More Like this

1. ReAl-LiFE: Accelerating the Discovery of Individualized Brain Connectomes on GPUs

   Kumar, Sawan; Pestilli, Franco; Sreenivasan, Varsha; Talukdar, Partha; Sridharan, Devarajan (January 2019, Association for the Advancement of Artificial Intelligence)

   Diffusion imaging and tractography enable mapping structural connections in the human brain, in-vivo. Linear Fascicle Evaluation (LiFE) is a state-of-the-art approach for pruning spurious connections in the estimated structural connectome, by optimizing its fit to the measured diffusion data. Yet, LiFE imposes heavy demands on computing time, precluding its use in analyses of large connectome databases. Here, we introduce a GPU-based implementation of LiFE that achieves 50-100x speedups over conventional CPU-based implementations for connectome sizes of up to several million fibers. Briefly, the algorithm accelerates generalized matrix multiplications on a compressed tensor through efficient GPU kernels, while ensuring favorable memory access patterns. Leveraging these speedups, we advance LiFE’s algorithm by imposing a regularization constraint on estimated fiber weights during connectome pruning. Our regularized, accelerated, LiFE algorithm (“ReAl-LiFE”) estimates sparser connectomes that also provide more accurate fits to the underlying diffusion signal. We demonstrate the utility of our approach by classifying pathological signatures of structural connectivity in patients with Alzheimer’s Disease (AD). We estimated million fiber whole-brain connectomes, followed by pruning with ReAl-LiFE, for 90 individuals (45 AD patients and 45 healthy controls). Linear classifiers, based on support vector machines, achieved over 80% accuracy in classifying AD patients from healthy controls based on their ReAl-LiFE pruned structural connectomes alone. Moreover, classification based on the ReAl-LiFE pruned connectome outperformed both the unpruned connectome, as well as the LiFE pruned connectome, in terms of accuracy. We propose our GPU-accelerated approach as a widely relevant tool for non-negative least-squares optimization, across many domains. 

   more » « less
2. A Sparse Tensor Decomposition with Multi-Dictionary Learning Applied to Diffusion Brain Imaging

   Caiafa, Cesar F; Cichocki, A; Pestilli, Franco (June 2017, SPARS)

   We use a multidimensional signal representation that inte- grates diffusion Magnetic Resonance Imaging (dMRI) and tractography (brain connections) using sparse tensor decomposition. The representa- tion encodes brain connections (fibers) into a very-large, but sparse, core tensor and allows to predict dMRI measurements based on a dictionary of diffusion signals. We propose an algorithm to learn the constituent parts of the model from a dataset. The algorithm assumes a tractography model (support of core tensor) and iteratively minimizes the Frobenius norm of the error as a function of the dictionary atoms, the values of nonzero entries in the sparse core tensor and the fiber weights. We use a nonparametric dictionary learning (DL) approach to estimate signal atoms. Moreover, the algorithm is able to learn multiple dictionaries associated to different brain locations (voxels) allowing for mapping distinctive tissue types. We illustrate the algorithm through results obtained on a large in-vivo high-resolution dataset. 

   more » « less
3. Tractometry of the Human Connectome Project: resources and insights

   https://doi.org/10.3389/fnins.2024.1389680  

   Kruper, John; Hagen, McKenzie P; Rheault, François; Crane, Isaac; Gilmore, Asa; Narayan, Manjari; Motwani, Keshav; Lila, Eardi; Rorden, Chris; Yeatman, Jason D; et al (June 2024, Frontiers in Neuroscience)

   The Human Connectome Project (HCP) has become a keystone dataset in human neuroscience, with a plethora of important applications in advancing brain imaging methods and an understanding of the human brain. We focused on tractometry of HCP diffusion-weighted MRI (dMRI) data. We used an open-source software library (pyAFQ;https://yeatmanlab.github.io/pyAFQ) to perform probabilistic tractography and delineate the major white matter pathways in the HCP subjects that have a complete dMRI acquisition (n = 1,041). We used diffusion kurtosis imaging (DKI) to model white matter microstructure in each voxel of the white matter, and extracted tract profiles of DKI-derived tissue properties along the length of the tracts. We explored the empirical properties of the data: first, we assessed the heritability of DKI tissue properties using the known genetic linkage of the large number of twin pairs sampled in HCP. Second, we tested the ability of tractometry to serve as the basis for predictive models of individual characteristics (e.g., age, crystallized/fluid intelligence, reading ability, etc.), compared to local connectome features. To facilitate the exploration of the dataset we created a new web-based visualization tool and use this tool to visualize the data in the HCP tractometry dataset. Finally, we used the HCP dataset as a test-bed for a new technological innovation: the TRX file-format for representation of dMRI-based streamlines. We released the processing outputs and tract profiles as a publicly available data resource through the AWS Open Data program's Open Neurodata repository. We found heritability as high as 0.9 for DKI-based metrics in some brain pathways. We also found that tractometry extracts as much useful information about individual differences as the local connectome method. We released a new web-based visualization tool for tractometry --- “Tractoscope” (https://nrdg.github.io/tractoscope). We found that the TRX files require considerably less disk space - a crucial attribute for large datasets like HCP. In addition, TRX incorporates a specification for grouping streamlines, further simplifying tractometry analysis. 

   more » « less
4. Shape Analysis of White Matter Tracts via the Laplace-Beltrami Spectrum

   Kitchell, L; Bullock, D; Hayashi, S; Pestilli, F (September 2018, MICCAI SHAPEMI)

   Diffusion-weighted magnetic resonance imaging (dMRI) allows for non-invasive, detailed examination of the white matter structures of the brain. White matter tract-specific measures based on either the diffusion tensor model (e.g. FA, ADC, and MD) or tractography (e.g. volume, streamline count or density) are often compared between groups of subjects to localize differences within the white matter. Less commonly examined is the shape of the individual white matter tracts. In this paper, we propose to use the Laplace-Beltrami (LB) spectrum as a descriptor of the shape of white matter tracts. We provide an open, automated pipeline for the computation of the LB spectrum on segmented white matter tracts and demonstrate its efficacy through machine learning classification experiments. We show that the LB spectrum allows for distinguishing subjects diagnosed with bipolar disorder from age and sex-matched healthy controls, with classification accuracy reaching 95%. We further demonstrate that the results cannot be explained by traditional measures, such as tract volume, streamline count or mean and total length. The results indicate that there is valuable information in the anatomical shape of the human white matter tracts. 

   more » « less
5. Implementation considerations for deep learning with diffusion MRI streamline tractography

   ViewView ORCID ProfileLeon Y. Cai, Ho Hin (July 2023, Medical Imaging with Deep Learning (MIDL))

   One area of medical imaging that has recently experienced innovative deep learning advances is diffusion MRI (dMRI) streamline tractography with recurrent neural networks (RNNs). Unlike traditional imaging studies which utilize voxel-based learning, these studies model dMRI features at points in continuous space off the voxel grid in order to propagate streamlines, or virtual estimates of axons. However, implementing such models is nontrivial, and an open-source implementation is not yet widely available. Here, we describe a series of considerations for implementing tractography with RNNs and demonstrate they allow one to approximate a deterministic streamline propagator with comparable performance to existing algorithms. We release this trained model and the associated implementations leveraging popular deep learning libraries. We hope the availability of these resources will lower the barrier of entry into this field, spurring further innovation. 

   more » « less