scholarly journals The impact of image dynamic range on texture classification of brain white matter

2008 ◽  
Vol 8 (1) ◽  
Author(s):  
Doaa Mahmoud-Ghoneim ◽  
Mariam K Alkaabi ◽  
Jacques D de Certaines ◽  
Frank-M Goettsche
Keyword(s):  
White Matter ◽  
Dynamic Range ◽  
Texture Classification ◽  
Brain White Matter ◽  
The Impact

scholarly journals An Audio Distortion Dynamic Range Index for Evaluating the Performance of Audio Systems

2020 ◽  
Vol 10 (22) ◽  
pp. 8022
Author(s):  
Desheng Wang ◽  
Yangjie Wei ◽  
Yi Wang ◽  
Jing Wang
Keyword(s):  
Dynamic Range ◽  
Signal To Noise Ratio ◽  
Measurement Methods ◽  
Performance Difference ◽  
Critical Factors ◽  
Signal To Noise ◽  
Measurement Condition ◽  
Actual Application ◽  
The Impact

The dynamic range (DR) index lacking of an official definition leads to ambiguities in performance evaluation. The existing measurement methods of DR do not always match with the various actual application conditions, and some detailed distortion behavior of the device under test (DUT) is not extracted. In this paper, a new index for evaluating the DR performance of audio systems is proposed and validated, herein referred to as the audio distortion dynamic range (ADDR). It reduces the uncertainty of measurement conditions by an explicit definition and unifies the signal-to-noise ratio (SNR) and the signal-to-noise-and-distortion ratio (SINAD) indexes if under the same measurement condition. Moreover, to comprehensively reflect the impact of harmonic, spurious, and noise components on the DUT, the definitions of the traditional indexes based on classification of distorted components are replaced by the variable thresholds in the ADDR definition. Subsequently, the detailed steps of ADDR and the critical factors influencing its accuracy, are analyzed and then the optimized measurement conditions are given. Experiments based on simulated DUTs show the ADDR index can distinguish performance difference that the traditional indexes cannot distinguish, which proves it is an effective supplementary to the existing indexes in some real applications.

scholarly journals Etiology-based classification of brain white matter hyperintensity on magnetic resonance imaging

2015 ◽  
Vol 2 (1) ◽  
pp. 014002 ◽  
Author(s):  
Mariana Leite ◽  
Letícia Rittner ◽  
Simone Appenzeller ◽  
Heloísa Helena Ruocco ◽  
Roberto Lotufo
Keyword(s):  
Magnetic Resonance Imaging ◽  
White Matter ◽  
Magnetic Resonance ◽  
White Matter Hyperintensity ◽  
Resonance Imaging ◽  
Brain White Matter

scholarly journals Fiber Clustering Acceleration With a Modified Kmeans++ Algorithm Using Data Parallelism

2021 ◽  
Vol 15 ◽  
Author(s):  
Isaac Goicovich ◽  
Paulo Olivares ◽  
Claudio Román ◽  
Andrea Vázquez ◽  
Cyril Poupon ◽  
...  
Keyword(s):  
White Matter ◽  
Brain Research ◽  
Data Parallelism ◽  
Processing Unit ◽  
Brain White Matter ◽  
Fiber Clustering ◽  
New Variant ◽  
Clustering Quality ◽  
Kmeans Algorithm ◽  
The Impact

Fiber clustering methods are typically used in brain research to study the organization of white matter bundles from large diffusion MRI tractography datasets. These methods enable exploratory bundle inspection using visualization and other methods that require identifying brain white matter structures in individuals or a population. Some applications, such as real-time visualization and inter-subject clustering, need fast and high-quality intra-subject clustering algorithms. This work proposes a parallel algorithm using a General Purpose Graphics Processing Unit (GPGPU) for fiber clustering based on the FFClust algorithm. The proposed GPGPU implementation exploits data parallelism using both multicore and GPU fine-grained parallelism present in commodity architectures, including current laptops and desktop computers. Our approach implements all FFClust steps in parallel, improving execution times in all of them. In addition, our parallel approach includes a parallel Kmeans++ algorithm implementation and defines a new variant of Kmeans++ to reduce the impact of choosing outliers as initial centroids. The results show that our approach provides clustering quality results very similar to FFClust, and it requires an execution time of 3.5 s for processing about a million fibers, achieving a speedup of 11.5 times compared to FFClust.

scholarly journals Auto-encoded Latent Representations of White Matter Streamlines for Quantitative Distance Analysis

2021 ◽  
Author(s):  
Shenjun Zhong ◽  
Zhaolin Chen ◽  
Gary Egan
Keyword(s):  
White Matter ◽  
Supervised Classification ◽  
Unsupervised Clustering ◽  
Distance Analysis ◽  
Brain White Matter ◽  
Latent Space ◽  
Generic Data ◽  
Connectivity Patterns ◽  
Latent Representations

Parcellation of whole brain tractogram is a critical step to study brain white matter structures and connectivity patterns. The existing methods based on supervised classification of streamlines into predefined streamline bundle types are not designed to explore sub-bundle structures, and methods with manually designed features are expensive to compute streamline-wise similarities. To resolve these issues, we proposed a novel atlas-free method that learnt a latent space using a deep recurrent autoencoder which efficiently embedded any lengths of streamlines to fixed-size feature vectors, namely, streamline embeddings, and enabled tractogram parcellation via unsupervised clustering in the latent space. The method is evaluated on the ISMRM 2015 tractography challenge dataset, and shows the ability to discriminate major bundles with unsupervised clustering and query streamline based on similarity. The learnt latent representations of streamlines and bundles also open the possibility of quantitatively studying any granularities of sub-bundle structures with generic data mining techniques.

Classification of first-episode schizophrenia spectrum disorders and controls from whole brain white matter fractional anisotropy using machine learning

2017 ◽  
Vol 41 (S1) ◽  
pp. S191-S191 ◽  
Author(s):  
P. Mikolas ◽  
J. Hlinka ◽  
Z. Pitra ◽  
A. Skoch ◽  
T. Frodl ◽  
...  
Keyword(s):  
Machine Learning ◽  
White Matter ◽  
Fractional Anisotropy ◽  
Classification Performance ◽  
Classification Model ◽  
First Episode ◽  
Support Vector ◽  
Brain White Matter ◽  
First Episode Schizophrenia

BackgroundSchizophrenia is a chronic disorder with an early onset and high disease burden in terms of life disability. Its early recognition may delay the resulting brain structural/functional alterations and improve treatment outcomes. Unlike conventional group-statistics, machine-learning techniques made it possible to classify patients and controls based on the disease patterns on an individual level. Diagnostic classification in first-episode schizophrenia to date was mostly performed on sMRI or fMRI data. DTI modalities have not gained comparable attention.MethodsWe performed the classification of 77 FES patients and 77 healthy controls matched by age and sex from fractional anisotropy data from using linear support-vector machine (SVM). We further analyzed the effect of medication and symptoms on the classification performance using standard statistical measures (t-test, linear regression) and machine learning (Kernel–Ridge regression).ResultsThe SVM distinguished between patients and controls with significant accuracy of 62.34% (P = 0.005). There was no association between the classification performance and medication nor symptoms. Group level statistical analysis yielded brain-wide significant differences in FA.ConclusionThe SVM in combination with brain white-matter fractional anisotropy might help differentiate FES from HC. The performance of our classification model was not associated with symptoms or medications and therefore reflects trait markers in the early course of the disease.Disclosure of interestThe authors have not supplied their declaration of competing interest.

scholarly journals Comparative Evaluation of Hand-Crafted Image Descriptors vs. Off-the-Shelf CNN-Based Features for Colour Texture Classification under Ideal and Realistic Conditions

2019 ◽  
Vol 9 (4) ◽  
pp. 738 ◽  
Author(s):  
Raquel Bello-Cerezo ◽  
Francesco Bianconi ◽  
Francesco Di Maria ◽  
Paolo Napoletano ◽  
Fabrizio Smeraldi
Keyword(s):  
Comparative Evaluation ◽  
Texture Classification ◽  
New Paradigm ◽  
Experimental Conditions ◽  
Fine Grained ◽  
Image Descriptors ◽  
Different Types ◽  
The Impact ◽  
Imaging Conditions

Convolutional Neural Networks (CNN) have brought spectacular improvements in several fields of machine vision including object, scene and face recognition. Nonetheless, the impact of this new paradigm on the classification of fine-grained images—such as colour textures—is still controversial. In this work, we evaluate the effectiveness of traditional, hand-crafted descriptors against off-the-shelf CNN-based features for the classification of different types of colour textures under a range of imaging conditions. The study covers 68 image descriptors (35 hand-crafted and 33 CNN-based) and 46 compilations of 23 colour texture datasets divided into 10 experimental conditions. On average, the results indicate a marked superiority of deep networks, particularly with non-stationary textures and in the presence of multiple changes in the acquisition conditions. By contrast, hand-crafted descriptors were better at discriminating stationary textures under steady imaging conditions and proved more robust than CNN-based features to image rotation.

scholarly journals The Influence of Radio-Frequency Transmit Field Inhomogeneities on the Accuracy of G-ratio Weighted Imaging

2021 ◽  
Vol 15 ◽  
Author(s):  
Tim M. Emmenegger ◽  
Gergely David ◽  
Mohammad Ashtarayeh ◽  
Francisco J. Fritz ◽  
Isabel Ellerbrock ◽  
...  
Keyword(s):  
White Matter ◽  
Radio Frequency ◽  
Dynamic Range ◽  
Volume Fraction ◽  
Statistical Parameter ◽  
Data Driven ◽  
Mapping Technique ◽  
Brain White Matter ◽  
B1 Field ◽  
G Ratio

G-ratio weighted imaging is a non-invasive, in-vivo MRI-based technique that aims at estimating an aggregated measure of relative myelination of axons across the entire brain white matter. The MR g-ratio and its constituents (axonal and myelin volume fraction) are more specific to the tissue microstructure than conventional MRI metrics targeting either the myelin or axonal compartment. To calculate the MR g-ratio, an MRI-based myelin-mapping technique is combined with an axon-sensitive MR technique (such as diffusion MRI). Correction for radio-frequency transmit (B1+) field inhomogeneities is crucial for myelin mapping techniques such as magnetization transfer saturation. Here we assessed the effect of B1+ correction on g-ratio weighted imaging. To this end, the B1+ field was measured and the B1+ corrected MR g-ratio was used as the reference in a Bland-Altman analysis. We found a substantial bias (≈-89%) and error (≈37%) relative to the dynamic range of g-ratio values in the white matter if the B1+ correction was not applied. Moreover, we tested the efficiency of a data-driven B1+ correction approach that was applied retrospectively without additional reference measurements. We found that it reduced the bias and error in the MR g-ratio by a factor of three. The data-driven correction is readily available in the open-source hMRI toolbox (www.hmri.info) which is embedded in the statistical parameter mapping (SPM) framework.

Sign in / Sign up

Export Citation Format

Share Document