scholarly journals ReAl-LiFE: Accelerating the Discovery of Individualized Brain Connectomes on GPUs

2019 ◽  
Vol 33 ◽  
pp. 630-638 ◽  
Author(s):  
Sawan Kumar ◽  
Varsha Sreenivasan ◽  
Partha Talukdar ◽  
Franco Pestilli ◽  
Devarajan Sridharan
Keyword(s):  
Diffusion Imaging ◽  
Computing Time ◽  
Structural Connectivity ◽  
Real Life ◽  
Support Vector ◽  
Healthy Controls ◽  
Linear Classifiers ◽  
Generalized Matrix ◽  
Access Patterns

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.

scholarly journals Insights into the Connectivity of the Human Brain Using DTI

2012 ◽  
Vol 1 (1) ◽  
pp. 78-91 ◽  
Author(s):  
S Kollias
Keyword(s):  
Human Brain ◽  
Molecular Diffusion ◽  
Diffusion Tensor ◽  
Wide Spectrum ◽  
Diffusion Imaging ◽  
Structural Connectivity ◽  
Nerve Tissue ◽  
Mammalian Brain ◽  
Fibre Direction

Diffusion tensor imaging (DTI) is a neuroimaging MR technique, which allows in vivo and non-destructive visualization of myeloarchitectonics in the neural tissue and provides quantitative estimates of WM integrity by measuring molecular diffusion. It is based on the phenomenon of diffusion anisotropy in the nerve tissue, in that water molecules diffuse faster along the neural fibre direction and slower in the fibre-transverse direction. On the basis of their topographic location, trajectory, and areas that interconnect the various fibre systems of the mammalian brain are divided into commissural, projectional and association fibre systems. DTI has opened an entirely new window on the white matter anatomy with both clinical and scientific applications. Its utility is found in both the localization and the quantitative assessment of specific neuronal pathways. The potential of this technique to address connectivity in the human brain is not without a few methodological limitations. A wide spectrum of diffusion imaging paradigms and computational tractography algorithms has been explored in recent years, which established DTI as promising new avenue, for the non-invasive in vivo mapping of structural connectivity at the macroscale level. Further improvements in the spatial resolution of DTI may allow this technique to be applied in the near future for mapping connectivity also at the mesoscale level. DOI: http://dx.doi.org/10.3126/njr.v1i1.6330 Nepalese Journal of Radiology Vol.1(1): 78-91

Speeding up reactive transport simulations: statistical surrogates and caching of simulation results in lookup tables

2020 ◽  
Author(s):  
Marco De Lucia ◽  
Robert Engelmann ◽  
Michael Kühn ◽  
Alexander Lindemann ◽  
Max Lübke ◽  
...  
Keyword(s):  
Reactive Transport ◽  
Large Scale ◽  
Computing Time ◽  
Real Life ◽  
Data Driven ◽  
Support Vector ◽  
Coupled Transport ◽  
Charge Balance ◽  
Lookup Tables ◽  
Simulation Results

<p>A successful strategy for speeding up coupled reactive transport simulations at price of acceptable accuracy loss is to compute geochemistry, which represents the bottleneck of these simulations, through data-driven surrogates instead of ‘full physics‘ equation-based models [1]. A surrogate is a multivariate regressor trained on a set of pre-calculated geochemical simulations or potentially even at runtime during the coupled simulations. Many available algorithms and implementations are available from the thriving Machine Learning community: tree-based regressors such as Random Forests or xgboost, Artificial Neural Networks, Gaussian Processes and Support Vector Machines just to name a few. Given the ‘black-box‘ nature of the surrogates, however, they generally disregard physical constraints such as mass and charge balance, which are of course of paramount importance for coupled transport simulations. A runtime check of error of balances in the surrogate outcomes is therefore necessary: predictions offending a given tolerance must be rejected and the full physics chemical simulations run instead. Thus the practical speedup of this strategy is a tradeoff between careful training of the surrogate and run-time efficiency.</p><p><br>In this contribution we demonstrate that the use of surrogates can lead to a dramatic decrease of required computing time, with speedup factors in the order of 10 or even 100 in the most favorable cases. Thus, large scale simulations with some 10<sup>6</sup> grid elements are feasible on common workstations without requiring computation on HPC clusters [2].</p><p><span><br>Furthermore, we showcase our implementation of Distributed Hash Tables caching geochemical simulation results for further reuse in subsequent time steps. The computational advantage here stems from the fact that query and retrieval from lookup tables is much faster than both full physics geochemical simulations and surrogate predictions. Another advantage of this algorithm is that virtually no loss of accuracy is introduced in the simulations. Enabling the caching of geochemical simulations through DHT speeds up large scale reactive transport simulations up to a factor of four even when computing on several hundred </span><span>cores</span><span>.</span></p><p><br>These algorithmical developments are demonstrated in comparison with published reactive transport benchmarks and on a real-life scenario of CO<sub>2</sub> storage.</p><p> </p><p> </p><p><span>[1] </span><span>Jatnieks, J., De Lucia, M., Dransch, D., Sips, M. (2016): Data-driven surrogate model approach for improving the performance of reactive transport simulations. Energy Procedia </span><span>97</span><span>, pp. 447-453. DOI: 10.1016/j.egypro.2016.10.047</span></p><p>[2] De Lucia, M., Kempka, T., Jatnieks, J., Kühn, M. (2017): Integrating surrogate models into subsurface simulation framework allows computation of complex reactive transport scenarios. Energy Procedia 125, pp. 580-587. DOI: 10.1016/j.egypro.2017.08.200</p>

scholarly journals Iron accumulation in the oculomotor nerve of the progressive supranuclear palsy brain

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hansol Lee ◽  
Myung Jun Lee ◽  
Eun-Joo Kim ◽  
Gi Yeong Huh ◽  
Jae-Hyeok Lee ◽  
...  
Keyword(s):  
High Resolution ◽  
Progressive Supranuclear Palsy ◽  
Oculomotor Nerve ◽  
Iron Accumulation ◽  
Blue Staining ◽  
Normal Brain ◽  
Myelinated Fiber ◽  
Healthy Controls ◽  
Icp Ms

AbstractAbnormal iron accumulation around the substantia nigra (SN) is a diagnostic indicator of Parkinsonism. This study aimed to identify iron-related microarchitectural changes around the SN of brains with progressive supranuclear palsy (PSP) via postmortem validations and in vivo magnetic resonance imaging (MRI). 7 T high-resolution MRI was applied to two postmortem brain tissues, from one normal brain and one PSP brain. Histopathological examinations were performed to demonstrate the molecular origin of the high-resolution postmortem MRI findings, by using ferric iron staining, myelin staining, and two-dimensional laser ablation-inductively coupled plasma-mass spectrometry (LA-ICP-MS) imaging. In vivo iron-related MRI was performed on five healthy controls, five patients with Parkinson’s disease (PD), and five patients with PSP. In the postmortem examination, excessive iron deposition along the myelinated fiber at the anterior SN and third cranial nerve (oculomotor nerve) fascicles of the PSP brain was verified by LA-ICP-MS. This region corresponded to those with high R2* values and positive susceptibility from quantitative susceptibility mapping (QSM), but was less sensitive in Perls’ Prussian blue staining. In in vivo susceptibility-weighted imaging, hypointense pixels were observed in the region between the SN and red nucleus (RN) in patients with PSP, but not in healthy controls and patients with PD. R2* and QSM values of such region were significantly higher in patients with PSP compared to those in healthy controls and patients with PD as well (vs. healthy control: p = 0.008; vs. PD: p = 0.008). Thus, excessive iron accumulation along the myelinated fibers at the anterior SN and oculomotor nerve fascicles may be a pathological characteristic and crucial MR biomarker in a brain with PSP.

scholarly journals Supervised Machine Learning Methods and Hyperspectral Imaging Techniques Jointly Applied for Brain Cancer Classification

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3827
Author(s):  
Gemma Urbanos ◽  
Alberto Martín ◽  
Guillermo Vázquez ◽  
Marta Villanueva ◽  
Manuel Villa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Blood Vessel ◽  
Hyperspectral Imaging ◽  
Imaging Techniques ◽  
Venous Blood ◽  
Healthy Tissue ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Arterial Blood

Hyperspectral imaging techniques (HSI) do not require contact with patients and are non-ionizing as well as non-invasive. As a consequence, they have been extensively applied in the medical field. HSI is being combined with machine learning (ML) processes to obtain models to assist in diagnosis. In particular, the combination of these techniques has proven to be a reliable aid in the differentiation of healthy and tumor tissue during brain tumor surgery. ML algorithms such as support vector machine (SVM), random forest (RF) and convolutional neural networks (CNN) are used to make predictions and provide in-vivo visualizations that may assist neurosurgeons in being more precise, hence reducing damages to healthy tissue. In this work, thirteen in-vivo hyperspectral images from twelve different patients with high-grade gliomas (grade III and IV) have been selected to train SVM, RF and CNN classifiers. Five different classes have been defined during the experiments: healthy tissue, tumor, venous blood vessel, arterial blood vessel and dura mater. Overall accuracy (OACC) results vary from 60% to 95% depending on the training conditions. Finally, as far as the contribution of each band to the OACC is concerned, the results obtained in this work are 3.81 times greater than those reported in the literature.

scholarly journals Prediction of Fuel Poverty Potential Risk Index Using Six Regression Algorithms: A Case-Study of Chilean Social Dwellings

2021 ◽  
Vol 13 (5) ◽  
pp. 2426
Author(s):  
David Bienvenido-Huertas ◽  
Jesús A. Pulido-Arcas ◽  
Carlos Rubio-Bellido ◽  
Alexis Pérez-Fargallo
Keyword(s):  
Low Income ◽  
Potential Risk ◽  
Energy Use ◽  
Risk Index ◽  
Computing Time ◽  
Simulated Data ◽  
Real Data ◽  
Support Vector ◽  
Energy Poverty ◽  
Regression Algorithms

In recent times, studies about the accuracy of algorithms to predict different aspects of energy use in the building sector have flourished, being energy poverty one of the issues that has received considerable critical attention. Previous studies in this field have characterized it using different indicators, but they have failed to develop instruments to predict the risk of low-income households falling into energy poverty. This research explores the way in which six regression algorithms can accurately forecast the risk of energy poverty by means of the fuel poverty potential risk index. Using data from the national survey of socioeconomic conditions of Chilean households and generating data for different typologies of social dwellings (e.g., form ratio or roof surface area), this study simulated 38,880 cases and compared the accuracy of six algorithms. Multilayer perceptron, M5P and support vector regression delivered the best accuracy, with correlation coefficients over 99.5%. In terms of computing time, M5P outperforms the rest. Although these results suggest that energy poverty can be accurately predicted using simulated data, it remains necessary to test the algorithms against real data. These results can be useful in devising policies to tackle energy poverty in advance.

New Multi-View Classification Method with Uncertain Data

2021 ◽  
Vol 16 (1) ◽  
pp. 1-23
Author(s):  
Bo Liu ◽  
Haowen Zhong ◽  
Yanshan Xiao
Keyword(s):  
Learning Strategy ◽  
State Of The Art ◽  
Uncertain Data ◽  
Real Life ◽  
Support Vector ◽  
Classification Methods ◽  
Complementary Information ◽  
Novel Approach ◽  
Svm Model ◽  
Iterative Framework

Multi-view classification aims at designing a multi-view learning strategy to train a classifier from multi-view data, which are easily collected in practice. Most of the existing works focus on multi-view classification by assuming the multi-view data are collected with precise information. However, we always collect the uncertain multi-view data due to the collection process is corrupted with noise in real-life application. In this case, this article proposes a novel approach, called uncertain multi-view learning with support vector machine (UMV-SVM) to cope with the problem of multi-view learning with uncertain data. The method first enforces the agreement among all the views to seek complementary information of multi-view data and takes the uncertainty of the multi-view data into consideration by modeling reachability area of the noise. Then it proposes an iterative framework to solve the proposed UMV-SVM model such that we can obtain the multi-view classifier for prediction. Extensive experiments on real-life datasets have shown that the proposed UMV-SVM can achieve a better performance for uncertain multi-view classification in comparison to the state-of-the-art multi-view classification methods.

scholarly journals Application of Artificial Intelligence (AI) for Sustainable Highway and Road System

Symmetry ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 60
Author(s):  
Md Arifuzzaman ◽  
Muhammad Aniq Gul ◽  
Kaffayatullah Khan ◽  
S. M. Zakir Hossain
Keyword(s):  
Experimental Data ◽  
High Performance ◽  
Adhesion Force ◽  
Model Development ◽  
Real Life ◽  
Bayesian Optimization ◽  
Support Vector ◽  
Adhesive Properties ◽  
Bayesian Optimization Algorithm ◽  
The Mean

There are several environmental factors such as temperature differential, moisture, oxidation, etc. that affect the extended life of the modified asphalt influencing its desired adhesive properties. Knowledge of the properties of asphalt adhesives can help to provide a more resilient and durable asphalt surface. In this study, a hybrid of Bayesian optimization algorithm and support vector regression approach is recommended to predict the adhesion force of asphalt. The effects of three important variables viz., conditions (fresh, wet and aged), binder types (base, 4% SB, 5% SB, 4% SBS and 5% SBS), and Carbon Nano Tube doses (0.5%, 1.0% and 1.5%) on adhesive force are taken into consideration. Real-life experimental data (405 specimens) are considered for model development. Using atomic force microscopy, the adhesive strength of nanoscales of test specimens is determined according to functional groups on the asphalt. It is found that the model predictions overlap with the experimental data with a high R2 of 90.5% and relative deviation are scattered around zero line. Besides, the mean, median and standard deviations of experimental and the predicted values are very close. In addition, the mean absolute Error, root mean square error and fractional bias values were found to be low, indicating the high performance of the developed model.

scholarly journals The Course of AαVal541 as a Proteinase 3 Specific Neo-Epitope after Alpha-1-Antitrypsin Augmentation in Severe Deficient Patients

2021 ◽  
Vol 22 (15) ◽  
pp. 8031
Author(s):  
Iris G. M. Schouten ◽  
Richard A. Mumford ◽  
Dirk Jan A. R. Moes ◽  
Pieter S. Hiemstra ◽  
Jan Stolk
Keyword(s):  
Plasma Level ◽  
Serine Proteases ◽  
Population Pharmacokinetic ◽  
Proteinase 3 ◽  
Healthy Controls ◽  
Population Pharmacokinetic Modeling ◽  
Antitrypsin Deficiency ◽  
Alpha 1 Antitrypsin Deficiency ◽  
Alpha 1 Antitrypsin

In alpha-1-antitrypsin deficiency (AATD), neutrophil serine proteases such as elastase and proteinase 3 (PR3) are insufficiently inhibited. A previous study in AATD patients showed a higher plasma level of the specific PR3-generated fibrinogen-derived peptide AαVal541, compared with healthy controls. Here, we analyzed the course of AαVal541 plasma levels during 4 weeks after a single iv dose of 240 mg/kg AAT in ten patients with genotype Z/Rare or Rare/Rare. To this end, we developed an immunoassay to measure AαVal541 in plasma and applied population pharmacokinetic modeling for AAT. The median AαVal541 plasma level before treatment was 140.2 nM (IQR 51.5–234.8 nM)). In five patients who received AAT for the first time, AαVal541 levels decreased to 20.6 nM (IQR 5.8–88.9 nM), and in five patients who already had received multiple infusions before, it decreased to 26.2 nM (IQR 22.31–35.0 nM). In 9 of 10 patients, AαVal541 levels were reduced to the median level of healthy controls (21.4 nM; IQR 16.7–30.1 nM). At 7–14 days after treatment, AαVal541 levels started to increase again in all patients. Our results show that fibrinopeptide AαVal541 may serve as a biochemical footprint to assess the efficacy of in vivo inhibition of PR3 activity in patients receiving intravenous AAT augmentation therapy.

scholarly journals Miswiring of Frontostriatal Projections in Schizophrenia

2020 ◽  
Vol 46 (4) ◽  
pp. 990-998 ◽  
Author(s):  
James J Levitt ◽  
Paul G Nestor ◽  
Marek Kubicki ◽  
Amanda E Lyall ◽  
Fan Zhang ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Diffusion Magnetic Resonance Imaging ◽  
Right Hemisphere ◽  
Structural Connectivity ◽  
Chronic Schizophrenia ◽  
Input Pattern ◽  
Healthy Controls ◽  
Resonance Imaging ◽  
Circuit Integration ◽  
Projection Zone

Abstract We investigated brain wiring in chronic schizophrenia and healthy controls in frontostriatal circuits using diffusion magnetic resonance imaging tractography in a novel way. We extracted diffusion streamlines in 27 chronic schizophrenia and 26 healthy controls connecting 4 frontal subregions to the striatum. We labeled the projection zone striatal surface voxels into 2 subtypes: dominant-input from a single cortical subregion, and, functionally integrative, with mixed-input from diverse cortical subregions. We showed: 1) a group difference for total striatal surface voxel number (P = .045) driven by fewer mixed-input voxels in the left (P  = .007), but not right, hemisphere; 2) a group by hemisphere interaction for the ratio quotient between voxel subtypes (P  = .04) with a left (P  = .006), but not right, hemisphere increase in schizophrenia, also reflecting fewer mixed-input voxels; and 3) fewer mixed-input voxel counts in schizophrenia (P  = .045) driven by differences in left hemisphere limbic (P  = .007) and associative (P  = .01), but not sensorimotor, striatum. These results demonstrate a less integrative pattern of frontostriatal structural connectivity in chronic schizophrenia. A diminished integrative pattern yields a less complex input pattern to the striatum from the cortex with less circuit integration at the level of the striatum. Further, as brain wiring occurs during early development, aberrant brain wiring could serve as a developmental biomarker for schizophrenia.

Sign in / Sign up

Export Citation Format

Share Document