The Experts below are selected from a list of 3822 Experts worldwide ranked by ideXlab platform
A. Clarke - One of the best experts on this subject based on the ideXlab platform.
-
In Vivo Assessment of Thoracic Vertebral Shape From MRI Data Using a Shape Model
Spine Deformity, 2019Co-Authors: Judith R. Meakin, S.j. Hopkins, A. ClarkeAbstract:Study Design Feasibility study on characterizing thoracic vertebral shape from magnetic resonance images using a shape model. Objectives Assess the reliability of characterizing thoracic vertebral shape from magnetic resonance images and estimate the normal Variation in vertebral shape using a shape model. Summary of Background Data The characterization of thoracic vertebra shape is important for understanding the initiation and progression of deformity and in developing surgical methods. Methods for characterizing shape need to be comprehensive, reliable, and suitable for use in vivo. Methods Magnetic resonance images of the thoracic vertebrae were acquired from 20 adults. Repeat scans were acquired, after repositioning the participants, for T4, T8, and T12. Landmark points were placed around the vertebra on the images and used to create a shape model. The reliability was assessed using relative error (E%) and intraclass correlation (ICC). The effect of vertebral level, sex and age on vertebral shape was assessed using repeated measures analysis of variance. Results Five Modes of Variation were retained from the shape model. Reliability was excellent for the first two Modes (mode 1: E% = 7, ICC = 0.98; mode 2: E% = 11, ICC = 0.96). These Modes described Variation in the vertebral bodies, the pedicle width and orientation, and the facet joint position and orientation with respect to the pedicle axis. Variation in vertebral shape was found along the thoracic spine and between individuals, but there was little effect of age and sex. Conclusions Magnetic resonance images and shape modeling provides a reliable method for characterizing vertebral shape in vivo. The method is able to identify differences between vertebral levels and between individuals. The use of these methods may be advantageous for performing repeated measurements in longitudinal studies. Level of Evidence N/A.
-
STATISTICAL SHAPE MODELS of THORACIC VERTEBRAL MORPHOLOGY
Journal of Bone and Joint Surgery-british Volume, 2014Co-Authors: Judith R. Meakin, S.j. Hopkins, A. ClarkeAbstract:The objective of this study was to assess the reliability and appropriateness of statistical shape modelling for capturing Variation in thoracic vertebral anatomy for future use in assessing scoliotic vertebral morphology. Magnetic resonance (MR) images of the thoracic vertebrae were acquired from 20 healthy adults (12 female, 8 male) using a 1.5 T MR scanner (Intera, Philips). A T1 weighted spin-echo sequence (repetition time = 294 ms, echo time = 8 ms, number of signal averages = 3) was used. A set of slices (number = 27, thickness = 1.9 mm, gap = 1.63 mm, pixel size = 0.5 mm) were acquired for each vertebrae, parallel to the mid-transverse plane of the vertebral body. Repeated imaging, including participant repositioning, was performed for T4, T8 and T12 to assess reliability. Landmark points were placed on the images to define anatomical features consisting of the vertebral body and foramen, pedicles, transverse and spinous processes, inferior and superior facets. A statistical shape model was created using software tools developed in MATLAB (R2013a, The MathWorks Inc.). The model was used to determine the mean vertebral shape and ‘Modes of Variation’ describing patterns in vertebral shape. Analysis of variance was used to test for differences between vertebral levels and subjects and reliability was assessed by determining the within-subject standard deviation from the repeated measurements. The first three Modes of Variation, shown below (green = mean, red and blue = ±2 standard deviations about the mean), accounted for 70% of the Variation in thoracic vertebral shape (Mode 1 = 44%, Mode 2 = 19%, Mode 3 = 4%). Visual inspection indicated that these Modes described Variation in anatomical features such as the aspect ratio of the vertebral bodies, width and orientation of the pedicles, and position and orientation of the processes and facet points. Variation in shape along the thoracic spine, characterised by these Modes of Variation, was consistent with that reported in the literature. Significant differences (p Statistical shape modelling provides a reliable method for characterizing many anatomical features of the thoracic vertebrae in a compact number of variables. This is useful for robustly assessing morphological differences between scoliotic and non-scoliotic vertebrae and in assessing entry points and trajectories for pedicle screws.
Evdokia Nikolova - One of the best experts on this subject based on the ideXlab platform.
-
A Directed Graph Fourier Transform With Spread Frequency Components
IEEE Transactions on Signal Processing, 2019Co-Authors: Rasoul Shafipour, Ali Khodabakhsh, Gonzalo Mateos, Evdokia NikolovaAbstract:We study the problem of constructing a graph Fourier transform (GFT) for directed graphs (digraphs), which decomposes graph signals into different Modes of Variation with respect to the underlying network. Accordingly, to capture low, medium, and high frequencies we seek a digraph (D)GFT such that the orthonormal frequency components are as spread as possible in the graph spectral domain. To that end, we advocate a two-step design whereby we 1) find the maximum directed Variation (i.e., a novel notion of frequency on a digraph) a candidate basis vector can attain and 2) minimize a smooth spectral dispersion function over the achievable frequency range to obtain the desired spread DGFT basis. Both steps involve non-convex, orthonormality-constrained optimization problems, which are efficiently tackled via a feasible optimization method on the Stiefel manifold that provably converges to a stationary solution. We also propose a heuristic to construct the DGFT basis from Laplacian eigenvectors of an undirected version of the digraph. We show that the spectral-dispersion minimization problem can be cast as supermodular optimization over the set of candidate frequency components, whose orthonormality can be enforced via a matroid basis constraint. This motivates adopting a scalable greedy algorithm to obtain an approximate solution with quantifiable worst-case spectral dispersion. We illustrate the effectiveness of our DGFT algorithms through numerical tests on synthetic and real-world networks. We also carry out a graph-signal denoising task, whereby the DGFT basis is used to decompose and then low pass filter temperatures recorded across the United States.
-
Digraph Fourier Transform via Spectral Dispersion Minimization
2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2018Co-Authors: Rasoul Shafipour, Ali Khodabakhsh, Gonzalo Mateos, Evdokia NikolovaAbstract:We address the problem of constructing a graph Fourier transform (GFT) for both undirected and directed graphs (digraphs), which decomposes graph signals into different Modes of Variation with respect to the underlying network. Accordingly, we seek orthonormal bases that yield maximally-spread frequency components in the graph spectral domain to better capture low, medium and high frequencies. To that end, we advocate a two-step design whereby we: (i) find the maximum directed Variation (i.e., frequency on a digraph) a candidate basis vector can attain; and (ii) minimize a smooth spectral dispersion function over the achievable frequency range to obtain the desired spread GFT basis. Both steps involve non-convex, orthonormality-constrained optimization problems, which are efficiently tackled via a provably convergent, feasible optimization method on the Stiefel manifold. We illustrate the effectiveness of the novel GFT construction algorithm through numerical tests on synthetic and real-world graphs.
-
A digraph fourier transform with spread frequency components
2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2017Co-Authors: Rasoul Shafipour, Ali Khodabakhsh, Gonzalo Mateos, Evdokia NikolovaAbstract:We study the problem of constructing a graph Fourier transform (GFT) for directed graphs (digraphs), which decomposes graph signals into different Modes of Variation with respect to the underlying network. Accordingly, to capture low, medium and high frequencies we seek a digraph (D)GFT such that the orthonormal frequency components are as spread as possible in the graph spectral domain. This specification gives rise to a challenging nonconvex optimization problem, so we resort to a simple yet efficient heuristic to construct the DGFT basis from Laplacian eigenvectors of an undirected version of the digraph. To select frequency components which are as spread as possible, we define a spectral dispersion function and show that it is supermodular. Moreover, we show that orthonormality can be enforced via a matroid basis constraint, which motivates adopting a scalable greedy algorithm to obtain an approximate solution with provable performance guarantee. The effectiveness of the novel DGFT is illustrated through numerical tests on synthetic and real-world graphs.
Yong Man Ro - One of the best experts on this subject based on the ideXlab platform.
-
encoding features robust to unseen Modes of Variation with attentive long short term memory
Pattern Recognition, 2020Co-Authors: Wissam J Baddar, Yong Man RoAbstract:Abstract Long short-term memory (LSTM) is a type of recurrent neural networks that is efficient for encoding spatio-temporal features in dynamic sequences. Recent work has shown that the LSTM retains information related to the mode of Variation in the input dynamic sequence which reduces the discriminability of the encoded features. To encode features robust to unseen Modes of Variation, we devise an LSTM adaptation named attentive mode Variational LSTM. The proposed attentive mode Variational LSTM utilizes the concept of attention to separate the input dynamic sequence into two parts: (1) task-relevant dynamic sequence features and (2) task-irrelevant static sequence features. The task-relevant dynamic features are used to encode and emphasize the dynamics in the input sequence. The task-irrelevant static sequence features are utilized to encode the mode of Variation in the input dynamic sequence. Finally, the attentive mode Variational LSTM suppresses the effect of mode Variation with a shared output gate and results in a spatio-temporal feature robust to unseen Variations. The effectiveness of the proposed attentive mode Variational LSTM has been verified using two tasks: facial expression recognition and human action recognition. Comprehensive and extensive experiments have verified that the proposed method encodes spatio-temporal features robust to Variations unseen during the training.
-
mode Variational lstm robust to unseen Modes of Variation application to facial expression recognition
National Conference on Artificial Intelligence, 2019Co-Authors: Wissam J Baddar, Yong Man RoAbstract:Spatio-temporal feature encoding is essential for encoding the dynamics in video sequences. Recurrent neural networks, particularly long short-term memory (LSTM) units, have been popular as an efficient tool for encoding spatio-temporal features in sequences. In this work, we investigate the effect of mode Variations on the encoded spatio-temporal features using LSTMs. We show that the LSTM retains information related to the mode Variation in the sequence, which is irrelevant to the task at hand (e.g. classification facial expressions). Actually, the LSTM forget mechanism is not robust enough to mode Variations and preserves information that could negatively affect the encoded spatio-temporal features. We propose the mode Variational LSTM to encode spatio-temporal features robust to unseen Modes of Variation. The mode Variational LSTM modifies the original LSTM structure by adding an additional cell state that focuses on encoding the mode Variation in the input sequence. To efficiently regulate what features should be stored in the additional cell state, additional gating functionality is also introduced. The effectiveness of the proposed mode Variational LSTM is verified using the facial expression recognition task. Comparative experiments on publicly available datasets verified that the proposed mode Variational LSTM outperforms existing methods. Moreover, a new dynamic facial expression dataset with different Modes of Variation, including various Modes like pose and illumination Variations, was collected to comprehensively evaluate the proposed mode Variational LSTM. Experimental results verified that the proposed mode Variational LSTM encodes spatio-temporal features robust to unseen Modes of Variation.
-
AAAI - Mode Variational LSTM Robust to Unseen Modes of Variation: Application to Facial Expression Recognition
Proceedings of the AAAI Conference on Artificial Intelligence, 2019Co-Authors: Wissam J Baddar, Yong Man RoAbstract:Spatio-temporal feature encoding is essential for encoding the dynamics in video sequences. Recurrent neural networks, particularly long short-term memory (LSTM) units, have been popular as an efficient tool for encoding spatio-temporal features in sequences. In this work, we investigate the effect of mode Variations on the encoded spatio-temporal features using LSTMs. We show that the LSTM retains information related to the mode Variation in the sequence, which is irrelevant to the task at hand (e.g. classification facial expressions). Actually, the LSTM forget mechanism is not robust enough to mode Variations and preserves information that could negatively affect the encoded spatio-temporal features. We propose the mode Variational LSTM to encode spatio-temporal features robust to unseen Modes of Variation. The mode Variational LSTM modifies the original LSTM structure by adding an additional cell state that focuses on encoding the mode Variation in the input sequence. To efficiently regulate what features should be stored in the additional cell state, additional gating functionality is also introduced. The effectiveness of the proposed mode Variational LSTM is verified using the facial expression recognition task. Comparative experiments on publicly available datasets verified that the proposed mode Variational LSTM outperforms existing methods. Moreover, a new dynamic facial expression dataset with different Modes of Variation, including various Modes like pose and illumination Variations, was collected to comprehensively evaluate the proposed mode Variational LSTM. Experimental results verified that the proposed mode Variational LSTM encodes spatio-temporal features robust to unseen Modes of Variation.
Nicholas Ayache - One of the best experts on this subject based on the ideXlab platform.
-
Medical Imaging: Image Processing - Comparison of statistical shape models built on correspondence probabilities and one-to-one correspondences
Medical Imaging 2008: Image Processing, 2008Co-Authors: Heike Hufnagel, Jan Ehrhardt, Xavier Pennec, Nicholas Ayache, Heinz HandelsAbstract:In this paper, we present a method to compute a statistical shape model based on shapes which are represented by unstructured point sets with arbitrary point numbers. A fundamental problem when computing statistical shape models is the determination of correspondences between the observations of the associated data set. often, homologies between points that represent the surfaces are assumed. When working merely with point clouds, this might lead to imprecise mean shape and variability results. To overcome this problem, we propose an approach where exact correspondences are replaced by evolving correspondence probabilities. These are the basis for a novel algorithm that computes a generative statistical shape model. We developed a unified Maximum A Posteriori (MAP) framework to compute the model parameters ('mean shape' and 'Modes of Variation') and the nuisance parameters which leads to an optimal adaption of the model to the set of observations. The registration of the model on the observations is solved using the Expectation Maximization - Iterative Closest Point algorithm which is based on probabilistic correspondences and proved to be robust and fast. The alternated optimization of the MAP explanation with respect to the observation and the generative model parameters leads to very efficient and closed-form solutions for nearly all parameters. A comparison with a statistical shape model which is built using the Iterative Closest Point (ICP) registration algorithm and a Principal Component Analysis (PCA) shows that our approach leads to better SSM quality measures.
-
shape analysis using a point based statistical shape model built on correspondence probabilities
Medical Image Computing and Computer-Assisted Intervention, 2007Co-Authors: Heike Hufnagel, Jan Ehrhardt, Heinz Handels, Xavier Pennec, Nicholas AyacheAbstract:A fundamental problem when computing statistical shape models is the determination of correspondences between the instances of the associated data set. often, homologies between points that represent the surfaces are assumed which might lead to imprecise mean shape and variability results. We propose an approach where exact correspondences are replaced by evolving correspondence probabilities. These are the basis for a novel algorithm that computes a generative statistical shape model. We developed an unified MAP framework to compute the model parameters ('mean shape' and 'Modes of Variation') and the nuisance parameters which leads to an optimal adaption of the model to the set of observations. The registration of the model on the instances is solved using the Expectation Maximization - Iterative Closest Point algorithm which is based on probabilistic correspondences and proved to be robust and fast. The alternated optimization of the MAP explanation with respect to the observation and the generative model parameters leads to very efficient and closed-form solutions for (almost) all parameters. Experimental results on brain structure data sets demonstrate the efficiency and well-posedness of the approach. The algorithm is then extended to an automatic classification method using the k-means clustering and applied to synthetic data as well as brain structure classification problems.
-
STATISTICAL SHAPE ANALYSIS VIA PRINCIPAL FACTOR ANALYSIS
2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2007Co-Authors: Mauricio Reyes Aguirre, Nicholas Ayache, Marius George Linguraru, Kostas Marias, Lutz-peter Nolte, Miguel Angel Gonzalez BallesterAbstract:Statistical shape analysis techniques commonly employed in the medical imaging community, such as active shape models or active appearance models, rely on principal component analysis (PCA) to decompose shape variability into a reduced set of interpretable components. In this paper we propose principal factor analysis (PFA) as an alternative and complementary tool to PCA providing a decomposition into Modes of Variation that can be more easily interpretable, while still being a linear efficient technique that performs dimensionality reduction (as opposed to independent component analysis, ICA). The key difference between PFA and PCA is that PFA models covariance between variables, rather than the total variance in the data. The added value of PFA is illustrated on 2D landmark data of corpora callosa outlines. Then, a study of the 3D shape variability of the human left femur is performed. Finally, we report results on vector-valued 3D deformation fields resulting from non-rigid registration of ventricles in MRI of the brain.
Judith R. Meakin - One of the best experts on this subject based on the ideXlab platform.
-
In Vivo Assessment of Thoracic Vertebral Shape From MRI Data Using a Shape Model
Spine Deformity, 2019Co-Authors: Judith R. Meakin, S.j. Hopkins, A. ClarkeAbstract:Study Design Feasibility study on characterizing thoracic vertebral shape from magnetic resonance images using a shape model. Objectives Assess the reliability of characterizing thoracic vertebral shape from magnetic resonance images and estimate the normal Variation in vertebral shape using a shape model. Summary of Background Data The characterization of thoracic vertebra shape is important for understanding the initiation and progression of deformity and in developing surgical methods. Methods for characterizing shape need to be comprehensive, reliable, and suitable for use in vivo. Methods Magnetic resonance images of the thoracic vertebrae were acquired from 20 adults. Repeat scans were acquired, after repositioning the participants, for T4, T8, and T12. Landmark points were placed around the vertebra on the images and used to create a shape model. The reliability was assessed using relative error (E%) and intraclass correlation (ICC). The effect of vertebral level, sex and age on vertebral shape was assessed using repeated measures analysis of variance. Results Five Modes of Variation were retained from the shape model. Reliability was excellent for the first two Modes (mode 1: E% = 7, ICC = 0.98; mode 2: E% = 11, ICC = 0.96). These Modes described Variation in the vertebral bodies, the pedicle width and orientation, and the facet joint position and orientation with respect to the pedicle axis. Variation in vertebral shape was found along the thoracic spine and between individuals, but there was little effect of age and sex. Conclusions Magnetic resonance images and shape modeling provides a reliable method for characterizing vertebral shape in vivo. The method is able to identify differences between vertebral levels and between individuals. The use of these methods may be advantageous for performing repeated measurements in longitudinal studies. Level of Evidence N/A.
-
STATISTICAL SHAPE MODELS of THORACIC VERTEBRAL MORPHOLOGY
Journal of Bone and Joint Surgery-british Volume, 2014Co-Authors: Judith R. Meakin, S.j. Hopkins, A. ClarkeAbstract:The objective of this study was to assess the reliability and appropriateness of statistical shape modelling for capturing Variation in thoracic vertebral anatomy for future use in assessing scoliotic vertebral morphology. Magnetic resonance (MR) images of the thoracic vertebrae were acquired from 20 healthy adults (12 female, 8 male) using a 1.5 T MR scanner (Intera, Philips). A T1 weighted spin-echo sequence (repetition time = 294 ms, echo time = 8 ms, number of signal averages = 3) was used. A set of slices (number = 27, thickness = 1.9 mm, gap = 1.63 mm, pixel size = 0.5 mm) were acquired for each vertebrae, parallel to the mid-transverse plane of the vertebral body. Repeated imaging, including participant repositioning, was performed for T4, T8 and T12 to assess reliability. Landmark points were placed on the images to define anatomical features consisting of the vertebral body and foramen, pedicles, transverse and spinous processes, inferior and superior facets. A statistical shape model was created using software tools developed in MATLAB (R2013a, The MathWorks Inc.). The model was used to determine the mean vertebral shape and ‘Modes of Variation’ describing patterns in vertebral shape. Analysis of variance was used to test for differences between vertebral levels and subjects and reliability was assessed by determining the within-subject standard deviation from the repeated measurements. The first three Modes of Variation, shown below (green = mean, red and blue = ±2 standard deviations about the mean), accounted for 70% of the Variation in thoracic vertebral shape (Mode 1 = 44%, Mode 2 = 19%, Mode 3 = 4%). Visual inspection indicated that these Modes described Variation in anatomical features such as the aspect ratio of the vertebral bodies, width and orientation of the pedicles, and position and orientation of the processes and facet points. Variation in shape along the thoracic spine, characterised by these Modes of Variation, was consistent with that reported in the literature. Significant differences (p Statistical shape modelling provides a reliable method for characterizing many anatomical features of the thoracic vertebrae in a compact number of variables. This is useful for robustly assessing morphological differences between scoliotic and non-scoliotic vertebrae and in assessing entry points and trajectories for pedicle screws.