fiber pathways, and microstructure features within the pathways. We find that the effects of acquisition protocol, in particular acquisition resolution, result in the lowest reproducibility of tractography and largest variation of features, followed by scanner-effects, and finally b-value effects which had similar reproducibility as scan-rescan variation. However, confounds varied both across pathways and across segmentation workflows, with some bundle segmentation workflows more (or less) robust to sources of variation. Despite variability, bundle dissection is consistently able to recover the same location of pathways in the deep white matter, with variation at the gray matter/ white matter interface. Next, we show that differences due to the choice of bundle segmentation workflows are larger than any other studied confound, with low-to-moderate overlap of the same intended pathway when segmented using different methods. Finally, quantifying microstructure features within a pathway, we show that tractography adds variability over-and-above that which exists due to noise, scanner effects, and acquisition effects. Overall, these confounds need to be considered when harmonizing diffusion datasets, interpreting or combining data across sites, and when attempting to understand the successes and limitations of different methodologies in the design and development of new tractography or bundle segmentation methods.

Download Full-text

The Structural Language Network

Language in Our Brain ◽

10.7551/mitpress/9780262036924.003.0004 ◽

2017 ◽

Author(s):

Angela D. Friederici ◽

Noam Chomsky

Keyword(s):

White Matter ◽

Language Processing ◽

Sentence Processing ◽

Information Transfer ◽

Right Hemisphere ◽

Brain Regions ◽

Neural Basis ◽

Fiber Tracts ◽

White Matter Fiber Tracts ◽

The Right

An adequate description of the neural basis of language processing must consider the entire network both with respect to its structural white matter connections and the functional connectivities between the different brain regions as the information has to be sent between different language-related regions distributed across the temporal and frontal cortex. This chapter discusses the white matter fiber bundles that connect the language-relevant regions. The chapter is broken into three sections. In the first, we look at the white matter fiber tracts connecting the language-relevant regions in the frontal and temporal cortices; in the second, the ventral and dorsal pathways in the right hemisphere that connect temporal and frontal regions; and finally in the third, the two syntax-relevant and (at least) one semantic-relevant neuroanatomically-defined networks that sentence processing is based on. From this discussion, it becomes clear that online language processing requires information transfer via the long-range white matter fiber pathways that connect the language-relevant brain regions within each hemisphere and between hemispheres.

Download Full-text

Early white matter development is abnormal in tuberous sclerosis complex patients who develop autism spectrum disorder

Journal of Neurodevelopmental Disorders ◽

10.1186/s11689-019-9293-x ◽

2019 ◽

Vol 11 (1) ◽

Cited By ~ 10

Author(s):

Anna K. Prohl ◽

◽

Benoit Scherrer ◽

Xavier Tomas-Fernandez ◽

Peter E. Davis ◽

...

Keyword(s):

Autism Spectrum Disorder ◽

White Matter ◽

Tuberous Sclerosis ◽

Tuberous Sclerosis Complex ◽

Neural Circuits ◽

Diffusion Tensor ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Fiber Bundles ◽

The Brain

Abstract Background Autism spectrum disorder (ASD) is prevalent in tuberous sclerosis complex (TSC), occurring in approximately 50% of patients, and is hypothesized to be caused by disruption of neural circuits early in life. Tubers, or benign hamartomas distributed stochastically throughout the brain, are the most conspicuous of TSC neuropathology, but have not been consistently associated with ASD. Widespread neuropathology of the white matter, including deficits in myelination, neuronal migration, and axon formation, exist and may underlie ASD in TSC. We sought to identify the neural circuits associated with ASD in TSC by identifying white matter microstructural deficits in a prospectively recruited, longitudinally studied cohort of TSC infants. Methods TSC infants were recruited within their first year of life and longitudinally imaged at time of recruitment, 12 months of age, and at 24 months of age. Autism was diagnosed at 24 months of age with the ADOS-2. There were 108 subjects (62 TSC-ASD, 55% male; 46 TSC+ASD, 52% male) with at least one MRI and a 24-month ADOS, for a total of 187 MRI scans analyzed (109 TSC-ASD; 78 TSC+ASD). Diffusion tensor imaging properties of multiple white matter fiber bundles were sampled using a region of interest approach. Linear mixed effects modeling was performed to test the hypothesis that infants who develop ASD exhibit poor white matter microstructural integrity over the first 2 years of life compared to those who do not develop ASD. Results Subjects with TSC and ASD exhibited reduced fractional anisotropy in 9 of 17 white matter regions, sampled from the arcuate fasciculus, cingulum, corpus callosum, anterior limbs of the internal capsule, and the sagittal stratum, over the first 2 years of life compared to TSC subjects without ASD. Mean diffusivity trajectories did not differ between groups. Conclusions Underconnectivity across multiple white matter fiber bundles develops over the first 2 years of life in subjects with TSC and ASD. Future studies examining brain-behavior relationships are needed to determine how variation in the brain structure is associated with ASD symptoms.

Download Full-text

Motor cortex gliomas induces microstructural changes of large fiber tracts revealed by TBSS

Scientific Reports ◽

10.1038/s41598-020-73746-1 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Xiangdong Wang ◽

Chunyao Zhou ◽

Lei Wang ◽

Yinyan Wang ◽

Tao Jiang

Keyword(s):

White Matter ◽

Motor Cortex ◽

Diffusion Tensor ◽

Early Stage ◽

Mean Diffusivity ◽

Cerebral White Matter ◽

Control Group ◽

Fiber Tracts ◽

3.0 T ◽

White Matter Fiber Tracts

Abstract Gliomas grow and invade along white matter fiber tracts. This study assessed the effects of motor cortex gliomas on the cerebral white matter fiber bundle skeleton. The motor cortex glioma group included 21 patients, and the control group comprised 14 healthy volunteers. Both groups underwent magnetic resonance imaging-based 3.0 T diffusion tensor imaging. We used tract-based spatial statistics to analyze the characteristics of white matter fiber bundles. The left and right motor cortex glioma groups were analyzed separately from the control group. Results were statistically corrected by the family-wise error rate. Compared with the controls, patients with left motor cortex gliomas exhibited significantly reduced fractional anisotropy and an increased radial diffusivity in the corpus callosum. The alterations in mean diffusivity (MD) and the axial diffusivity (AD) were widely distributed throughout the brain. Furthermore, atlas-based analysis showed elevated MD and AD in the contralateral superior fronto-occipital fasciculus. Motor cortex gliomas significantly affect white matter fiber microstructure proximal to the tumor. The range of affected white matter fibers may extend beyond the tumor-affected area. These changes are primarily related to early stage tumor invasion.

Download Full-text