A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is
Tractography is a family of algorithms that use diffusion-weighted magnetic resonance imaging data to reconstruct the white matter pathways of the brain. Although it has been proven to be particularly effective for studying non-invasively the neuronal architecture of the brain, recent studies have highlighted that the large incidence of false positive connections retrieved by these techniques can significantly bias any connectivity analysis. Some solutions have been proposed to overcome thisdoi:10.1101/608349 fatcat:mpzcvlw3svfz5hlzasdbytazyu
more »... ue and the ones relying on convex optimization framework showed a significant improvement. Here we propose an evolution of the Convex Optimization Modeling for Microstructure Informed Tractography (COMMIT) framework, that combines basic prior knowledge about brain anatomy with group-sparsity regularization into the optimization problem. We show that the new formulation dramatically reduces the incidence of false positives in synthetic data.
GOAL This study goal is to determine and compare the echocardiographic cardiac Echocardiography Differences Between Athlete's Heart Hearth and Hypertrophic Cardiomyopathy Amir Kreso 1 , Fahir Barakovic ... 2 , Senad Medjedovic 3 , Amila Halilbasic 1 , Muhamed Klepic 1 1 Echocardiography Differences Between Athlete's Heart Hearth and Hypertrophic Cardiomyopathy parameters of the long term athletes and ...doi:10.5455/aim.2015.23.276-279 pmid:26635434 pmcid:PMC4639332 fatcat:fbimvhtpkbbybkgnj57s2sihwa
"Athlete's heart syndrome" is a condition characterized by structural, electrophysiologic and functional adaptation of the myocardium to physical activity (training), depending on the activity intensity, duration and type. In athletes left ventricular hypertrophy often resembles comorbid conditions (hypertension or hypertrophic cardiomyopathy) so the differential diagnosis of the disease is very important and crucial, especially in people who are in active training. In fact, if an athlete hasdoi:10.5455/medarh.2015.69.319-322 pmid:26622085 pmcid:PMC4639330 fatcat:65zdbj3a7vbv5jas6kc3igsc3y
more »... nding which indicate thickening of the left ventricle walls, should be distinguished hypertrophy which occurred as a result of many years of training from accidental existence of hypertension or hypertrophic cardiomyopathy in the same person. Therefore, it is important to make a diagnostic difference between healthy and sick heart. Material and methods: The study involved male persons aged 20-45 which have increased muscle mass of the left ventricle due to different etiology. Definite sample included 80 respondents divided into two groups. All respondent underwent interview, clinical examination, ECG and echocardiography. Results: Average systolic blood pressure (SBP) for the athletes were 115.8±7.2 mmHg, and in patients, with hypertension 154.4±3.5 mmHg, average values of diastolic blood pressure (DBP) for the athletes were 74.2±8.1 mmHg in patients, hypertensive 96.2 ± 3.9 mmHg. Values of SBP and DBP were significantly lower in the group of athletes compared to patients with hypertension (p=0.001). The value of the SFO/min was significantly lower in the group of athletes compared to patients with hypertension (p <0.001). There was a statistically significant difference in the sum of SV2 RV5 and between groups of athletes and groups of patients with hypertension (p<0.05). There was no significant difference in the echocardiography parameters between two groups. There was a statistically significant difference in the sum of SV 2 and RV 5 between groups of athletes and groups of patients with hypertension (p<0.05). Conclusion: ECG parameters, PQ, QRS, QT did not prove to be useful in the differentiation between the groups because no statistically significant differences in their values were found. Echocardiography is a reliable diagnostic tool in differentiating physiologic hypertrophy of athletes compared to hypertrophy in patients with hypertension.
Mathematics and Visualization
AbstractThe anisotropic microstructure of white matter is reflected in various MRI contrasts. Transverse relaxation rates can be probed as a function of fibre-orientation with respect to the main magnetic field, while diffusion properties are probed as a function of fibre-orientation with respect to an encoding gradient. While the latter is easy to obtain by varying the orientation of the gradient, as the magnetic field is fixed, obtaining the former requires re-orienting the head. In this workdoi:10.1007/978-3-030-56215-1_12 fatcat:rv7qx5ufdvgjffitfczbsejwgu
more »... we deployed a tiltable RF-coil to study $$T_2$$ T 2 - and diffusional anisotropy of the brain white matter simultaneously in diffusion-$$T_2$$ T 2 correlation experiments.
Recovering the T2 distribution from multi-echo T2 magnetic resonance (MR) signals is challenging but has high potential as it provides biomarkers characterizing the tissue micro-structure, such as the myelin water fraction (MWF). In this work, we propose to combine machine learning and aspects of parametric (fitting from the MRI signal using biophysical models) and non-parametric (model-free fitting of the T2 distribution from the signal) approaches to T2 relaxometry in brain tissue by using aarXiv:2007.10225v1 fatcat:n3qimwaw4rc67edcdy4soi2m4q
more »... ulti-layer perceptron (MLP) for the distribution reconstruction. For training our network, we construct an extensive synthetic dataset derived from biophysical models in order to constrain the outputs with a priori knowledge of in vivo distributions. The proposed approach, called Model-Informed Machine Learning (MIML), takes as input the MR signal and directly outputs the associated T2 distribution. We evaluate MIML in comparison to non-parametric and parametric approaches on synthetic data, an ex vivo scan, and high-resolution scans of healthy subjects and a subject with Multiple Sclerosis. In synthetic data, MIML provides more accurate and noise-robust distributions. In real data, MWF maps derived from MIML exhibit the greatest conformity to anatomical scans, have the highest correlation to a histological map of myelin volume, and the best unambiguous lesion visualization and localization, with superior contrast between lesions and normal appearing tissue. In whole-brain analysis, MIML is 22 to 4980 times faster than non-parametric and parametric methods, respectively.
Adapted from Barakovic, 2021. Fig. 4 . ... ., 2017; Barakovic, 2021; Veraart et al., 2020) . ...doi:10.1016/j.pneurobio.2021.102186 pmid:34780864 pmcid:PMC8752969 fatcat:gbvogf5k3zfzvg3yzb6dof7xwq
Recovering the T2 distribution from multi-echo T2 magnetic resonance (MR) signals is challenging but has high potential as it provides biomarkers characterizing the tissue micro-structure, such as the myelin water fraction (MWF). In this work, we propose to combine machine learning and aspects of parametric (fitting from the MRI signal using biophysical models) and non-parametric (model-free fitting of the T2 distribution from the signal) approaches to T2 relaxometry in brain tissue by using adoi:10.1016/j.media.2020.101940 pmid:33422828 fatcat:vw6oqlgyzbclha333ths7af55e
more »... ulti-layer perceptron (MLP) for the distribution reconstruction. For training our network, we construct an extensive synthetic dataset derived from biophysical models in order to constrain the outputs with a priori knowledge of in vivo distributions. The proposed approach, called Model-Informed Machine Learning (MIML), takes as input the MR signal and directly outputs the associated T2 distribution. We evaluate MIML in comparison to a Gaussian Mixture Fitting (parametric) and Regularized Non-Negative Least Squares algorithms (non-parametric) on synthetic data, an ex vivo scan, and high-resolution scans of healthy subjects and a subject with Multiple Sclerosis. In synthetic data, MIML provides more accurate and noise-robust distributions. In real data, MWF maps derived from MIML exhibit the greatest conformity to anatomical scans, have the highest correlation to a histological map of myelin volume, and the best unambiguous lesion visualization and localization, with superior contrast between lesions and normal appearing tissue. In whole-brain analysis, MIML is 22 to 4980 times faster than the non-parametric and parametric methods, respectively.
Diffusion magnetic resonance imaging is a noninvasive imaging modality that has been extensively used in the literature to study the neuronal architecture of the brain in a wide range of neurological conditions using tractography. However, recent studies highlighted that the anatomical accuracy of the reconstructions is inherently limited and challenged its appropriateness. Several solutions have been proposed to tackle this issue, but none of them proved effective to overcome this fundamentaldoi:10.1126/sciadv.aba8245 pmid:32789176 pmcid:PMC7399649 fatcat:z5w5bim5d5cofepkbmyxjc4jrm
more »... imitation. In this work, we present a novel processing framework to inject into the reconstruction problem basic prior knowledge about brain anatomy and its organization and evaluate its effectiveness using both simulated and real human brain data. Our results indicate that our proposed method dramatically increases the accuracy of the estimated brain networks and, thus, represents a major step forward for the study of connectivity.
MATERIALS AND METHODS Bundle-Specific Estimation To enable estimation of the axon diameter index of individual bundles, similarly to the recently proposed COMMIT-T 2 method (Barakovic et al., 2021) ... Copyright © 2021 Barakovic, Girard, Schiavi, Romascano, Descoteaux, Granziera, Jones, Innocenti, Thiran and Daducci. ...doi:10.3389/fnins.2021.646034 fatcat:h4fppfpdyzb6nhy25e2vbkp7ki
The limited availability of large image datasets, mainly due to data privacy and differences in acquisition protocols or hardware, is a significant issue in the development of accurate and generalizable machine learning methods in medicine. This is especially the case for Magnetic Resonance (MR) images, where different MR scanners introduce a bias that limits the performance of a machine learning model. We present a novel method that learns to ignore the scanner-related features present in MRarXiv:2110.06803v3 fatcat:2d7z4egi7zdvdajhv5m576eqly
more »... ages, by introducing specific additional constraints on the latent space. We focus on a real-world classification scenario, where only a small dataset provides images of all classes. Our method Learn to Ignore (L2I) outperforms state-of-the-art domain adaptation methods on a multi-site MR dataset for a classification task between multiple sclerosis patients and healthy controls.
., 2020b ) and in a COMMIT-style framework ( Barakovic et al., 2018 ) . ... Credit authorship contribution statementMuhamed Barakovic: Conceptualization, Methodology, Software, Validation, Investigation, Data curation, Writing -original draft, Writing -review & editing, Visualization ...doi:10.1016/j.neuroimage.2020.117617 pmid:33301934 fatcat:aeglpy5brne6bep2h672l6uo2i
Distributional shift, or the mismatch between training and deployment data, is a significant obstacle to the usage of machine learning in high-stakes industrial applications, such as autonomous driving and medicine. This creates a need to be able to assess how robustly ML models generalize as well as the quality of their uncertainty estimates. Standard ML baseline datasets do not allow these properties to be assessed, as the training, validation and test data are often identically distributed.arXiv:2206.15407v2 fatcat:rb2vx3zvnng3ppp2xbecvvjur4
more »... ecently, a range of dedicated benchmarks have appeared, featuring both distributionally matched and shifted data. Among these benchmarks, the Shifts dataset stands out in terms of the diversity of tasks as well as the data modalities it features. While most of the benchmarks are heavily dominated by 2D image classification tasks, Shifts contains tabular weather forecasting, machine translation, and vehicle motion prediction tasks. This enables the robustness properties of models to be assessed on a diverse set of industrial-scale tasks and either universal or directly applicable task-specific conclusions to be reached. In this paper, we extend the Shifts Dataset with two datasets sourced from industrial, high-risk applications of high societal importance. Specifically, we consider the tasks of segmentation of white matter Multiple Sclerosis lesions in 3D magnetic resonance brain images and the estimation of power consumption in marine cargo vessels. Both tasks feature ubiquitous distributional shifts and a strict safety requirement due to the high cost of errors. These new datasets will allow researchers to further explore robust generalization and uncertainty estimation in new situations. In this work, we provide a description of the dataset and baseline results for both tasks.
The presence of cortical lesions in multiple sclerosis patients has emerged as an important biomarker of the disease. They appear in the earliest stages of the illness and have been shown to correlate with the severity of clinical symptoms. However, cortical lesions are hardly visible in conventional magnetic resonance imaging (MRI) at 3T, and thus their automated detection has been so far little explored. In this study, we propose a fully-convolutional deep learning approach, based on the 3Ddoi:10.1016/j.nicl.2020.102335 pmid:32663798 pmcid:PMC7358270 fatcat:hnlu2nphgzdc7ezfbowg7iy3x4
more »... Net, for the automated segmentation of cortical and white matter lesions at 3T. For this purpose, we consider a clinically plausible MRI setting consisting of two MRI contrasts only: one conventional T2-weighted sequence (FLAIR), and one specialized T1-weighted sequence (MP2RAGE). We include 90 patients from two different centers with a total of 728 and 3856 gray and white matter lesions, respectively. We show that two reference methods developed for white matter lesion segmentation are inadequate to detect small cortical lesions, whereas our proposed framework is able to achieve a detection rate of 76% for both cortical and white matter lesions with a false positive rate of 29% in comparison to manual segmentation. Further results suggest that our framework generalizes well for both types of lesion in subjects acquired in two hospitals with different scanners.
Investigative studies of white matter (WM) brain structures using diffusion MRI (dMRI) tractography frequently require manual WM bundle segmentation, often called "virtual dissection". Human errors and personal decisions make these manual segmentations hard to reproduce, which have not yet been quantified by the dMRI community. The contribution of this study is to provide the first large-scale, international, multi-center variability assessment of the "virtual dissection of the pyramidal tractdoi:10.1101/623892 fatcat:cnxao7zykzabvnu246mxetmrqq
more »... PyT). Eleven (11) experts and thirteen (13) non-experts in neuroanatomy and "virtual dissection" were asked to perform 30 PyT segmentation and their results were compared using various voxel-wise and streamline-wise measures. Overall the voxel representation is always more reproducible than streamlines ($\approx$70\% and $ \approx$35\% overlap respectively) and distances between segmentations are also lower for voxel-wise than streamline-wise measures ($\approx$3mm~and~$\approx$6mm respectively). This needs to be seriously considered before using tract-based measures (e.g. bundle volume versus streamline count) for an analysis. We show and argue that future bundle segmentation protocols need to be designed to be more robust to human subjectivity. Coordinated efforts by the diffusion MRI tractography community are needed to quantify and account for reproducibility of WM bundle extraction techniques in this era of open and collaborative science.
Copyright © 2021 Kesenheimer, Wendebourg, Weigel, Weidensteiner, Haas, Richter, Sander, Horvath, Barakovic, Cattin, Granziera, Bieri and Schlaeger. ...doi:10.3389/fneur.2021.637198 pmid:33841307 pmcid:PMC8027254 fatcat:supkqce47zanfprl34ud62l5d4
« Previous Showing results 1 — 15 out of 37 results