Accelerated Compressed Sensing Based CT Image Reconstruction

In X-ray computed tomography (CT) an important objective is to reduce the radiation dose without significantly degrading the image quality. Compressed sensing (CS) enables the radiation dose to be reduced by producing diagnostic images from a limited number of projections. However, conventional CS-based algorithms are computationally intensive and time-consuming. We propose a new algorithm that accelerates the CS-based reconstruction by using a fast pseudopolar Fourier based Radon transform and rebinning the diverging fan beams to parallel beams. The reconstruction process is analyzed using a maximum-a-posterior approach, which is transformed into a weighted CS problem. The weights involved in the proposed model are calculated based on the statistical characteristics of the reconstruction process, which is formulated in terms of the measurement noise and rebinning interpolation error .Therefore, the proposed method not only accelerates the reconstruction, but also removes the rebinning and interpolation errors. Simulation results are shown for phantoms and a patient. For example, a 512 × 512 Shepp-Logan phantom when reconstructed from 128 rebinned projections using a conventional CS method had 10% error, whereas with the proposed method the reconstruction error was less than 1%.Moreover, computation times of less than 30 sec were obtained using a standard desktop computer without numerical optimization.

Download Full-text

Accelerated Compressed Sensing Based CT Image Reconstruction

Computational and Mathematical Methods in Medicine ◽

10.1155/2015/161797 ◽

2015 ◽

Vol 2015 ◽

pp. 1-16 ◽

Cited By ~ 6

Author(s):

SayedMasoud Hashemi ◽

Soosan Beheshti ◽

Patrick R. Gill ◽

Narinder S. Paul ◽

Richard S. C. Cobbold

Keyword(s):

Radiation Dose ◽

Compressed Sensing ◽

Reconstruction Error ◽

Statistical Characteristics ◽

Desktop Computer ◽

Reconstruction Process ◽

Proposed Model ◽

X Ray Computed ◽

Maximum A Posterior ◽

Computationally Intensive

In X-ray computed tomography (CT) an important objective is to reduce the radiation dose without significantly degrading the image quality. Compressed sensing (CS) enables the radiation dose to be reduced by producing diagnostic images from a limited number of projections. However, conventional CS-based algorithms are computationally intensive and time-consuming. We propose a new algorithm that accelerates the CS-based reconstruction by using a fast pseudopolar Fourier based Radon transform and rebinning the diverging fan beams to parallel beams. The reconstruction process is analyzed using a maximum-a-posterior approach, which is transformed into a weighted CS problem. The weights involved in the proposed model are calculated based on the statistical characteristics of the reconstruction process, which is formulated in terms of the measurement noise and rebinning interpolation error. Therefore, the proposed method not only accelerates the reconstruction, but also removes the rebinning and interpolation errors. Simulation results are shown for phantoms and a patient. For example, a 512 × 512 Shepp-Logan phantom when reconstructed from 128 rebinned projections using a conventional CS method had 10% error, whereas with the proposed method the reconstruction error was less than 1%. Moreover, computation times of less than 30 sec were obtained using a standard desktop computer without numerical optimization.

Download Full-text

Accelerated Compressed Sensing Based CT Image Reconstruction

10.32920/14639349.v1 ◽

2021 ◽

Author(s):

Sayed Masoud Hashemi ◽

Soosan Beheshti ◽

Patrick R. Gill ◽

Narinder S. Paul ◽

Richard S. C. Cobbold

Keyword(s):

Radiation Dose ◽

Compressed Sensing ◽

Reconstruction Error ◽

Statistical Characteristics ◽

Desktop Computer ◽

Reconstruction Process ◽

Proposed Model ◽

X Ray Computed ◽

Maximum A Posterior ◽

Computationally Intensive

Download Full-text

Parallel Computing of Patch-Based Nonlocal Operator and Its Application in Compressed Sensing MRI

Computational and Mathematical Methods in Medicine ◽

10.1155/2014/257435 ◽

2014 ◽

Vol 2014 ◽

pp. 1-6

Author(s):

Qiyue Li ◽

Xiaobo Qu ◽

Yunsong Liu ◽

Di Guo ◽

Jing Ye ◽

...

Keyword(s):

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Compressed Sensing ◽

Multicore Processors ◽

Parallel Architecture ◽

Computation Time ◽

Reconstruction Error ◽

Nonlocal Operator ◽

Resonance Imaging ◽

Reconstruction Process

Magnetic resonance imaging has been benefited from compressed sensing in improving imaging speed. But the computation time of compressed sensing magnetic resonance imaging (CS-MRI) is relatively long due to its iterative reconstruction process. Recently, a patch-based nonlocal operator (PANO) has been applied in CS-MRI to significantly reduce the reconstruction error by making use of self-similarity in images. But the two major steps in PANO, learning similarities and performing 3D wavelet transform, require extensive computations. In this paper, a parallel architecture based on multicore processors is proposed to accelerate computations of PANO. Simulation results demonstrate that the acceleration factor approaches the number of CPU cores and overall PANO-based CS-MRI reconstruction can be accomplished in several seconds.

Download Full-text

Nodule Detection with Convolutional Neural Network Using Apache Spark and GPU Frameworks

Applied Sciences ◽

10.3390/app11062838 ◽

2021 ◽

Vol 11 (6) ◽

pp. 2838

Author(s):

Nikitha Johnsirani Venkatesan ◽

Dong Ryeol Shin ◽

Choon Sung Nam

Keyword(s):

Neural Network ◽

Radiation Dose ◽

Convolutional Neural Network ◽

Model Performance ◽

Performance Comparison ◽

Apache Spark ◽

Training Time ◽

Learning Framework ◽

Proposed Model

In the pharmaceutical field, early detection of lung nodules is indispensable for increasing patient survival. We can enhance the quality of the medical images by intensifying the radiation dose. High radiation dose provokes cancer, which forces experts to use limited radiation. Using abrupt radiation generates noise in CT scans. We propose an optimal Convolutional Neural Network model in which Gaussian noise is removed for better classification and increased training accuracy. Experimental demonstration on the LUNA16 dataset of size 160 GB shows that our proposed method exhibit superior results. Classification accuracy, specificity, sensitivity, Precision, Recall, F1 measurement, and area under the ROC curve (AUC) of the model performance are taken as evaluation metrics. We conducted a performance comparison of our proposed model on numerous platforms, like Apache Spark, GPU, and CPU, to depreciate the training time without compromising the accuracy percentage. Our results show that Apache Spark, integrated with a deep learning framework, is suitable for parallel training computation with high accuracy.

Download Full-text

Gradient Projection with Approximate L0 Norm Minimization for Sparse Reconstruction in Compressed Sensing

Sensors ◽

10.3390/s18103373 ◽

2018 ◽

Vol 18 (10) ◽

pp. 3373 ◽

Cited By ~ 6

Author(s):

Ziran Wei ◽

Jianlin Zhang ◽

Zhiyong Xu ◽

Yongmei Huang ◽

Yong Liu ◽

...

Keyword(s):

Image Reconstruction ◽

Compressed Sensing ◽

Objective Function ◽

Signal Reconstruction ◽

Reconstruction Error ◽

Sparse Signal ◽

Reconstruction Accuracy ◽

L1 Norm ◽

Function Model ◽

L2 Norm

In the reconstruction of sparse signals in compressed sensing, the reconstruction algorithm is required to reconstruct the sparsest form of signal. In order to minimize the objective function, minimal norm algorithm and greedy pursuit algorithm are most commonly used. The minimum L1 norm algorithm has very high reconstruction accuracy, but this convex optimization algorithm cannot get the sparsest signal like the minimum L0 norm algorithm. However, because the L0 norm method is a non-convex problem, it is difficult to get the global optimal solution and the amount of calculation required is huge. In this paper, a new algorithm is proposed to approximate the smooth L0 norm from the approximate L2 norm. First we set up an approximation function model of the sparse term, then the minimum value of the objective function is solved by the gradient projection, and the weight of the function model of the sparse term in the objective function is adjusted adaptively by the reconstruction error value to reconstruct the sparse signal more accurately. Compared with the pseudo inverse of L2 norm and the L1 norm algorithm, this new algorithm has a lower reconstruction error in one-dimensional sparse signal reconstruction. In simulation experiments of two-dimensional image signal reconstruction, the new algorithm has shorter image reconstruction time and higher image reconstruction accuracy compared with the usually used greedy algorithm and the minimum norm algorithm.

Download Full-text

Compressed Sensing and Its Application in CT and EEG

Medical Imaging ◽

10.4018/978-1-5225-0571-6.ch046 ◽

2017 ◽

pp. 1126-1149

Author(s):

Sajib Saha ◽

Murat Tahtali

Keyword(s):

Compressed Sensing ◽

Applied Mathematics ◽

Signal Reconstruction ◽

Optimization Technique ◽

Linear Measurements ◽

Reconstruction Procedure ◽

Sparsity Constraints ◽

Ill Posed ◽

X Ray Computed ◽

A New Technique

Compressed sensing, also known as compressive sampling is a new technique being rapidly developed over the last few years. The theory states that when some prior information about the signal is available and appropriately incorporated into the signal reconstruction procedure, a signal can be accurately reconstructed even if the Shannon/ Nyquest sampling requirement is violated. The key idea of compressed sensing is to recover a sparse signal from very few non-adaptive, linear measurements by optimization technique. Following the discovery by Donoho in (2006), that sparsity could enable exact solution of ill-posed problems under certain conditions, there has been a tremendous growth on efficient application of sparsity constraints for solving ill-posed problems. The theoretical foundation of compressed sensing has already become a key concept in various areas of applied mathematics, computer science, and electrical engineering. In this chapter we will detail the application of compressed sensing in X-ray computed tomography (CT) and Electroencephalography. Starting from the very basic principles we will provide theoretical justifications on why and how sparsity prior is used in CT and in EEG.

Download Full-text

A Combined Quantitative Evaluation Model for the Capability of Hyperspectral Imagery for Mineral Mapping

Sensors ◽

10.3390/s19020328 ◽

2019 ◽

Vol 19 (2) ◽

pp. 328 ◽

Cited By ~ 3

Author(s):

Na Li ◽

Xinchen Huang ◽

Huijie Zhao ◽

Xianfei Qiu ◽

Kewang Deng ◽

...

Keyword(s):

Remote Sensing ◽

Statistical Analysis ◽

Imaging System ◽

Evaluation Model ◽

Spectral Response ◽

Influence Factors ◽

Hyperspectral Data ◽

Statistical Characteristics ◽

Mineral Mapping ◽

Proposed Model

To analyze the influence factors of hyperspectral remote sensing data processing, and quantitatively evaluate the application capability of hyperspectral data, a combined evaluation model based on the physical process of imaging and statistical analysis was proposed. The normalized average distance between different classes of ground cover is selected as the evaluation index. The proposed model considers the influence factors of the full radiation transmission process and processing algorithms. First- and second-order statistical characteristics (mean and covariance) were applied to calculate the changes for the imaging process based on the radiation energy transfer. The statistical analysis was combined with the remote sensing process and the application performance, which consists of the imaging system parameters and imaging conditions, by building the imaging system and processing models. The season (solar zenith angle), sensor parameters (ground sampling distance, modulation transfer function, spectral resolution, spectral response function, and signal to noise ratio), and number of features were considered in order to analyze the influence factors of the application capability level. Simulated and real data collected by Hymap in the Dongtianshan area (Xinjiang Province, China), were used to estimate the proposed model’s performance in the application of mineral mapping. The predicted application capability of the proposed model is consistent with the theoretical analysis.

Download Full-text

An Adaptive Scheme to Achieve Fine Grained Video Scaling

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v8.i1.pp43-58 ◽

2017 ◽

Vol 8 (1) ◽

pp. 43

Author(s):

S Safinaz ◽

A. V. Ravi Kumar

Keyword(s):

Reconstruction Error ◽

Experimental Results ◽

Adaptive Scheme ◽

Fine Grained ◽

Proposed Model ◽

Reconstruction Quality ◽

Adaptive Reconstruction ◽

Robust Adaptive ◽

Parallel Configuration ◽

Very High

<p>A robust Adaptive Reconstruction Error Minimization Convolution Neural Network (<strong> ARemCNN</strong>) architecture introduced to provide high reconstruction quality from low resolution using parallel configuration. Our proposed model can easily train the bulky datasets such as YUV21 and Videoset4.Our experimental results shows that our model outperforms many existing techniques in terms of PSNR, SSIM and reconstruction quality. The experimental results shows that our average PSNR result is 39.81 considering upscale-2, 35.56 for upscale-3 and 33.77 for upscale-4 for Videoset4 dataset which is very high in contrast to other existing techniques. Similarly, the experimental results shows that our average PSNR result is 38.71 considering upscale-2, 34.58 for upscale-3 and 33.047 for upscale-4 for YUV21 dataset.</p>

Download Full-text

Quantization for low-rank matrix recovery

Information and Inference A Journal of the IMA ◽

10.1093/imaiai/iay007 ◽

2018 ◽

Vol 8 (1) ◽

pp. 161-180

Author(s):

Eric Lybrand ◽

Rayan Saab

Keyword(s):

Compressed Sensing ◽

Reconstruction Error ◽

Linear Operators ◽

Low Rank ◽

Quantization Scheme ◽

Reconstruction Algorithms ◽

Finite Frame ◽

Rank Matrix ◽

Band Limited ◽

Low Rank Matrix

Abstract We study Sigma–Delta $(\varSigma\!\varDelta) $ quantization methods coupled with appropriate reconstruction algorithms for digitizing randomly sampled low-rank matrices. We show that the reconstruction error associated with our methods decays polynomially with the oversampling factor, and we leverage our results to obtain root-exponential accuracy by optimizing over the choice of quantization scheme. Additionally, we show that a random encoding scheme, applied to the quantized measurements, yields a near-optimal exponential bit rate. As an added benefit, our schemes are robust both to noise and to deviations from the low-rank assumption. In short, we provide a full generalization of analogous results, obtained in the classical setup of band-limited function acquisition, and more recently, in the finite frame and compressed sensing setups to the case of low-rank matrices sampled with sub-Gaussian linear operators. Finally, we believe our techniques for generalizing results from the compressed sensing setup to the analogous low-rank matrix setup is applicable to other quantization schemes.

Download Full-text

Atrial Fibrillation Detection Directly from Compressed ECG with the Prior of Measurement Matrix

Information ◽

10.3390/info11090436 ◽

2020 ◽

Vol 11 (9) ◽

pp. 436

Author(s):

Yunfei Cheng ◽

Ying Hu ◽

Mengshu Hou ◽

Tongjie Pan ◽

Wenwen He ◽

...

Keyword(s):

Atrial Fibrillation ◽

Compressed Sensing ◽

Health Monitoring ◽

Prior Information ◽

Classification Performance ◽

Experimental Results ◽

Measurement Matrix ◽

Ecg Signals ◽

Proposed Model ◽

Atrial Fibrillation Detection

In the wearable health monitoring based on compressed sensing, atrial fibrillation detection directly from the compressed ECG can effectively reduce the time cost of data processing rather than classification after reconstruction. However, the existing methods for atrial fibrillation detection from compressed ECG did not fully benefit from the existing prior information, resulting in unsatisfactory classification performance, especially in some applications that require high compression ratio (CR). In this paper, we propose a deep learning method to detect atrial fibrillation directly from compressed ECG without reconstruction. Specifically, we design a deep network model for one-dimensional ECG signals, and the measurement matrix is used to initialize the first layer of the model so that the proposed model can obtain more prior information which benefits improving the classification performance of atrial fibrillation detection from compressed ECG. The experimental results on the MIT-BIH Atrial Fibrillation Database show that when the CR is 10%, the accuracy and F1 score of the proposed method reach 97.52% and 98.02%, respectively. Compared with the atrial fibrillation detection from original ECG, the corresponding accuracy and F1 score are only reduced by 0.88% and 0.69%. Even at a high CR of 90%, the accuracy and F1 score are still only reduced by 6.77% and 5.31%, respectively. All of the experimental results demonstrate that the proposed method is superior to other existing methods for atrial fibrillation detection from compressed ECG. Therefore, the proposed method is promising for atrial fibrillation detection in wearable health monitoring based on compressed sensing.

Download Full-text