Because of the growing concern over the radiation dose delivered to patients, X-ray cone-beam CT(CBCT) imaging of low dose is of great interest. It is difficult for traditional reconstruction methods such as Feldkamp ...Because of the growing concern over the radiation dose delivered to patients, X-ray cone-beam CT(CBCT) imaging of low dose is of great interest. It is difficult for traditional reconstruction methods such as Feldkamp to reduce noise and keep resolution at low doses. A typical method to solve this problem is using optimizationbased methods with careful modeling of physics and additional constraints. However, it is computationally expensive and very time-consuming to reach an optimal solution. Recently, some pioneering work applying deep neural networks had some success in characterizing and removing artifacts from a low-dose data set. In this study,we incorporate imaging physics for a cone-beam CT into a residual convolutional neural network and propose a new end-to-end deep learning-based method for slice-wise reconstruction. By transferring 3D projection to a 2D problem with a noise reduction property, we can not only obtain reconstructions of high image quality, but also lower the computational complexity. The proposed network is composed of three serially connected sub-networks: a cone-to-fan transformation sub-network, a 2D analytical inversion sub-network, and an image refinement sub-network. This provides a comprehensive solution for end-to-end reconstruction for CBCT. The advantages of our method are that the network can simplify a 3D reconstruction problem to a 2D slice-wise reconstruction problem and can complete reconstruction in an end-to-end manner with the system matrix integrated into the network design. Furthermore, reconstruction can be less computationally expensive and easily parallelizable compared with iterative reconstruction methods.展开更多
Neural network methods have recently emerged as a hot topic in computed tomography(CT) imaging owing to their powerful fitting ability;however, their potential applications still need to be carefully studied because t...Neural network methods have recently emerged as a hot topic in computed tomography(CT) imaging owing to their powerful fitting ability;however, their potential applications still need to be carefully studied because their results are often difficult to interpret and are ambiguous in generalizability. Thus, quality assessments of the results obtained from a neural network are necessary to evaluate the neural network. Assessing the image quality of neural networks using traditional objective measurements is not appropriate because neural networks are nonstationary and nonlinear. In contrast, subjective assessments are trustworthy, although they are time-and energy-consuming for radiologists. Model observers that mimic subjective assessment require the mean and covariance of images, which are calculated from numerous image samples;however, this has not yet been applied to the evaluation of neural networks. In this study, we propose an analytical method for noise propagation from a single projection to efficiently evaluate convolutional neural networks(CNNs) in the CT imaging field. We propagate noise through nonlinear layers in a CNN using the Taylor expansion. Nesting of the linear and nonlinear layer noise propagation constitutes the covariance estimation of the CNN. A commonly used U-net structure is adopted for validation. The results reveal that the covariance estimation obtained from the proposed analytical method agrees well with that obtained from the image samples for different phantoms, noise levels, and activation functions, demonstrating that propagating noise from only a single projection is feasible for CNN methods in CT reconstruction. In addition, we use covariance estimation to provide three measurements for the qualitative and quantitative performance evaluation of U-net. The results indicate that the network cannot be applied to projections with high noise levels and possesses limitations in terms of efficiency for processing low-noise projections. U-net is more effective in improving the image quality of smooth regions compared with that of the edge. LeakyReLU outperforms Swish in terms of noise reduction.展开更多
Spectral computed tomography(CT) based on photon counting detectors(PCDs) is a well-researched topic in the field of X-ray imaging. When PCD is applied in a spectral CT system, the PCD energy thresholds must be carefu...Spectral computed tomography(CT) based on photon counting detectors(PCDs) is a well-researched topic in the field of X-ray imaging. When PCD is applied in a spectral CT system, the PCD energy thresholds must be carefully selected, especially for K-edge imaging, which is an important spectral CT application. This paper presents a threshold selection method that yields better-quality images in K-edge imaging. The main idea is to optimize the energy thresholds ray-by-ray according to the targeted component coefficients, followed by obtaining an overall optimal energy threshold by frequency voting. A low-dose pre-scan is used in practical implementations to estimate the line integrals of the component coefficients for the basis functions. The variance of the decomposed component coefficients is then minimized using the Cramer–Rao lower bound method with respect to the energy thresholds. The optimal energy thresholds are then used to take a full scan and gain better image reconstruction with less noise than would be given by a full scan using the non-optimal energy thresholds. Simulations and practical experiments on imaging iodine and gadolinium solutions, which are commonly used as contrast agents in medical applications, were used to validate the method. The noise was significantly reduced with the same dose relative to the non-optimal energy thresholds in both simulations and in practical experiments.展开更多
基金supported by the National Natural Science Foundation of China(Nos.61771279,11435007)the National Key Research and Development Program of China(No.2016YFF0101304)
文摘Because of the growing concern over the radiation dose delivered to patients, X-ray cone-beam CT(CBCT) imaging of low dose is of great interest. It is difficult for traditional reconstruction methods such as Feldkamp to reduce noise and keep resolution at low doses. A typical method to solve this problem is using optimizationbased methods with careful modeling of physics and additional constraints. However, it is computationally expensive and very time-consuming to reach an optimal solution. Recently, some pioneering work applying deep neural networks had some success in characterizing and removing artifacts from a low-dose data set. In this study,we incorporate imaging physics for a cone-beam CT into a residual convolutional neural network and propose a new end-to-end deep learning-based method for slice-wise reconstruction. By transferring 3D projection to a 2D problem with a noise reduction property, we can not only obtain reconstructions of high image quality, but also lower the computational complexity. The proposed network is composed of three serially connected sub-networks: a cone-to-fan transformation sub-network, a 2D analytical inversion sub-network, and an image refinement sub-network. This provides a comprehensive solution for end-to-end reconstruction for CBCT. The advantages of our method are that the network can simplify a 3D reconstruction problem to a 2D slice-wise reconstruction problem and can complete reconstruction in an end-to-end manner with the system matrix integrated into the network design. Furthermore, reconstruction can be less computationally expensive and easily parallelizable compared with iterative reconstruction methods.
基金supported by the National Natural Science Foundation of China(Nos.62031020 and 61771279)。
文摘Neural network methods have recently emerged as a hot topic in computed tomography(CT) imaging owing to their powerful fitting ability;however, their potential applications still need to be carefully studied because their results are often difficult to interpret and are ambiguous in generalizability. Thus, quality assessments of the results obtained from a neural network are necessary to evaluate the neural network. Assessing the image quality of neural networks using traditional objective measurements is not appropriate because neural networks are nonstationary and nonlinear. In contrast, subjective assessments are trustworthy, although they are time-and energy-consuming for radiologists. Model observers that mimic subjective assessment require the mean and covariance of images, which are calculated from numerous image samples;however, this has not yet been applied to the evaluation of neural networks. In this study, we propose an analytical method for noise propagation from a single projection to efficiently evaluate convolutional neural networks(CNNs) in the CT imaging field. We propagate noise through nonlinear layers in a CNN using the Taylor expansion. Nesting of the linear and nonlinear layer noise propagation constitutes the covariance estimation of the CNN. A commonly used U-net structure is adopted for validation. The results reveal that the covariance estimation obtained from the proposed analytical method agrees well with that obtained from the image samples for different phantoms, noise levels, and activation functions, demonstrating that propagating noise from only a single projection is feasible for CNN methods in CT reconstruction. In addition, we use covariance estimation to provide three measurements for the qualitative and quantitative performance evaluation of U-net. The results indicate that the network cannot be applied to projections with high noise levels and possesses limitations in terms of efficiency for processing low-noise projections. U-net is more effective in improving the image quality of smooth regions compared with that of the edge. LeakyReLU outperforms Swish in terms of noise reduction.
基金supported by Grants from National key research and development program(No.2016YFF0101304)the National Natural Science Foundation of China(Nos.61771279,11435007)
文摘Spectral computed tomography(CT) based on photon counting detectors(PCDs) is a well-researched topic in the field of X-ray imaging. When PCD is applied in a spectral CT system, the PCD energy thresholds must be carefully selected, especially for K-edge imaging, which is an important spectral CT application. This paper presents a threshold selection method that yields better-quality images in K-edge imaging. The main idea is to optimize the energy thresholds ray-by-ray according to the targeted component coefficients, followed by obtaining an overall optimal energy threshold by frequency voting. A low-dose pre-scan is used in practical implementations to estimate the line integrals of the component coefficients for the basis functions. The variance of the decomposed component coefficients is then minimized using the Cramer–Rao lower bound method with respect to the energy thresholds. The optimal energy thresholds are then used to take a full scan and gain better image reconstruction with less noise than would be given by a full scan using the non-optimal energy thresholds. Simulations and practical experiments on imaging iodine and gadolinium solutions, which are commonly used as contrast agents in medical applications, were used to validate the method. The noise was significantly reduced with the same dose relative to the non-optimal energy thresholds in both simulations and in practical experiments.
