scholarly journals Microstructure Diffusion Scalar Measures from Reduced MRI Acquisitions

2019 ◽  
Author(s):  
Santiago Aja-Fernández ◽  
Rodrigo de Luis-García ◽  
Maryam Afzali ◽  
Malwina Molendowska ◽  
Tomasz Pieciak ◽  
...  
Keyword(s):  
Diffusion Tensor ◽  
State Of The Art ◽  
B Value ◽  
Computationally Efficient ◽  
Huge Amount ◽  
Average Diffusion ◽  
Efficient Alternative ◽  
Alternative Techniques ◽  
Dense Sampling ◽  
Diffusion Properties

AbstractIn diffusion MRI, the Ensemble Average diffusion Propagator (EAP) provides relevant microstructural information and meaningful descriptive maps of the white matter previously obscured by traditional techniques like the Diffusion Tensor. The direct estimation of the EAP, however, requires a dense sampling of the Cartesian q-space. Due to the huge amount of samples needed for an accurate reconstruction, more efficient alternative techniques have been proposed in the last decade. Even so, all of them imply acquiring a large number of diffusion gradients with different b-values. In order to use the EAP in practical studies, scalar measures must be directly derived, being the most common the return-to-origin probability (RTOP) and the return-to-plane and return-to-axis probabilities (RTPP, RTAP).In this work, we propose the so-called “Apparent Measures Using Reduced Acquisitions” (AMURA) to drastically reduce the number of samples needed for the estimation of diffusion properties. AMURA avoids the calculation of the whole EAP by assuming the diffusion anisotropy is roughly independent from the radial direction. With such an assumption, and as opposed to common multi-shell procedures based on iterative optimization, we achieve closed-form expressions for the measures using information from one single shell. This way, the new methodology remains compatible with standard acquisition protocols commonly used for HARDI (based on just one b-value). We report extensive results showing the potential of AMURA to reveal microstructural properties of the tissues compared to state of the art EAP estimators, and is well above that of Diffusion Tensor techniques. At the same time, the closed forms provided for RTOP, RTPP, and RTAP-like magnitudes make AMURA both computationally efficient and robust.

scholarly journals Apparent Propagator Anisotropy from reduced Diffusion MRI acquisitions

2019 ◽  
Author(s):  
Santiago Aja-Fernández ◽  
Antonio Tristán-Vega ◽  
Derek Jones
Keyword(s):  
Diffusion Mri ◽  
Estimation Procedure ◽  
B Value ◽  
Closed Form Expression ◽  
Computationally Efficient ◽  
Form Expression ◽  
Discrimination Power ◽  
Processing Times ◽  
Average Diffusion ◽  
Dense Sampling

AbstractThe Propagator Anisotropy (PA) is a measurement of the orientational variability inside a tissue estimated from diffusion MRI using the Ensemble Average diffusion Propagator (EAP). It is based on the quantification of the angular difference between the propagator in a specific voxel and its isotropic counterpart. The PA has shown the ability to reveal microstructural information of interest and meaningful descriptive maps inside the white matter. However, the use of PA is not generalized among the clinical community, due to the great amount of data needed for its calculation, together with the associated long processing times. In order to calculate the PA, the EAP must also be properly estimated. This task would require a dense sampling of the Cartesian q-space. Alternatively, more efficient techniques have been proposed in the last decade. Even so, all of them imply acquiring a large number of diffusion gradients with different b-values and long processing times.In this work, we propose an alternative implementation to drastically reduce the number of samples needed, as well as boosting the estimation procedure. We avoid the calculation of the whole EAP by assuming that the diffusion anisotropy is roughly independent from the radial direction. With such an assumption, we achieve a closed-form expression for a measure similar to the PA but using information from one single shell: the Apparent Propagator Anisotropy (APA). The new measure remains compatible with standard acquisition protocols commonly used for HARDI (based on just one b-value). The intention of the APA is not to exactly replicate the PA but inferring microstructural information with comparable discrimination power as the PA but using a reduced amount of data.We report extensive results showing that the proposed measures present a robust behavior in clinical studies and they are computationally efficient and robust when compared with PA and other anisotropy measures.

scholarly journals Parametric covariance dynamics for the nonlinear diffusive Burgers equation

2018 ◽  
Vol 25 (3) ◽  
pp. 481-495 ◽  
Author(s):  
Olivier Pannekoucke ◽  
Marc Bocquet ◽  
Richard Ménard
Keyword(s):  
Kalman Filter ◽  
Burgers Equation ◽  
Diffusion Tensor ◽  
Error Variance ◽  
Covariance Model ◽  
Computationally Efficient ◽  
Closure Model ◽  
Error Covariance ◽  
Efficient Alternative ◽  
Linear Covariance

Abstract. The parametric Kalman filter (PKF) is a computationally efficient alternative method to the ensemble Kalman filter. The PKF relies on an approximation of the error covariance matrix by a covariance model with a space–time evolving set of parameters. This study extends the PKF to nonlinear dynamics using the diffusive Burgers equation as an application, focusing on the forecast step of the assimilation cycle. The covariance model considered is based on the diffusion equation, with the diffusion tensor and the error variance as evolving parameters. An analytical derivation of the parameter dynamics highlights a closure issue. Therefore, a closure model is proposed based on the kurtosis of the local correlation functions. Numerical experiments compare the PKF forecast with the statistics obtained from a large ensemble of nonlinear forecasts. These experiments strengthen the closure model and demonstrate the ability of the PKF to reproduce the tangent linear covariance dynamics, at a low numerical cost.

scholarly journals Parametric covariance dynamics for the nonlinear diffusive Burgers' equation

2018 ◽  
Author(s):  
Olivier Pannekoucke ◽  
Marc Bocquet ◽  
Richard Ménard
Keyword(s):  
Kalman Filter ◽  
Burgers Equation ◽  
Diffusion Tensor ◽  
Error Variance ◽  
Covariance Model ◽  
Computationally Efficient ◽  
Closure Model ◽  
Error Covariance ◽  
Efficient Alternative ◽  
Linear Covariance

Abstract. The parametric Kalman filter (PKF) is a computationally efficient alternative method to the ensemble Kalman filter (EnKF). The PKF relies on an approximation of the error covariance matrix by a covariance model with space-time evolving set of parameters. This study extends the PKF to nonlinear dynamics using the diffusive Burgers' equation as an application, focusing on the forecast step of the assimilation cycle. The covariance model considered is based on the diffusion equation, with the diffusion tensor and the error variance as evolving parameter. An analytical derivation of the parameter dynamics highlights a closure issue. Therefore, a closure model is proposed based on the so-called kurtosis of the local correlation functions. Numerical experiments compare the PKF forecast with the statistics obtained from an large ensemble of nonlinear forecasts. These experiments strengthen the closure model and demonstrate the ability of the PKF to reproduce the tangent-linear covariance dynamics, at a low numerical cost.

Machete

2021 ◽  
Vol 28 (1) ◽  
pp. 1-46
Author(s):  
Eugene M. Taranta II ◽  
Corey R. Pittman ◽  
Mehran Maghoumi ◽  
Mykola Maslych ◽  
Yasmine M. Moolenaar ◽  
...  
Keyword(s):  
Video Game ◽  
Recognition Accuracy ◽  
Training Sample ◽  
Low Latency ◽  
Computationally Efficient ◽  
Extensive Evaluation ◽  
Segmentation Accuracy ◽  
Alternative Techniques ◽  
High Recognition Accuracy ◽  
Continuous Dynamic

We present Machete, a straightforward segmenter one can use to isolate custom gestures in continuous input. Machete uses traditional continuous dynamic programming with a novel dissimilarity measure to align incoming data with gesture class templates in real time. Advantages of Machete over alternative techniques is that our segmenter is computationally efficient, accurate, device-agnostic, and works with a single training sample. We demonstrate Machete’s effectiveness through an extensive evaluation using four new high-activity datasets that combine puppeteering, direct manipulation, and gestures. We find that Machete outperforms three alternative techniques in segmentation accuracy and latency, making Machete the most performant segmenter. We further show that when combined with a custom gesture recognizer, Machete is the only option that achieves both high recognition accuracy and low latency in a video game application.

scholarly journals Diffusion tensor imaging and fiber tractography of the median nerve at 1.5T: optimization of b value

2008 ◽  
Vol 38 (1) ◽  
pp. 51-59 ◽  
Author(s):  
Gustav Andreisek ◽  
Lawrence M. White ◽  
Andrea Kassner ◽  
George Tomlinson ◽  
Marshall S. Sussman
Keyword(s):  
Diffusion Tensor Imaging ◽  
Median Nerve ◽  
Diffusion Tensor ◽  
B Value ◽  
Fiber Tractography

scholarly journals A computationally efficient estimator for mutual information

2008 ◽  
Vol 464 (2093) ◽  
pp. 1203-1215 ◽  
Author(s):  
Dafydd Evans
Keyword(s):  
Data Analysis ◽  
Mutual Information ◽  
Time Complexity ◽  
Exploratory Data Analysis ◽  
Nearest Neighbour ◽  
Computationally Efficient ◽  
One Dimensional ◽  
Exploratory Data ◽  
Efficient Alternative ◽  
Computationally Expensive

Mutual information quantifies the determinism that exists in a relationship between random variables, and thus plays an important role in exploratory data analysis. We investigate a class of non-parametric estimators for mutual information, based on the nearest neighbour structure of observations in both the joint and marginal spaces. Unless both marginal spaces are one-dimensional, we demonstrate that a well-known estimator of this type can be computationally expensive under certain conditions, and propose a computationally efficient alternative that has a time complexity of order ( N  log  N ) as the number of observations N →∞.

scholarly journals Regularized Training and Tight Certification for Randomized Smoothed Classifier with Provable Robustness

2020 ◽  
Vol 34 (04) ◽  
pp. 3858-3865
Author(s):  
Huijie Feng ◽  
Chunpeng Wu ◽  
Guoyang Chen ◽  
Weifeng Zhang ◽  
Yang Ning
Keyword(s):  
Neural Network ◽  
High Probability ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Computationally Efficient ◽  
Base Classifier ◽  
Training Scheme ◽  
Adversarial Training ◽  
Gaussian Perturbation ◽  
Probabilistic Robustness

Recently smoothing deep neural network based classifiers via isotropic Gaussian perturbation is shown to be an effective and scalable way to provide state-of-the-art probabilistic robustness guarantee against ℓ2 norm bounded adversarial perturbations. However, how to train a good base classifier that is accurate and robust when smoothed has not been fully investigated. In this work, we derive a new regularized risk, in which the regularizer can adaptively encourage the accuracy and robustness of the smoothed counterpart when training the base classifier. It is computationally efficient and can be implemented in parallel with other empirical defense methods. We discuss how to implement it under both standard (non-adversarial) and adversarial training scheme. At the same time, we also design a new certification algorithm, which can leverage the regularization effect to provide tighter robustness lower bound that holds with high probability. Our extensive experimentation demonstrates the effectiveness of the proposed training and certification approaches on CIFAR-10 and ImageNet datasets.

An Approach to Improve Bayesian Inference in Assessment of Coast Evolution

2018 ◽  
pp. 163-174
Author(s):  
Victoria Shterkhun ◽  
Gonéri Le Cozannet ◽  
Manuel Garcin
Keyword(s):  
Bayesian Inference ◽  
State Of The Art ◽  
The State ◽  
Probabilistic Assessment ◽  
Bayesian Computation ◽  
Coastal Environments ◽  
Efficient Alternative

The chapter reports the state of the art in the modeling of coastal environments by the method of event bush. This method appears to be an efficient alternative to highly subjective conceptualizations used in the databases that provide data for probabilistic assessment of evolution of the coast. The event bushes themselves may be used for Bayesian computation, but there emerge complications that pose intriguing theoretical tasks. Still, their application requires deep conceptual rethinking of the field of knowledge including both the terminology and concepts traditionally accepted in it.

scholarly journals CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification

2020 ◽  
Vol 2020 ◽  
pp. 1-7 ◽  
Author(s):  
Aboubakar Nasser Samatin Njikam ◽  
Huan Zhao
Keyword(s):  
Text Classification ◽  
Building Block ◽  
Large Scale ◽  
State Of The Art ◽  
Building Blocks ◽  
Training Data ◽  
Superior Performance ◽  
Classification Problems ◽  
Computationally Efficient ◽  
Convolutional Network

This paper introduces an extremely lightweight (with just over around two hundred thousand parameters) and computationally efficient CNN architecture, named CharTeC-Net (Character-based Text Classification Network), for character-based text classification problems. This new architecture is composed of four building blocks for feature extraction. Each of these building blocks, except the last one, uses 1 × 1 pointwise convolutional layers to add more nonlinearity to the network and to increase the dimensions within each building block. In addition, shortcut connections are used in each building block to facilitate the flow of gradients over the network, but more importantly to ensure that the original signal present in the training data is shared across each building block. Experiments on eight standard large-scale text classification and sentiment analysis datasets demonstrate CharTeC-Net’s superior performance over baseline methods and yields competitive accuracy compared with state-of-the-art methods, although CharTeC-Net has only between 181,427 and 225,323 parameters and weighs less than 1 megabyte.

Deep Image Demosaicing for Submicron Image Sensors

2019 ◽  
Vol 63 (6) ◽  
pp. 60410-1-60410-12
Author(s):  
Irina Kim ◽  
Seongwook Song ◽  
Soonkeun Chang ◽  
Sukhwan Lim ◽  
Kai Guo
Keyword(s):  
Image Quality ◽  
Mobile Devices ◽  
State Of The Art ◽  
Image Sensor ◽  
Sensor Technology ◽  
Color Filter ◽  
Computationally Efficient ◽  
Linear Feature ◽  
Visual Artifacts ◽  
Very High

Abstract Latest trend in image sensor technology allowing submicron pixel size for high-end mobile devices comes at very high image resolutions and with irregularly sampled Quad Bayer color filter array (CFA). Sustaining image quality becomes a challenge for the image signal processor (ISP), namely for demosaicing. Inspired by the success of deep learning approach to standard Bayer demosaicing, we aim to investigate how artifacts-prone Quad Bayer array can benefit from it. We found that deeper networks are capable to improve image quality and reduce artifacts; however, deeper networks can be hardly deployed on mobile devices given very high image resolutions: 24MP, 36MP, 48MP. In this article, we propose an efficient end-to-end solution to bridge this gap—a duplex pyramid network (DPN). Deep hierarchical structure, residual learning, and linear feature map depth growth allow very large receptive field, yielding better details restoration and artifacts reduction, while staying computationally efficient. Experiments show that the proposed network outperforms state of the art for standard and Quad Bayer demosaicing. For the challenging Quad Bayer CFA, the proposed method reduces visual artifacts better than state-of-the-art deep networks including artifacts existing in conventional commercial solutions. While superior in image quality, it is 2‐25 times faster than state-of-the-art deep neural networks and therefore feasible for deployment on mobile devices, paving the way for a new era of on-device deep ISPs.

Sign in / Sign up

Export Citation Format

Share Document