The Experts below are selected from a list of 135 Experts worldwide ranked by ideXlab platform

Denis Friboulet - One of the best experts on this subject based on the ideXlab platform.

  • compressed sensing reconstruction of 3d ultrasound data using dictionary learning and line wise subsampling
    IEEE Transactions on Medical Imaging, 2015
    Co-Authors: Oana Lorintiu, Herve Liebgott, Martino Alessandrini, Olivier Bernard, Denis Friboulet
    Abstract:

    In this paper we present a compressed sensing (CS) method adapted to 3D ultrasound imaging (US). In contrast to previous work, we propose a new approach based on the use of learned overcomplete dictionaries that allow for much sparser representations of the signals since they are optimized for a particular class of images such as US images. In this study, the dictionary was learned using the K-SVD algorithm and CS reconstruction was performed on the non-log envelope data by removing 20% to 80% of the original data. Using numerically simulated images, we evaluate the influence of the training parameters and of the sampling strategy. The latter is done by comparing the two most common sampling patterns, i.e., point-wise and line-wise random patterns. The results show in particular that line-wise sampling yields an accuracy comparable to the conventional point-wise sampling. This indicates that CS acquisition of 3D data is feasible in a relatively simple setting, and thus offers the perspective of increasing the frame rate by skipping the acquisition of RF lines. Next, we evaluated this approach on US volumes of several ex vivo and in vivo organs. We first show that the learned dictionary approach yields better performances than conventional Fixed Transforms such as Fourier or discrete cosine. Finally, we investigate the generality of the learned dictionary approach and show that it is possible to build a general dictionary allowing to reliably reconstruct different volumes of different ex vivo or in vivo organs.

  • Compressed sensing reconstruction of 3D ultrasound data using dictionary learning and line-wise subsampling
    IEEE Transactions on Medical Imaging, 2015
    Co-Authors: Oana Lorintiu, Herve Liebgott, Martino Alessandrini, Olivier Bernard, Denis Friboulet
    Abstract:

    In this paper we present a compressed sensing (CS) method adapted to 3D ultrasound imaging (US). In contrast to previous work, we propose a new approach based on the use of learned overcomplete dictionaries. Such dictionaries allow for much sparser representations of the signals since they are optimized for a particular class of images such as US images. In this study, the dictionary was learned using the K-SVD algorithm on patches extracted from a training dataset and the reconstruction was performed from 3D volumes not included in the training dataset. In each case, CS reconstruction was performed on the non-log envelope data by removing 20% to 80% of the original samples and the accuracy of the reconstruction was evaluated in terms of the normalized root mean square error relative to the original volume. Using numerically simulated data, we evaluate the influence of the training parameters and the influence of the sampling strategy. The latter is done by comparing the two most common sampling patterns, i.e. point-wise and line-wise random patterns. The results show in particular that line-wise sampling yields an accuracy comparable to the conventional point-wise sampling. This indicates that CS acquisition of 3D data is feasible in a relatively simple setting, and thus offers the perspective of increasing the frame rate by simply skipping the acquisition of many lines among the several thousands required in 3D imaging. We then evaluate the approach on US volumes of several ex vivo and in vivo organs. We first show that the learned dictionary approach yields better performances than conventional sparsifying dictionaries based on Fixed Transforms such as Fourier or discrete cosine. Finally, we investigate the generality of the learned dictionary approach and show that it is possible to build a general dictionary allowing to reliably reconstruct different volumes of different ex vivo or in vivo organs. The difference between the reconstruction error obtained with a- specific dictionary and the one obtained with the general dictionary is minimal

Ali N Akansu - One of the best experts on this subject based on the ideXlab platform.

  • an efficient method to derive explicit klt kernel for first order autoregressive discrete process
    IEEE Transactions on Signal Processing, 2013
    Co-Authors: Mustafa U Torun, Ali N Akansu
    Abstract:

    Signal dependent Karhunen-Loeve transform (KLT), also called factor analysis or principal component analysis (PCA), has been of great interest in applied mathematics and various engineering disciplines due to optimal performance. However, implementation of KLT has always been the main concern. Therefore, Fixed Transforms like discrete Fourier (DFT) and discrete cosine (DCT) with efficient algorithms have been successfully used as good approximations to KLT for popular applications spanning from source coding to digital communications. In this paper, we propose a simple method to derive explicit KLT kernel, or to perform PCA, in closed-form for first-order autoregressive, AR (1), discrete process. It is a widely used approximation to many real world signals. The merit of the proposed technique is shown. The novel method introduced in this paper is expected to make real-time and data-intensive applications of KLT, and PCA, more feasible.

  • performance analysis and optimal structuring of subchannels for discrete multitone transceivers
    International Symposium on Circuits and Systems, 1995
    Co-Authors: A Benyassine, Ali N Akansu
    Abstract:

    A smart algorithm for the decomposition of a channel into its subchannel in the discrete multitone communications is proposed in this paper. This algorithm evaluates the unevenness and energy distribution of the channel spectrum in order to get a variable adaptive partitioning of the channel. It is shown that the proposed algorithm leads to a near optimum performance of the discrete multitone transceiver. This flexible and smart splitting of the channel suffers less from the aliasing problem that exists in blind decompositions using Fixed Transforms. This paper extends the Fixed discrete multitone to the flexible unequal bandwidth multichannel concept which has significant potentials for performance improvements in high-speed digital communications.

  • ISCAS - Performance analysis and optimal structuring of subchannels for discrete multitone transceivers
    Proceedings of ISCAS'95 - International Symposium on Circuits and Systems, 1
    Co-Authors: A Benyassine, Ali N Akansu
    Abstract:

    A smart algorithm for the decomposition of a channel into its subchannel in the discrete multitone communications is proposed in this paper. This algorithm evaluates the unevenness and energy distribution of the channel spectrum in order to get a variable adaptive partitioning of the channel. It is shown that the proposed algorithm leads to a near optimum performance of the discrete multitone transceiver. This flexible and smart splitting of the channel suffers less from the aliasing problem that exists in blind decompositions using Fixed Transforms. This paper extends the Fixed discrete multitone to the flexible unequal bandwidth multichannel concept which has significant potentials for performance improvements in high-speed digital communications.

Oana Lorintiu - One of the best experts on this subject based on the ideXlab platform.

  • compressed sensing reconstruction of 3d ultrasound data using dictionary learning and line wise subsampling
    IEEE Transactions on Medical Imaging, 2015
    Co-Authors: Oana Lorintiu, Herve Liebgott, Martino Alessandrini, Olivier Bernard, Denis Friboulet
    Abstract:

    In this paper we present a compressed sensing (CS) method adapted to 3D ultrasound imaging (US). In contrast to previous work, we propose a new approach based on the use of learned overcomplete dictionaries that allow for much sparser representations of the signals since they are optimized for a particular class of images such as US images. In this study, the dictionary was learned using the K-SVD algorithm and CS reconstruction was performed on the non-log envelope data by removing 20% to 80% of the original data. Using numerically simulated images, we evaluate the influence of the training parameters and of the sampling strategy. The latter is done by comparing the two most common sampling patterns, i.e., point-wise and line-wise random patterns. The results show in particular that line-wise sampling yields an accuracy comparable to the conventional point-wise sampling. This indicates that CS acquisition of 3D data is feasible in a relatively simple setting, and thus offers the perspective of increasing the frame rate by skipping the acquisition of RF lines. Next, we evaluated this approach on US volumes of several ex vivo and in vivo organs. We first show that the learned dictionary approach yields better performances than conventional Fixed Transforms such as Fourier or discrete cosine. Finally, we investigate the generality of the learned dictionary approach and show that it is possible to build a general dictionary allowing to reliably reconstruct different volumes of different ex vivo or in vivo organs.

  • Compressed sensing reconstruction of 3D ultrasound data using dictionary learning and line-wise subsampling
    IEEE Transactions on Medical Imaging, 2015
    Co-Authors: Oana Lorintiu, Herve Liebgott, Martino Alessandrini, Olivier Bernard, Denis Friboulet
    Abstract:

    In this paper we present a compressed sensing (CS) method adapted to 3D ultrasound imaging (US). In contrast to previous work, we propose a new approach based on the use of learned overcomplete dictionaries. Such dictionaries allow for much sparser representations of the signals since they are optimized for a particular class of images such as US images. In this study, the dictionary was learned using the K-SVD algorithm on patches extracted from a training dataset and the reconstruction was performed from 3D volumes not included in the training dataset. In each case, CS reconstruction was performed on the non-log envelope data by removing 20% to 80% of the original samples and the accuracy of the reconstruction was evaluated in terms of the normalized root mean square error relative to the original volume. Using numerically simulated data, we evaluate the influence of the training parameters and the influence of the sampling strategy. The latter is done by comparing the two most common sampling patterns, i.e. point-wise and line-wise random patterns. The results show in particular that line-wise sampling yields an accuracy comparable to the conventional point-wise sampling. This indicates that CS acquisition of 3D data is feasible in a relatively simple setting, and thus offers the perspective of increasing the frame rate by simply skipping the acquisition of many lines among the several thousands required in 3D imaging. We then evaluate the approach on US volumes of several ex vivo and in vivo organs. We first show that the learned dictionary approach yields better performances than conventional sparsifying dictionaries based on Fixed Transforms such as Fourier or discrete cosine. Finally, we investigate the generality of the learned dictionary approach and show that it is possible to build a general dictionary allowing to reliably reconstruct different volumes of different ex vivo or in vivo organs. The difference between the reconstruction error obtained with a- specific dictionary and the one obtained with the general dictionary is minimal

Dong Liang - One of the best experts on this subject based on the ideXlab platform.

  • IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRI
    IEEE Transactions on Computational Imaging, 2020
    Co-Authors: Yiling Liu, Shanshan Wang, Qiegen Liu, Minghui Zhang, Qingxin Yang, Dong Liang
    Abstract:

    To improve the compressive sensing MRI (CS-MRI) approaches in terms of fine structure loss under high acceleration factors, we have proposed an iterative feature refinement model (IFR-CS), equipped with Fixed Transforms, to restore the meaningful structures and details. Nevertheless, the proposed IFR-CS still has some limitations, such as the selection of hyper-parameters, a lengthy reconstruction time, and the Fixed sparsifying transform. To alleviate these issues, we unroll the iterative feature refinement procedures in IFR-CS to a supervised model-driven network, dubbed IFR-Net. Equipped with training data pairs, both regularization parameter and the utmost feature refinement operator in IFR-CS become trainable. Additionally, inspired by the powerful representation capability of convolutional neural network (CNN), CNN-based inversion blocks are explored in the sparsity-promoting denoising module to generalize the sparsity-enforcing operator. Extensive experiments on both simulated and in vivo MR datasets have shown that the proposed network possesses a strong capability to capture image details and preserve well the structural information with fast reconstruction speed.

  • Iterative feature refinement for accurate undersampled MR image reconstruction.
    Physics in medicine and biology, 2016
    Co-Authors: Shanshan Wang, Jianbo Liu, Liu Qiegen, Leslie Ying, Xin Liu, Hairong Zheng, Dong Liang
    Abstract:

    Accelerating MR scan is of great significance for clinical, research and advanced applications, and one main effort to achieve this is the utilization of compressed sensing (CS) theory. Nevertheless, the existing CSMRI approaches still have limitations such as fine structure loss or high computational complexity. This paper proposes a novel iterative feature refinement (IFR) module for accurate MR image reconstruction from undersampled K-space data. Integrating IFR with CSMRI which is equipped with Fixed Transforms, we develop an IFR-CS method to restore meaningful structures and details that are originally discarded without introducing too much additional complexity. Specifically, the proposed IFR-CS is realized with three iterative steps, namely sparsity-promoting denoising, feature refinement and Tikhonov regularization. Experimental results on both simulated and in vivo MR datasets have shown that the proposed module has a strong capability to capture image details, and that IFR-CS is comparable and even superior to other state-of-the-art reconstruction approaches.

Olivier Bernard - One of the best experts on this subject based on the ideXlab platform.

  • compressed sensing reconstruction of 3d ultrasound data using dictionary learning and line wise subsampling
    IEEE Transactions on Medical Imaging, 2015
    Co-Authors: Oana Lorintiu, Herve Liebgott, Martino Alessandrini, Olivier Bernard, Denis Friboulet
    Abstract:

    In this paper we present a compressed sensing (CS) method adapted to 3D ultrasound imaging (US). In contrast to previous work, we propose a new approach based on the use of learned overcomplete dictionaries that allow for much sparser representations of the signals since they are optimized for a particular class of images such as US images. In this study, the dictionary was learned using the K-SVD algorithm and CS reconstruction was performed on the non-log envelope data by removing 20% to 80% of the original data. Using numerically simulated images, we evaluate the influence of the training parameters and of the sampling strategy. The latter is done by comparing the two most common sampling patterns, i.e., point-wise and line-wise random patterns. The results show in particular that line-wise sampling yields an accuracy comparable to the conventional point-wise sampling. This indicates that CS acquisition of 3D data is feasible in a relatively simple setting, and thus offers the perspective of increasing the frame rate by skipping the acquisition of RF lines. Next, we evaluated this approach on US volumes of several ex vivo and in vivo organs. We first show that the learned dictionary approach yields better performances than conventional Fixed Transforms such as Fourier or discrete cosine. Finally, we investigate the generality of the learned dictionary approach and show that it is possible to build a general dictionary allowing to reliably reconstruct different volumes of different ex vivo or in vivo organs.

  • Compressed sensing reconstruction of 3D ultrasound data using dictionary learning and line-wise subsampling
    IEEE Transactions on Medical Imaging, 2015
    Co-Authors: Oana Lorintiu, Herve Liebgott, Martino Alessandrini, Olivier Bernard, Denis Friboulet
    Abstract:

    In this paper we present a compressed sensing (CS) method adapted to 3D ultrasound imaging (US). In contrast to previous work, we propose a new approach based on the use of learned overcomplete dictionaries. Such dictionaries allow for much sparser representations of the signals since they are optimized for a particular class of images such as US images. In this study, the dictionary was learned using the K-SVD algorithm on patches extracted from a training dataset and the reconstruction was performed from 3D volumes not included in the training dataset. In each case, CS reconstruction was performed on the non-log envelope data by removing 20% to 80% of the original samples and the accuracy of the reconstruction was evaluated in terms of the normalized root mean square error relative to the original volume. Using numerically simulated data, we evaluate the influence of the training parameters and the influence of the sampling strategy. The latter is done by comparing the two most common sampling patterns, i.e. point-wise and line-wise random patterns. The results show in particular that line-wise sampling yields an accuracy comparable to the conventional point-wise sampling. This indicates that CS acquisition of 3D data is feasible in a relatively simple setting, and thus offers the perspective of increasing the frame rate by simply skipping the acquisition of many lines among the several thousands required in 3D imaging. We then evaluate the approach on US volumes of several ex vivo and in vivo organs. We first show that the learned dictionary approach yields better performances than conventional sparsifying dictionaries based on Fixed Transforms such as Fourier or discrete cosine. Finally, we investigate the generality of the learned dictionary approach and show that it is possible to build a general dictionary allowing to reliably reconstruct different volumes of different ex vivo or in vivo organs. The difference between the reconstruction error obtained with a- specific dictionary and the one obtained with the general dictionary is minimal