Search

PURPOSE: Mapping brain white matter (WM) is essential for building an understanding of brain anatomy and function. Tractography-based methods derived from diffusion-weighted MRI (dMRI) are the principal tools for investigating WM. These procedures rely on time-consuming dMRI acquisitions that may not always be available, especially for legacy or time-constrained studies. To address this problem, we aim to generate WM tracts from structural magnetic resonance imaging (MRI) image by deep learning. METHODS: Following recently proposed innovations in structural anatomical segmentation, we evaluate the feasibility of training multiply spatial localized convolution neural networks to learn context from fixed spatial patches from structural MRI on standard template. We focus on six widely used dMRI tractography algorithms (TractSeg, RecoBundles, XTRACT, Tracula, automated fiber quantification (AFQ), and AFQclipped) and train 125 U-Net models to learn these techniques from 3870 T1-weighted images from the Baltimore Longitudinal Study of Aging, the Human Connectome Project S1200 release, and scans acquired at Vanderbilt University. RESULTS: The proposed framework identifies fiber bundles with high agreement against tractography-based pathways with a median Dice coefficient from 0.62 to 0.87 on a test cohort, achieving improved subject-specific accuracy when compared to population atlas-based methods. We demonstrate the generalizability of the proposed framework on three externally available datasets. CONCLUSIONS: We show that patch-wise convolutional neural network can achieve robust bundle segmentation from T1w. We envision the use of this framework for visualizing the expected course of WM pathways when dMRI is not available.

Preterm birth still represents a concrete emergency to be managed and addressed globally. Since cerebral white matter injury is the major form of brain impairment in survivors of premature birth, the identification of reliable, non-invasive markers of altered white matter development is of utmost importance in diagnostics. Diffusion MRI has recently emerged as a valuable tool to investigate these kinds of alterations. In this work, rather than focusing on a single MRI modality, we worked on a compound of beyond-DTI High Angular Resolution Diffusion Imaging (HARDI) techniques in a group of 46 preterm babies studied on a 3T scanner at term equivalent age and in 23 control neonates born at term. After extracting relevant derived parameters, we examined discriminative patterns of preterm birth through (i) a traditional voxel-wise statistical method such as the Tract-Based Spatial Statistics approach (TBSS); (ii) an advanced Machine Learning approach such as the Support Vector Machine (SVM) classification; (iii) establishing the degree of association between the two methods in voting white matter most discriminating areas. Finally, we applied a multi-set Canonical Correlation Analysis (CCA) in search for sources of linked alterations across modalities. TBSS analysis showed significant differences between preterm and term cohorts in several white matter areas for multiple HARDI features. SVM classification performed on skeletonized HARDI measures produced satisfactory accuracy rates, especially as for highly informative parameters about fibers’ directionality. Assessment of the degree of overlap between the relevant measures identified by the two methods exhibited a good, though parameter-dependent rate of agreement. Finally, CCA analysis identified joint changes precisely for those features exhibiting less correspondence between TBSS and SVM. Our results suggest that a data-driven intramodal imaging approach is crucial to extract deep and complementary information that cannot be extracted from a single modality.

Nonlinear registration plays a central role in most neuroimage analysis methods and pipelines, such as in tractography-based individual and group-level analysis methods. However, nonlinear registration is a non-trivial task, especially when dealing with tractography data that digitally represent the underlying anatomy of the brain’s white matter. Furthermore, such process often changes the structure of the data, causing artifacts that can suppress the underlying anatomical and structural details. In this paper, we introduce BundleWarp, a novel and robust streamline-based nonlinear registration method for the registration of white matter tracts. BundleWarp intelligently warps two bundles while preserving the bundles’ crucial topological features. BundleWarp has two main steps. The first step involves the solution of an assignment problem that matches corresponding streamlines from the two bundles (iterLAP step). The second step introduces streamline-specific point-based deformations while keeping the topology of the bundle intact (mlCPD step).We provide comparisons against streamline-based linear registration and image-based nonlinear registration methods. BundleWarp quantitatively and qualitatively outperforms both, and we show that Bundle-Warp can deform and, at the same time, preserve important characteristics of the original anatomical shape of the bundles. Results are shown on 1,728 pairs of bundle registrations across 27 different bundle types. In addition, we present an application of BundleWarp for quantifying bundle shape differences using the generated deformation fields.

The anterior cingulate cortex (ACC) is functionally closely related with the insula and the ventral lateral prefrontal cortex (vlPFC). Extensive work on their functional relationships has led to the salience network theory and advanced understanding of value-based learning and decision making. However, the anatomical connections between the ACC and the two regions remain unknown in the human brain. Despite the anatomical ground truth established by nonhuman primate (NHP) tract-tracing, diffusion magnetic resonance imaging (dMRI) has not seen success identifying homologous pathways in humans. In this study we show that the negative finding does not reflect a cross-species discrepancy but rather a technical issue. We used NHP dMRI as a bridge to compare the ground-truth pathways in NHPs and dMRI-derived pathways in humans. The insight from NHP data helped pinpoint a bias in fiber orientation distribution functions (fODFs) caused by the disproportion of anterior-posterior vs. medial-lateral fibers in the human brain. Guided by this information, we successfully recovered the ACC-insula and ACC-vlPFC pathways that followed the same trajectories as in the NHP dMRI and tract-tracing data. Our findings provide an anatomical basis for the functional interactions among the ACC, the insula and the vlPFC.

Whole brain tractography is commonly used to study the brain’s white matter fiber pathways, but the large number of streamlines generated - up to one million per brain - can be challenging for large-scale population studies. We propose a robust dimensionality reduction framework for tractography, using a Convolutional Variational Autoencoder (ConvVAE) to learn low-dimensional embeddings from white matter bundles. The resulting embeddings can be used to facilitate downstream tasks such as outlier and abnormality detection, and mapping of disease effects on white matter tracts in individuals or groups. We design experiments to evaluate how well embeddings of different dimensions preserve distances from the original high-dimensional dataset, using distance correlation methods. We find that streamline distances and inter-bundle distances are well preserved in the latent space, with a 6-dimensional optimal embedding space. The generative ConvVAE model allows fast inference on new data, and the smooth latent space enables meaningful decodings that can be used for downstream tasks. We demonstrate the use of a ConvVAE model trained on control subjects’ data to detect structural anomalies in white matter tracts in patients with Alzheimer’s disease (AD). Using ConvVAEs to facilitate population analyses, we identified 6 tracts with statistically significant differences between AD and controls after controlling for age and sex effect, visualizing specific locations along the tracts with high anomalies despite large inter-subject variations in fiber bundle geometry.

Brain extraction is one of the first steps of pre-processing 3D brain MRI data and a prerequisite for any forthcoming brain imaging analyses. However, it is not a simple segmentation problem due to the complex structure of the brain and human head. Although multiple solutions have been proposed in the literature, we are still far from having truly robust methods. While previous methods have used machine learning with structural/geometric priors, with the development of Deep Learning (DL), there has been an increase in proposed Neural Network architectures. Most models focus on improving the training data and loss functions with little change in the architecture. However, the amount of accessible training data with expert-labelled ground truth vary between groups. Moreover, the labels are created not from scratch but from outputs of non-DL methods. Thus, most DL method's performance depend on the amount and quality of data one has. In this paper, we propose a novel architecture we call EVAC+ to work around this issue. We show that EVAC+ has 3 major advantages compared to other networks: (1) Multi-scale input with limited random augmentation for efficient learning, (2) a unique way of using Conditional Random Fields Recurrent Layer and (3) a loss function specifically created to enhance this architecture. We compare our model to state-of-the-art non-DL and DL methods. Results show that even with little change in the traditional architecture and limited training resources, EVAC+ achieves a high and stable Dice Coefficient and Jaccard Index along with a desirable lower surface distance. Ultimately, our model provides a robust way of accurately reducing segmentation errors in complex multi-tissue interfacing areas of brain., Replaced with advancements in the model and results

Diffusion-weighted magnetic resonance imaging (DWI) is the only noninvasive method for quantifying microstructure and reconstructing white-matter pathways in the living human brain. Fluctuations from multiple sources create significant additive noise in DWI data which must be suppressed before subsequent microstructure analysis. We introduce a self-supervised learning method for denoising DWI data, Patch2Self (P2S), which uses the entire volume to learn a full-rank locally linear denoiser for that volume. By taking advantage of the oversampled q-space of DWI data, P2S can separate structure from noise without requiring an explicit model for either. The setup of P2S however can be resource intensive, both in terms of running time and memory usage, as it uses all voxels (n) from all-but-one held-in volumes (d − 1) to learn a linear mapping Φ : ℝn×(d−1) ↦ ℝn for denoising the held-out volume. We exploit the redundancy imposed by P2S to alleviate its performance issues and inspect regions that influence the noise disproportionately. Specifically we introduce P2S-sketch, which makes a two-fold contribution: (1) P2S-sketch uses matrix sketching to perform self-supervised denoising. By solving a sub-problem on a smaller sub-space, so called, coreset, we show how P2S can yield a significant speedup in training time while using less memory. (2) We show how the so-called statistical leverage scores can be used to interpret the denoising of dMRI data, a process that was traditionally treated as a black-box. Our experiments conducted on simulated and real data clearly demonstrate that P2S via matrix sketching (P2S-sketch) does not lead to any loss in denoising quality, while yielding significant speedup and improved memory usage by training on a smaller fraction of the data. With thorough comparisons on real and simulated data, we show that Patch2Self outperforms the current state-of-the-art methods for DWI denoising both in terms of visual conspicuity and downstream modeling tasks. We demonstrate the effectiveness of our approach via multiple quantitative metrics such as fiber bundle coherence, R2 via cross-validation on model fitting, mean absolute error of DTI residuals across a cohort of sixty subjects.