Statistical image reconstruction for low-dose CT using nonlocal means-based regularization

A self-supervised guided knowledge distillation framework for unpaired low-dose CT image denoising

Low-dose computed tomography (LDCT) can significantly reduce the damage of X-ray to the human body, but the reduction of CT dose will produce images with severe noise and artifacts, which will affect the diagnosis of doctors. Recently, deep learning has attracted more and more attention from researchers. However, most of the denoising networks applied to deep learning-based LDCT imaging are supervised methods, which require paired data for network training. In a realistic imaging scenario, obtaining well-aligned image pairs is challenging due to the error in the table re-positioning and the patient's physiological movement during data acquisition. In contrast, the unpaired learning method can overcome the drawbacks of supervised learning, making it more feasible to collect unpaired training data in most real-world imaging applications. In this study, we develop a novel unpaired learning framework, Self-Supervised Guided Knowledge Distillation (SGKD), which enables the guidance of supervised learning using the results generated by self-supervised learning. The proposed SGKD scheme contains two stages of network training. First, we can achieve the LDCT image quality improvement by the designed self-supervised cycle network. Meanwhile, it can also produce two complementary training datasets from the unpaired LDCT and NDCT images. Second, a knowledge distillation strategy with the above two datasets is exploited to further improve the LDCT image denoising performance. To evaluate the effectiveness and feasibility of the proposed method, extensive experiments were performed on the simulated AAPM challenging and real-world clinical LDCT datasets. The qualitative and quantitative results show that the proposed SGKD achieves better performance in terms of noise suppression and detail preservation compared with some state-of-the-art network models.

Comparison of supervised-learning approaches for designing a channelized observer for image quality assessment in CT

BACKGROUND

The current paradigm for evaluating computed tomography (CT) system performance relies on a task-based approach. As the Hotelling observer (HO) provides an upper bound of observer performances in specific signal detection tasks, the literature advocates HO use for optimization purposes. However, computing the HO requires calculating the inverse of the image covariance matrix, which is often intractable in medical applications. As an alternative, dimensionality reduction has been extensively investigated to extract the task-relevant features from the raw images. This can be achieved by using channels, which yields the channelized-HO (CHO). The channels are only considered efficient when the channelized observer (CO) can approximate its unconstrained counterpart. Previous work has demonstrated that supervised learning-based methods can usually benefit CO design, either for generating efficient channels using partial least squares (PLS) or for replacing the Hotelling detector with machine-learning (ML) methods.

PURPOSE

Here we investigated the efficiency of a supervised ML-algorithm used to design a CO for predicting the performance of unconstrained HO. The ML-algorithm was applied either (1) in the estimator for dimensionality reduction, or (2) in the detector function.

METHODS

A channelized support vector machine (CSVM) was employed and compared against the CHO in terms of ability to predict HO performances. Both the CSVM and the CHO were estimated with channels derived from the singular value decomposition (SVD) of the system operator, principal component analysis (PCA), and PLS. The huge variety of regularization strategies proposed by CT system vendors for statistical image reconstruction (SIR) make the generalization capability of an observer a key point to consider upfront of implementation in clinical practice. To evaluate the generalization properties of the observers, we adopted a 2-step testing process: (1) achieved with the same regularization strategy (as in the training phase) and (2) performed using different reconstruction properties. We generated simulated- signal-known-exactly/background-known-exactly (SKE/BKE) tasks in which different noise structures were generated using Markov random field (MRF) regularizations using either a Green or a quadratic, function.

RESULTS

The CSVM outperformed the CHO for all types of channels and regularization strategies. Furthermore, even though both COs generalized well to images reconstructed with the same regularization strategy as the images considered in the training phase, the CHO failed to generalize to images reconstructed differently whereas the CSVM managed to successfully generalize. Lastly, the proposed CSVM observer used with PCA channels outperformed the CHO with PLS channels while using a smaller training data set.

CONCLUSION

These results argue for introducing the supervised-learning paradigm in the detector function rather than in the operator of the channels when designing a CO to provide an accurate estimate of HO performance. The CSVM with PCA channels proposed here could be used as a surrogate for HO in image quality assessment.

X-ray CT image denoising with MINF: A modularized iterative network framework for data from multiple dose levels

In clinical applications, multi-dose scan protocols will cause the noise levels of computed tomography (CT) images to fluctuate widely. The popular low-dose CT (LDCT) denoising network outputs denoised images through an end-to-end mapping between an LDCT image and its corresponding ground truth. The limitation of this method is that the reduced noise level of the image may not meet the diagnostic needs of doctors. To establish a denoising model adapted to the multi-noise levels robustness, we proposed a novel and efficient modularized iterative network framework (MINF) to learn the feature of the original LDCT and the outputs of the previous modules, which can be reused in each following module. The proposed network can achieve the goal of gradual denoising, outputting clinical images with different denoising levels, and providing the reviewing physicians with increased confidence in their diagnosis. Moreover, a multi-scale convolutional neural network (MCNN) module is designed to extract as much feature information as possible during the network's training. Extensive experiments on public and private clinical datasets were carried out, and comparisons with several state-of-the-art methods show that the proposed method can achieve satisfactory results for noise suppression of LDCT images. In further comparisons with modularized adaptive processing neural network (MAP-NN), the proposed network shows superior step-by-step or gradual denoising performance. Considering the high quality of gradual denoising results, the proposed method can obtain satisfactory performance in terms of image contrast and detail protection as the level of denoising increases, which shows its potential to be suitable for a multi-dose levels denoising task.

Segmentation-guided Denoising Network for Low-dose CT Imaging

BACKGROUND

To reduce radiation exposure and improve diagnosis in low-dose computed tomography, several deep learning (DL)-based image denoising methods have been proposed to suppress noise and artifacts over the past few years. However, most of them seek an objective data distribution approximating the gold standard and neglect structural semantic preservation. Moreover, the numerical response in CT images presents substantial regional anatomical differences among tissues in terms of X-ray absorbency.

METHODS

In this paper, we introduce structural semantic information for low-dose CT imaging. First, the regional segmentation prior to low-dose CT can guide the denoising process. Second the structural semantical results can be considered as evaluation metrics on the estimated normal-dose CT images. Then, a semantic feature transform is engaged to combine the semantic and image features on a semantic fusion module. In addition, the structural semantic loss function is introduced to measure the segmentation difference.

RESULTS

Experiments are conducted on clinical abdomen data obtained from a clinical hospital, and the semantic labels consist of subcutaneous fat, muscle and visceral fat associated with body physical evaluation. Compared with other DL-based methods, the proposed method achieves better performance on quantitative metrics and better semantic evaluation.

CONCLUSIONS

The quantitative experimental results demonstrate the promising performance of the proposed methods in noise reduction and structural semantic preservation. While, the proposed method may suffer from several limitations on abnormalities, unknown noise and different manufacturers. In the future, the proposed method will be further explored, and wider applications in PET/CT and PET/MR will be sought.

CCN-CL: A content-noise complementary network with contrastive learning for low-dose computed tomography denoising

In recent years, low-dose computed tomography (LDCT) has played an increasingly important role in the diagnosis CT to reduce the potential adverse effects of x-ray radiation on patients while maintaining the same diagnostic image quality. Current deep learning-based denoising methods applied to LDCT imaging only use normal dose CT (NDCT) images as positive examples to guide the denoising process. Recent studies on contrastive learning have proved that the original images as negative examples can also be helpful for network learning. Therefore, this paper proposes a novel content-noise complementary network with contrastive learning for an LDCT denoising task. First, to better train our proposed network, a contrastive learning loss, taking the NDCT image as a positive example and the original LDCT image as a negative example to guide the network learning is added. Furthermore, we also design a network structure that combines content-noise complementary learning strategy, attention mechanism, and deformable convolution for better network performance. In an evaluation study, we compare the performance of our designed network with some of the state-of-the-art methods in the 2016 NIH-AAPM-Mayo Clinic Low Dose CT Grand Challenge dataset. The quantitative and qualitative evaluation results demonstrate the feasibility and effectiveness of applying our proposed CCN-CL network model as a new deep learning-based LDCT denoising method.

Voxel-based partial volume correction of PET images via subtle MRI guided non-local means regularization

PURPOSE

Positron emission tomography (PET) images tend to be significantly degraded by the partial volume effect (PVE) resulting from the limited spatial resolution of the reconstructed images. Our purpose is to propose a partial volume correction (PVC) method to tackle this issue.

METHODS

In the present work, we explore a voxel-based PVC method under the least squares framework (LS) employing anatomical non-local means (NLMA) regularization. The well-known non-local means (NLM) filter utilizes the high degree of information redundancy that typically exists in images, and is typically used to directly reduce image noise by replacing each voxel intensity with a weighted average of its non-local neighbors. Here we explore NLM as a regularization term within iterative-deconvolution model to perform PVC. Further, an anatomical-guided version of NLM was proposed that incorporates MRI information into NLM to improve resolution and suppress image noise. The proposed approach makes subtle usage of the accompanying MRI information to define a more appropriate search space within the prior model. To optimize the regularized LS objective function, we used the Gauss-Seidel (GS) algorithm with the one-step-late (OSL) technique.

RESULTS

After the import of NLMA, the visual and quality results are all improved. With a visual check, we notice that NLMA reduce the noise compared to other PVC methods. This is also validated in bias-noise curve compared to non-MRI-guided PVC framework. We can see NLMA gives better bias-noise trade-off compared to other PVC methods.

CONCLUSIONS

Our efforts were evaluated in the base of amyloid brain PET imaging using the BrainWeb phantom and in vivo human data. We also compared our method with other PVC methods. Overall, we demonstrated the value of introducing subtle MRI-guidance in the regularization process, the proposed NLMA method resulting in promising visual as well as quantitative performance improvements.

Incorporation of residual attention modules into two neural networks for low-dose CT denoising

PURPOSE

The low-dose computed tomography (CT) imaging can reduce the damage caused by x-ray radiation to the human body. However, low-dose CT images have a different degree of artifacts than conventional CT images, and their resolution is lower than that of conventional CT images, which can affect disease diagnosis by clinicians. Therefore, methods for noise-level reduction and resolution improvement in low-dose CT images have inevitably become a research hotspot in the field of low-dose CT imaging.

METHODS

In this paper, residual attention modules (RAMs) are incorporated into the residual encoder-decoder convolutional neural network (RED-CNN) and generative adversarial network with Wasserstein distance (WGAN) to learn features that are beneficial to improving the performances of denoising networks, and developed models are denoted as RED-CNN-RAM and WGAN-RAM, respectively. In detail, RAM is composed of a multi-scale convolution module and an attention module built on the residual network architecture, where the attention module consists of a channel attention module and a spatial attention module. The residual network architecture solves the problem of network degradation with increased network depth. The function of the attention module is to learn which features are beneficial to reduce the noise level of low-dose CT images to reduce the loss of detail in the final denoising images, which is also the key point of the proposed algorithms.

RESULTS

To develop a robust network for low-dose CT image denoising, multidose-level torso phantom images provided by a cooperating equipment vendor are used to train the network, which can improve the network's adaptability to clinical application. In addition, a clinical dataset is used to test the network's migration capabilities and clinical applicability. The experimental results demonstrate that these proposed networks can effectively remove noise and artifacts from multidose CT scans. Subjective and objective analyses of multiple groups of comparison experiments show that the proposed networks achieve good noise suppression performance while preserving the image texture details.

CONCLUSION

In this study, two deep learning network models are developed using multidose-level CT images acquired from a commercial spiral CT scanner. The two network models can reduce and even remove streaking artifacts, and noise from low-dose CT images confirms the effectiveness of the proposed algorithms.

Region-Based Segmentation and Wiener Pilot-Based Novel Amoeba Denoising Scheme for CT Imaging

Computed tomography (CT) is one of the most common and beneficial medical imaging schemes, but the associated high radiation dose injurious to the patient is always a concern. Therefore, postprocessing-based enhancement of a CT reconstructed image acquired using a reduced dose is an active research area. Amoeba- (or spatially variant kernel-) based filtering is a strong candidate scheme for postprocessing of the CT image, which adapts its shape according to the image contents. In the reported research work, the amoeba filtering is customized for postprocessing of CT images acquired at a reduced X-ray dose. The proposed scheme modifies both the pilot image formation and amoeba shaping mechanism of the conventional amoeba implementation. The proposed scheme uses a Wiener filter-based pilot image, while region-based segmentation is used for amoeba shaping instead of the conventional amoeba distance-based approach. The merits of the proposed scheme include being more suitable for CT images because of the similar region-based and symmetric nature of the human body anatomy, image smoothing without compromising on the edge details, and being adaptive in nature and more robust to noise. The performance of the proposed amoeba scheme is compared to the traditional amoeba kernel in the image denoising application for CT images using filtered back projection (FBP) on sparse-view projections. The scheme is supported by computer simulations using fan-beam projections of clinically reconstructed and simulated head CT phantoms. The scheme is tested using multiple image quality matrices, in the presence of additive projection noise. The scheme implementation significantly improves the image quality visually and statistically, providing better contrast and image smoothing without compromising on edge details. Promising results indicate the efficacy of the proposed scheme.

Scatter correction based on adaptive photon path-based Monte Carlo simulation method in Multi-GPU platform

Monte Carlo (MC)-based simulation is the most precise method in scatter correction for Cone-beam CT (CBCT). Nonetheless, the existing MC methods cannot be fully applied in clinical due to its low efficiency. The traditional MC simulations perform calculations via a particle-by-particle scheme, which leads to high computation costs because abundant photons do not reach the X-ray detector in transport. The conventional approaches cannot control where the particle ends. Hence, it unavoidably waste lots of time in transporting numerous photons that have no contribution to the signal at the detector, yielding a low computational efficiency. To solve the problem, an innovative GPU-based Metropolis MC (gMMC) method was proposed. Compared with the traditional ones, the Metropolis based algorithm utilizes a path-by-path sampling method. The method can automatically control each particle path and eventually accelerate the convergence. In this paper, we firstly take planning CT image as prior information because of its precise CT value, and utilize gMMC to estimate scatter signal. Then the scatter signals are removed from the raw CBCT projections. Afterwards, FDK reconstruction is performed to obtain the corrected image,some accelerating strategies including reducing photon history number, pixels sampling, projection angles sampling and reconstructed image down-sampling achieve adaptive fast CBCT image reconstruction. For having high computational efficiency, we implemented the whole workflow on a 4-GPU workstation. In order to verify the feasibility of the the method, the experiment of several cases are conducted including simulation, phantom, and real patient cases. Results indicate that the image contrast becomes better, the scatter artifacts are eliminated. The maximum error (e_max), the minimum error (e_min), the 95th percentile error (e_95%), average error (¯e) are reduced from 264, 56, 14 and 21 HU to 28, 10, 3 and 7 HU in full-fan case, and from 387, 5, 19 and 95 HU to 39, 2, 2 and 6 HU in the half-fan case. In terms of computation time, the MC simulation time of all cases is within 2.5 seconds, and the total time is within 15 seconds.

Ordered subsets Non-Local means constrained reconstruction for sparse view cone beam CT system

Sparse-view sampling scans reduce the patient's radiation dose by reducing the total exposure duration. CT reconstructions under such scan mode are often accompanied by severe artifacts due to the high ill-posedness of the problem. In this paper, we use a Non-Local means kernel as a regularization constraint to reconstruct image volumes from sparse-angle sampled cone-beam CT scans. To overcome the huge computational cost of the 3D reconstruction, we propose a sequential update scheme relying on ordered subsets in the image domain. It is shown through experiments on simulated and real data and comparisons with other methods that the proposed approach is robust enough to deal with the number of views reduced up to 1/10. When coupled with a CUDA parallel computing technique, the computation speed of the iterative reconstruction is greatly improved.

Tensor decomposition and non-local means based spectral CT image denoising

BACKGROUNDAs one type of the state-of-the-art detectors, photon counting detectors are used in spectral computed tomography (CT) to classify the received photons into several energy channels and generate multichannel projections simultaneously. However, FBP reconstructed images contain severe noise due to the low photon counts in each energy channel.OBJECTIVEA spectral CT image denoising method based on tensor-decomposition and non-local means (TDNLM) is proposed.METHODSIn a CT image, it is widely accepted that there exists self-similarity over the spatial domain. In addition, because a multichannel CT image is obtained from the same object at different energies, images among different channels are highly correlated. Motivated by these two characteristics of the spectral CT images, tensor decomposition and non-local means are employed to recover fine structures in spectral CT images. Moreover, images in all energy channels are added together to form a high signal-to-noise ratio image, which is applied to encourage the signal preservation of the TDNLM. The combination of TD, NLM and the guidance of a high-quality image enhances the low-dose spectral CT, and a parameter selection strategy is designed to achieve the optimal image quality.RESULTSThe effectiveness of the developed algorithm is validated on both numerical simulations and realistic preclinical applications. The root mean square error (RMSE) and the structural similarity (SSIM) are used to quantitatively assess the image quality. The proposed method successfully restored high-quality images (average RMSE=0.0217 cm-1 and SSIM=0.987) from noisy spectral CT images (average RMSE=0.225 cm-1 and SSIM=0.633). In addition, RMSE of each decomposed material component is also remarkably reduced. Compared to the state-of-the-art iterative spectral CT reconstruction algorithms, the proposed method achieves comparable performance with dramatically reduced computational cost, resulting in a speedup of >50.CONCLUSIONSThe outstanding denoising performance, the high computational efficiency and the adaptive parameter selection strategy make the proposed method practical for spectral CT applications.

Projection data smoothing through noise-level weighted total variation regularization for low-dose computed tomography

Reducing radiation dose while maintaining the quality of the reconstructed images is a major challenge in the computed tomography (CT) community. In light of the non-stationary Gaussian noise distribution, we developed a model that incorporates a noise-level weighted total variation (NWTV) regularization term for denoising the projection data. Contrary to the well-known edge-weighted total variation method, which aims for better edge preserving, the proposed NWTV tries to adapt the regularization with the spatially varying noise levels. Experiments on simulated data as well as the real imaging data suggest that the proposed NWTV regularization could achieve quite competitive results. For sinograms with sharp edges, the NWTV could do a better job at balancing noise reduction and edge preserving, such that noise is removed in a more uniform manner. Another conclusion from our experiments is that the well-recognized stair-casing artifacts of TV regularization play little role in the reconstructed images when the NWTV method is applied to low-dose CT imaging data.

Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network

Low-dose computed tomography (LDCT) has offered tremendous benefits in radiation-restricted applications, but the quantum noise as resulted by the insufficient number of photons could potentially harm the diagnostic performance. Current image-based denoising methods tend to produce a blur effect on the final reconstructed results especially in high noise levels. In this paper, a deep learning-based approach was proposed to mitigate this problem. An adversarially trained network and a sharpness detection network were trained to guide the training process. Experiments on both simulated and real dataset show that the results of the proposed method have very small resolution loss and achieves better performance relative to state-of-the-art methods both quantitatively and visually.

Regularization strategies in statistical image reconstruction of low-dose x-ray CT: A review

Statistical image reconstruction (SIR) methods have shown potential to substantially improve the image quality of low-dose x-ray computed tomography (CT) as compared to the conventional filtered back-projection (FBP) method. According to the maximum a posteriori (MAP) estimation, the SIR methods are typically formulated by an objective function consisting of two terms: (a) a data-fidelity term that models imaging geometry and physical detection processes in projection data acquisition, and (b) a regularization term that reflects prior knowledge or expectations of the characteristics of the to-be-reconstructed image. SIR desires accurate system modeling of data acquisition, while the regularization term also has a strong influence on the quality of reconstructed images. A variety of regularization strategies have been proposed for SIR in the past decades, based on different assumptions, models, and prior knowledge. In this paper, we review the conceptual and mathematical bases of these regularization strategies and briefly illustrate their efficacies in SIR of low-dose CT.

Assessment of prior image induced nonlocal means regularization for low-dose CT reconstruction: Change in anatomy

PURPOSE

Repeated computed tomography (CT) scans are prescribed for some clinical applications such as lung nodule surveillance. Several studies have demonstrated that incorporating a high-quality prior image into the reconstruction of subsequent low-dose CT (LDCT) acquisitions can either improve image quality or reduce data fidelity requirements. Our proposed previous normal-dose image induced nonlocal means (ndiNLM) regularization method for LDCT is an example of such a method. However, one major concern with prior image based methods is that they might produce false information when the prior image and the current LDCT image show different structures (for example, if a lung nodule emerges, grows, shrinks, or disappears over time). This study aims to assess the performance of the ndiNLM regularization method in situations with change in anatomy.

METHOD

We incorporated the ndiNLM regularization into the statistical image reconstruction (SIR) framework for reconstruction of subsequent LDCT images. Because of its patch-based search mechanism, a rough registration between the prior image and the current LDCT image is adequate for the SIR-ndiNLM method. We assessed the performance of the SIR-ndiNLM method in lung nodule surveillance for two different scenarios: (a) the nodule was not found in a baseline exam but appears in a follow-up LDCT scan; (b) the nodule was present in a baseline exam but disappears in a follow-up LDCT scan. We further investigated the effect of nodule size on the performance of the SIR-ndiNLM method.

RESULTS

We found that a relatively large search-window (e.g., 33 × 33) should be used for the SIR-ndiNLM method to account for misalignment between the prior image and the current LDCT image, and to ensure that enough similar patches can be found in the prior image. With proper selection of other parameters, experimental results with two patient datasets demonstrated that the SIR-ndiNLM method did not miss true nodules nor introduce false nodules in the lung nodule surveillance scenarios described above. We also found that the SIR-ndiNLM reconstruction shows improved image quality when the prior image is similar to the current LDCT image in anatomy. These gains in image quality might appear small upon visual inspection, but they can be detected using quantitative measures. Finally, the SIR-ndiNLM method also performed well in ultra-low-dose conditions and with different nodule sizes.

CONCLUSIONS

This study assessed the performance of the SIR-ndiNLM method in situations in which the prior image and the current LDCT image show substantial anatomical differences, specifically, changes in lung nodules. The experimental results demonstrate that the SIR-ndiNLM method does not introduce false lung nodules nor miss true nodules, which relieves the concern that this method might produce false information. However, there is insufficient evidence that these findings will hold true for all kinds of anatomical changes.

MULTI-ENERGY CONE-BEAM CT RECONSTRUCTION WITH A SPATIAL SPECTRAL NONLOCAL MEANS ALGORITHM

Multi-energy computed tomography (CT) is an emerging medical image modality with a number of potential applications in diagnosis and therapy. However, high system cost and technical barriers obstruct its step into routine clinical practice. In this study, we propose a framework to realize multi-energy cone beam CT (ME-CBCT) on the CBCT system that is widely available and has been routinely used for radiotherapy image guidance. In our method, a kVp switching technique is realized, which acquires x-ray projections with kVp levels cycling through a number of values. For this kVp-switching based ME-CBCT acquisition, x-ray projections of each energy channel are only a subset of all the acquired projections. This leads to an undersampling issue, posing challenges to the reconstruction problem. We propose a spatial spectral non-local means (ssNLM) method to reconstruct ME-CBCT, which employs image correlations along both spatial and spectral directions to suppress noisy and streak artifacts. To address the intensity scale difference at different energy channels, a histogram matching method is incorporated. Our method is different from conventionally used NLM methods in that spectral dimension is included, which helps to effectively remove streak artifacts appearing at different directions in images with different energy channels. Convergence analysis of our algorithm is provided. A comprehensive set of simulation and real experimental studies demonstrate feasibility of our ME-CBCT scheme and the capability of achieving superior image quality compared to conventional filtered backprojection-type (FBP) and NLM reconstruction methods.

Nonlocal low-rank and sparse matrix decomposition for spectral CT reconstruction

Spectral computed tomography (CT) has been a promising technique in research and clinic because of its ability to produce improved energy resolution images with narrow energy bins. However, the narrow energy bin image is often affected by serious quantum noise because of the limited number of photons used in the corresponding energy bin. To address this problem, we present an iterative reconstruction method for spectral CT using nonlocal low-rank and sparse matrix decomposition (NLSMD), which exploits the self-similarity of patches that are collected in multi-energy images. Specifically, each set of patches can be decomposed into a low-rank component and a sparse component, and the low-rank component represents the stationary background over different energy bins, while the sparse component represents the rest of different spectral features in individual energy bins. Subsequently, an effective alternating optimization algorithm was developed to minimize the associated objective function. To validate and evaluate the NLSMD method, qualitative and quantitative studies were conducted by using simulated and real spectral CT data. Experimental results show that the NLSMD method improves spectral CT images in terms of noise reduction, artifacts suppression and resolution preservation.

Joint regularization-based image reconstruction by combining data-driven tight frame and total variation for low-dose computed tomography

Since the excessive radiation dose may induce potential body lesion, the low-dose computed tomography (LDCT) is widely applied for clinical diagnosis and treatment. However, the dose reduction will inevitably cause severe noise and degrade image quality. Most state-of-the-art methods utilize a pre-determined regularizer to account for the prior images, which may be insufficient for the most images acquired in the clinical practice. This study proposed and investigated a joint regularization method combining a data-driven tight frame and total variation (DDTF-TV) to solve this problem. Unlike the existing methods that designed pre-determined sparse transform for image domain, data-driven regularizer introduced a learning strategy to adaptively and iteratively update the framelets of DDTF, which can preferably recover the detailed image structures. The other regularizer, TV term can reconstruct strong edges and suppress noise. The joint term, DDTF-TV, collaboratively affect detail preservation and noise suppression. The proposed new model was efficiently solved by alternating the direction method of the multipliers. Qualitative and quantitative evaluations were carried out in simulation and real data experiments to demonstrate superiority of the proposed DDTF-TV method. Both visual inspection and numerical accuracy analysis show the potential of the proposed method for improving image quality of the LDCT.

Discriminative Feature Representation to Improve Projection Data Inconsistency for Low Dose CT Imaging

In low dose computed tomography (LDCT) imaging, the data inconsistency of measured noisy projections can significantly deteriorate reconstruction images. To deal with this problem, we propose here a new sinogram restoration approach, the sinogram- discriminative feature representation (S-DFR) method. Different from other sinogram restoration methods, the proposed method works through a 3-D representation-based feature decomposition of the projected attenuation component and the noise component using a well-designed composite dictionary containing atoms with discriminative features. This method can be easily implemented with good robustness in parameter setting. Its comparison to other competing methods through experiments on simulated and real data demonstrated that the S-DFR method offers a sound alternative in LDCT.

Iterative reconstruction for dual energy CT with an average image-induced nonlocal means regularization

Reducing radiation dose in dual energy computed tomography (DECT) is highly desirable but it may lead to excessive noise in the filtered backprojection (FBP) reconstructed DECT images, which can inevitably increase the diagnostic uncertainty. To obtain clinically acceptable DECT images from low-mAs acquisitions, in this work we develop a novel scheme based on measurement of DECT data. In this scheme, inspired by the success of edge-preserving non-local means (NLM) filtering in CT imaging and the intrinsic characteristics underlying DECT images, i.e. global correlation and non-local similarity, an averaged image induced NLM-based (aviNLM) regularization is incorporated into the penalized weighted least-squares (PWLS) framework. Specifically, the presented NLM-based regularization is designed by averaging the acquired DECT images, which takes the image similarity within the two energies into consideration. In addition, the weighted least-squares term takes into account DECT data-dependent variance. For simplicity, the presented scheme was termed as 'PWLS-aviNLM'. The performance of the presented PWLS-aviNLM algorithm was validated and evaluated on digital phantom, physical phantom and patient data. The extensive experiments validated that the presented PWLS-aviNLM algorithm outperforms the FBP, PWLS-TV and PWLS-NLM algorithms quantitatively. More importantly, it delivers the best qualitative results with the finest details and the fewest noise-induced artifacts, due to the aviNLM regularization learned from DECT images. This study demonstrated the feasibility and efficacy of the presented PWLS-aviNLM algorithm to improve the DECT reconstruction and resulting material decomposition.

Applications of nonlocal means algorithm in low-dose X-ray CT image processing and reconstruction: A review

Low-dose X-ray computed tomography (LDCT) imaging is highly recommended for use in the clinic because of growing concerns over excessive radiation exposure. However, the CT images reconstructed by the conventional filtered back-projection (FBP) method from low-dose acquisitions may be severely degraded with noise and streak artifacts due to excessive X-ray quantum noise, or with view-aliasing artifacts due to insufficient angular sampling. In 2005, the nonlocal means (NLM) algorithm was introduced as a non-iterative edge-preserving filter to denoise natural images corrupted by additive Gaussian noise, and showed superior performance. It has since been adapted and applied to many other image types and various inverse problems. This paper specifically reviews the applications of the NLM algorithm in LDCT image processing and reconstruction, and explicitly demonstrates its improving effects on the reconstructed CT image quality from low-dose acquisitions. The effectiveness of these applications on LDCT and their relative performance are described in detail.

Iterative reconstruction for CT perfusion with a prior-image induced hybrid nonlocal means regularization: Phantom studies

PURPOSE

In computed tomography perfusion (CTP) imaging, an initial phase CT acquired with a high-dose protocol can be used to improve the image quality of later phase CT acquired with a low-dose protocol. For dynamic regions, signals in the later low-dose CT may not be completely recovered if the initial CT heavily regularizes the iterative reconstruction process. The authors propose a hybrid nonlocal means (hNLM) regularization model for iterative reconstruction of low-dose CTP to overcome the limitation of the conventional prior-image induced penalty.

METHODS

The hybrid penalty was constructed by combining the NLM of the initial phase high-dose CT in the stationary region and later phase low-dose CT in the dynamic region. The stationary and dynamic regions were determined by the similarity between the initial high-dose scan and later low-dose scan. The similarity was defined as a Gaussian kernel-based distance between the patch-window of the same pixel in the two scans, and its measurement was then used to weigh the influence of the initial high-dose CT. For regions with high similarity (e.g., stationary region), initial high-dose CT played a dominant role for regularizing the solution. For regions with low similarity (e.g., dynamic region), the regularization relied on a low-dose scan itself. This new hNLM penalty was incorporated into the penalized weighted least-squares (PWLS) for CTP reconstruction. Digital and physical phantom studies were performed to evaluate the PWLS-hNLM algorithm.

RESULTS

Both phantom studies showed that the PWLS-hNLM algorithm is superior to the conventional prior-image induced penalty term without considering the signal changes within the dynamic region. In the dynamic region of the Catphan phantom, the reconstruction error measured by root mean square error was reduced by 42.9% in PWLS-hNLM reconstructed image.

CONCLUSIONS

The PWLS-hNLM algorithm can effectively use the initial high-dose CT to reconstruct low-dose CTP in the stationary region while reducing its influence in the dynamic region.

Penalized weighted least-squares approach for multienergy computed tomography image reconstruction via structure tensor total variation regularization

Multienergy computed tomography (MECT) allows identifying and differentiating different materials through simultaneous capture of multiple sets of energy-selective data belonging to specific energy windows. However, because sufficient photon counts are not available in each energy window compared with that in the whole energy window, the MECT images reconstructed by the analytical approach often suffer from poor signal-to-noise and strong streak artifacts. To address the particular challenge, this work presents a penalized weighted least-squares (PWLS) scheme by incorporating the new concept of structure tensor total variation (STV) regularization, which is henceforth referred to as 'PWLS-STV' for simplicity. Specifically, the STV regularization is derived by penalizing higher-order derivatives of the desired MECT images. Thus it could provide more robust measures of image variation, which can eliminate the patchy artifacts often observed in total variation (TV) regularization. Subsequently, an alternating optimization algorithm was adopted to minimize the objective function. Extensive experiments with a digital XCAT phantom and meat specimen clearly demonstrate that the present PWLS-STV algorithm can achieve more gains than the existing TV-based algorithms and the conventional filtered backpeojection (FBP) algorithm in terms of both quantitative and visual quality evaluations.

Patch-based models and algorithms for image processing: a review of the basic principles and methods, and their application in computed tomography

PURPOSE

Image models are central to all image processing tasks. The great advancements in digital image processing would not have been made possible without powerful models which, themselves, have evolved over time. In the past decade, "patch-based" models have emerged as one of the most effective models for natural images. Patch-based methods have outperformed other competing methods in many image processing tasks. These developments have come at a time when greater availability of powerful computational resources and growing concerns over the health risks of the ionizing radiation encourage research on image processing algorithms for computed tomography (CT). The goal of this paper is to explain the principles of patch-based methods and to review some of their recent applications in CT.

METHODS

We first review the central concepts in patch-based image processing and explain some of the state-of-the-art algorithms, with a focus on aspects that are more relevant to CT. Then, we review some of the recent application of patch-based methods in CT.

RESULTS

Patch-based methods have already transformed the field of image processing, leading to state-of-the-art results in many applications. More recently, several studies have proposed patch-based algorithms for various image processing tasks in CT, from denoising and restoration to iterative reconstruction. Although these studies have reported good results, the true potential of patch-based methods for CT has not been yet appreciated.

CONCLUSIONS

Patch-based methods can play a central role in image reconstruction and processing for CT. They have the potential to lead to substantial improvements in the current state of the art.

Low-dose CT statistical iterative reconstruction via modified MRF regularization

It is desirable to reduce the excessive radiation exposure to patients in repeated medical CT applications. One of the most effective ways is to reduce the X-ray tube current (mAs) or tube voltage (kVp). However, it is difficult to achieve accurate reconstruction from the noisy measurements. Compared with the conventional filtered back-projection (FBP) algorithm leading to the excessive noise in the reconstructed images, the approaches using statistical iterative reconstruction (SIR) with low mAs show greater image quality. To eliminate the undesired artifacts and improve reconstruction quality, we proposed, in this work, an improved SIR algorithm for low-dose CT reconstruction, constrained by a modified Markov random field (MRF) regularization. Specifically, the edge-preserving total generalized variation (TGV), which is a generalization of total variation (TV) and can measure image characteristics up to a certain degree of differentiation, was introduced to modify the MRF regularization. In addition, a modified alternating iterative algorithm was utilized to optimize the cost function. Experimental results demonstrated that images reconstructed by the proposed method could not only generate high accuracy and resolution properties, but also ensure a higher peak signal-to-noise ratio (PSNR) in comparison with those using existing methods.

Statistical image reconstruction for low-dose CT using nonlocal means-based regularization. Part II: An adaptive approach

To reduce radiation dose in X-ray computed tomography (CT) imaging, one common strategy is to lower the tube current and exposure time settings during projection data acquisition. However, this strategy would inevitably increase the projection data noise, and the resulting image by the conventional filtered back-projection (FBP) method may suffer from excessive noise and streak artifacts. The well-known edge-preserving nonlocal means (NLM) filtering can reduce the noise-induced artifacts in the FBP reconstructed image, but it sometimes cannot completely eliminate the artifacts, especially under the very low-dose circumstance when the image is severely degraded. Instead of taking NLM filtering, we proposed a NLM-regularized statistical image reconstruction scheme, which can effectively suppress the noise-induced artifacts and significantly improve the reconstructed image quality. From our previous investigation on NLM-based strategy, we noted that using a spatially invariant filtering parameter in the regularization was rarely optimal for the entire field of view (FOV). Therefore, in this study we developed a novel strategy for designing spatially variant filtering parameters which are adaptive to the local characteristics of the image to be reconstructed. This adaptive NLM-regularized statistical image reconstruction method was evaluated with low-contrast phantoms and clinical patient data to show (1) the necessity in introducing the spatial adaptivity and (2) the efficacy of the adaptivity in achieving superiority in reconstructing CT images from low-dose acquisitions.