Iterative CT Reconstruction Research Articles

Combining dual-tree complex wavelets and multiresolution in iterative CT reconstruction with application to metal artifact reduction

BackgroundThis paper investigates the benefits of data filtering via complex dual wavelet transform for metal artifact reduction (MAR). The advantage of using complex dual wavelet basis for MAR was studied on simulated dental computed tomography (CT) data for its efficiency in terms of noise suppression and removal of secondary artifacts. Dual-tree complex wavelet transform (DT-CWT) was selected due to its enhanced directional analysis of image details compared to the ordinary wavelet transform. DT-CWT was used for multiresolution decomposition within a modified total variation (TV) regularized inversion algorithm.MethodsIn this study, we have tested the multiresolution TV (MRTV) approach with DT-CWT on a 2D polychromatic jaw phantom model with Gaussian and Poisson noise. High noise and sparse measurement settings were used to assess the performance of DT-CWT. The results were compared to the outcome of the single-resolution reconstruction and filtered back-projection (FBP) techniques as well as reconstructions with Haar wavelet basis.ResultsThe results indicate that filtering of wavelet coefficients with DT-CWT effectively removes the noise without introducing new artifacts after inpainting. Furthermore, adoption of multiple resolution levels yield to a more robust algorithm compared to varying the regularization strength.ConclusionsThe multiresolution reconstruction with DT-CWT is also more robust when reconstructing the data with sparse projections compared to the single-resolution approach and Haar wavelets.

Comparison of different iterative CT reconstruction techniques and filtered back projection for assessment of the medial clavicular epiphysis in forensic age estimation

To assess the impact of iterative reconstruction and filtered back projection (FBP) on image quality in computed tomography (CT)-based forensic age estimation of the medial clavicular epiphysis. CT of the clavicle was performed in 19 patients due to forensic reasons (70 mAs/140 kVp). Raw data were reconstructed with FBP and with an iterative algorithm at level 4 and 6. Clavicular ossification stage was determined by two radiologists in consensus, firstly on FBP reconstructed images and secondly after reviewing all reconstructions including iDose 4 and 6. In addition, the 3 reconstructions were compared regarding artefacts and delineation of the meta-/epiphyseal interface. Quantitative image noise was measured. Quantitative noise was lower in iDose 6 reconstructed images than in FBP (P < 0.042), but not significantly lower between iDose 4 and FBP (P = 0.127). Side by side comparison revealed lesser qualitative image noise on both iDose reconstructed images than for FBP. The meta-/epiphyseal interface delineation was rated better on both iDose levels than with FBP. In 3 of 19 patients, the clavicular ossification stage was reclassified after iterative reconstructions had been additionally reviewed. Using iterative CT reconstruction algorithms, a reduction of image noise and an enhancement of image quality regarding the meta-/epiphyseal clavicular interface can be achieved. The study highlights the importance of image standardization as variation of reconstruction technique has impact on forensic age estimation.

Sparse-view helical CT reconstruction based on tensor total generalized variation minimization

We propose a sparse-view helical CT iterative reconstruction algorithm based on projection of convex set tensor total generalized variation minimization (TTGV-POCS) to reduce the X-ray dose of helical CT scanning. The three-dimensional volume data of helical CT reconstruction was viewed as the third-order tensor. The tensor generalized total variation (TTGV) was used to describe the structural sparsity of the three-dimensional image. The POCS iterative reconstruction framework was adopted to achieve a robust result of sparse-view helical CT reconstruction. The TTGV-POCS algorithm fully used the structural sparsity of first-order and second-order derivation and the correlation between the slices of helical CT image data to effectively suppress artifacts and noise in the image of sparse-view reconstruction and better preserve image edge information. The experimental results of XCAT phantom and patient scan data showed that the TTGVPOCS algorithm had better performance in reducing noise, removing artifacts and maintaining edges than the existing reconstruction algorithms. Comparison of the sparse-view reconstruction results of XCAT phantom data with 144 exposure views showed that the TTGV-POCS algorithm proposed herein increased the PSNR quantitative index by 9.17%-15.24% compared with the experimental comparison algorithm; the FSIM quantitative index was increased by 1.27%-9.30%. The TTGV-POCS algorithm can effectively improve the image quality of helical CT sparse-view reconstruction and reduce the radiation dose of helical CT examination to improve the clinical imaging diagnosis.

State of the Art in Abdominal CT: The Limits of Iterative Reconstruction Algorithms.

The development and widespread adoption of iterative reconstruction (IR) algorithms for CT have greatly facilitated the contemporary practice of radiation dose reduction during abdominal CT examinations. IR mitigates the increased image noise typically associated with reduced radiation dose levels, thereby maintaining subjective image quality and diagnostic confidence for a variety of clinical tasks. Mounting evidence, however, points to important limitations of this method involving radiologists' ability to perform low-contrast diagnostic tasks, such as the detection of liver metastases or pancreatic masses. Radiologists need to be aware that use of IR can result in a decline of spatial resolution for low-contrast structures and degradation of low-contrast detectability when radiation dose reductions exceed approximately 25%. This article will review the principles of IR algorithm technology, describe the various commercial implementations of IR in CT, and review published studies that have evaluated the ability of IR to preserve diagnostic performance for low-contrast diagnostic tasks. In addition, future developments in CT noise reduction techniques and methods to rigorously evaluate their diagnostic performance will be discussed.

Pediatric head computed tomography with advanced modeled iterative reconstruction: focus on image quality and reduction of radiation dose.

Iterative reconstruction has become the standard method for reconstructing computed tomography (CT) scans and needs to be verified for adaptation. To assess the image quality after adapting advanced modeled iterative reconstruction (ADMIRE) for pediatric head CT. We included image sets with filtered back projection reconstruction (the cFBP group, n=105) and both filtered back projection and ADMIRE reconstruction (the lower-dose group, n=109) after dose reduction. All five strength levels of ADMIRE and filtered back projection were adapted for the lower-dose group and compared with the cFBP group. Quantitative parameters including noise, signal-to-noise ratio and contrast-to-noise ratio and qualitative parameters including noise, white matter and gray matter differentiation of the supra- and infratentorial levels, sharpness, artifact, and diagnostic accuracy were also evaluated and compared with interobserver agreement. There was a mean dose reduction of 30.6% in CT dose index volume, 32.1% in dose length product, and 32.1% in effective dose after tube current reduction. There was gradual reduction of noise in air, cerebrospinal fluid and white matter with strength levels of ADMIRE from 1 to 5 (P<0.001). Signal-to-noise ratio and contrast-to-noise ratio in all age groups increased among strength levels of ADMIRE, in sequence from 1 to 5, with statistical significance (P<0.001). Gradual reduction of qualitative parameters was noted among strength levels of ADMIRE in sequence from 1 to 5 (P<0.001). Use of ADMIRE for pediatric head CT can reduce radiation dose without degrading image quality.

Unintended Consequences: Review of New Artifacts Introduced by Iterative Reconstruction CT Metal Artifact Reduction in Spine Imaging.

Metal hardware serves as a common artifact source in spine CT imaging in the form of beam-hardening, photon starvation, and streaking. Postprocessing metal artifact reduction techniques have been developed to decrease these artifacts, which has been proved to improve visualization of soft-tissue structures and increase diagnostic confidence. However, metal artifact reduction reconstruction introduces its own novel artifacts that can mimic pathology.

CT iterative reconstruction algorithms: a task-based image quality assessment.

To assess the dose performance in terms of image quality of filtered back projection (FBP) and two generations of iterative reconstruction (IR) algorithms developed by the most common CT vendors. We used four CT systems equipped with a hybrid/statistical IR (H/SIR) and a full/partial/advanced model-based IR (MBIR) algorithms. Acquisitions were performed on an ACR phantom at five dose levels. Raw data were reconstructed using a standard soft tissue kernel for FBP and one iterative level of the two IR algorithm generations. The noise power spectrum (NPS) and the task-based transfer function (TTF) were computed. A detectability index (d') was computed to model the detection task of a large mass in the liver (large feature; 120HU and 25-mm diameter) and a small calcification (small feature; 500HU and 1.5-mm diameter). With H/SIR, the highest values of d' for both features were found for Siemens, then for Canon and the lowest values for Philips and GE. For the large feature, potential dose reductions with MBIR compared with H/SIR were - 35% for GE, - 62% for Philips, and - 13% for Siemens; for the small feature, corresponding reductions were - 45%, - 78%, and - 14%, respectively. With the Canon system, a potential dose reduction of - 32% was observed only for the small feature with MBIR compared with the H/SIR algorithm. For the large feature, the dose increased by 100%. This multivendor comparison of several versions of IR algorithms allowed to compare the different evolution within each vendor. The use of d' is highly adapted and robust for an optimization process. • The performance of four CT systems was evaluated by using imQuest software to assess noise characteristic, spatial resolution, and lesion detection. • Two task functions were defined to model the detection task of a large mass in the liver and a small calcification. • The advantage of task-based image quality assessment for radiologists is that it does not include only complicated metrics, but also clinically meaningful image quality.

Iterative image reconstruction for sparse-view CT via total variation regularization and dictionary learning.

Recently, low-dose computed tomography (CT) has become highly desirable due to the increasing attention paid to the potential risks of excessive radiation of the regular dose CT. However, ensuring image quality while reducing the radiation dose in the low-dose CT imaging is a major challenge. Compared to classical filtered back-projection (FBP) algorithms, statistical iterative reconstruction (SIR) methods for modeling measurement statistics and imaging geometry can significantly reduce the radiation dose, while maintaining the image quality in a variety of CT applications. To facilitate low-dose CT imaging, we in this study proposed an improved statistical iterative reconstruction scheme based on the penalized weighted least squares (PWLS) standard combined with total variation (TV) minimization and sparse dictionary learning (DL), which is named as a method of PWLS-TV-DL. To evaluate this PWLS-TV-DL method, we performed experiments on digital phantoms and physical phantoms, and analyzed the results in terms of image quality and calculation. The results show that the proposed method is better than the comparison methods, which indicates the potential of applying this PWLS-TV-DL method to reconstruct low-dose CT images.

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.

A fast regularized iterative algorithm for fan-beam CT reconstruction

We propose a fast iterative image reconstruction algorithm for normal, short-scan, and super-short-scan fan-beam computed tomography (CT), which aims at iterative reconstruction for low-dose and few-view CT by minimizing a data-fidelity term regularized with a total variation (TV) penalty. The derivation of the algorithm can be outlined as follows. First, the original minimization problem is formulated into a saddle-point (primal-dual) problem by using the Lagrangian duality, to which we apply the alternating projection proximal (APP) algorithm, which belongs to a class of first-order primal-dual methods. Second, we precondition the iterative formula using the modified ramp filter of the filtered back-projection (FBP) reconstruction algorithm in such a way that the solution to this preconditioned iteration perfectly coincides with the solution to the original problem. The resulting algorithm converges quickly to the minimizer of the cost function. To demonstrate the advantages of our method, we perform reconstruction experiments using projection data from both numerical phantoms and real CT data. Both qualitative and quantitative results are presented.

A new in-line X-ray phase-contrast computed tomography reconstruction algorithm based on adaptive-weighted anisotropic TpV regularization for insufficient data.

In-line X-ray phase-contrast computed tomography (IL-PCCT) is a valuable tool for revealing the internal detailed structures in weakly absorbing objects (e.g. biological soft tissues), and has a great potential to become clinically applicable. However, the long scanning time for IL-PCCT will result in a high radiation dose to biological samples, and thus impede the wider use of IL-PCCT in clinical and biomedical imaging. To alleviate this problem, a new iterative CT reconstruction algorithm is presented that aims to decrease the radiation dose by reducing the projection views, while maintaining the high quality of reconstructed images. The proposed algorithm combines the adaptive-weighted anisotropic total p-variation (AwaTpV, 0 < p < 1) regularization technique with projection onto convex sets (POCS) strategy. Noteworthy, the AwaTpV regularization term not only contains the horizontal and vertical image gradients but also adds the diagonal image gradients in order to enforce the directional continuity in the gradient domain. To evaluate the effectiveness and ability of the proposed algorithm, experiments with a numerical phantom and synchrotron IL-PCCT were performed, respectively. The results demonstrated that the proposed algorithm had the ability to significantly reduce the artefacts caused by insufficient data and effectively preserved the edge details under noise-free and noisy conditions, and thus could be used as an effective approach to decrease the radiation dose for IL-PCCT.

Iterative CT reconstruction in abdominal low-dose CT used for hybrid SPECT-CT applications: effect on image quality, image noise, detectability, and reader's confidence.

BackgroundIterative computed tomography (CT) image reconstruction shows high potential for the preservation of image quality in diagnostic CT while reducing patients’ exposure; it has become available for low-dose CT (LD-CT) in high-end hybrid imaging systems (e.g. single-photon emission computed tomography [SPECT]-CT).PurposeTo examine the effect of an iterative CT reconstruction algorithm on image quality, image noise, detectability, and the reader’s confidence for LD-CT data by a subjective assessment.Material and MethodsThe LD-CT data were validated for 40 patients examined by an abdominal hybrid SPECT-CT (U = 120 kV, I = 40 mA, pitch = 1.375). LD-CT was reconstructed using either filtered back projection (FBP) or an iterative image reconstruction algorithm (Adaptive Statistical Iterative Reconstruction [ASIR]®) with different parameters (ASIR levels 50% and 100%). The data were validated by two independent blinded readers using a scoring system for image quality, image noise, detectability, and reader confidence, for a predefined set of 16 anatomic substructures.ResultsThe image quality was significantly improved by iterative reconstruction of the LD-CT data compared with FBP (P ≤ 0.0001). While detectability increased in only 2/16 structures (P ≤ 0.03), the reader’s confidence increased significantly due to iterative reconstruction (P ≤ 0.002). Meanwhile, at the ASIR level of 100%, the detectability in bone structure was highly reduced (P = 0.003).ConclusionAn ASIR level of 50% represents a good compromise in abdominal LD-CT image reconstruction. The specific ASIR level improved image quality (reduced image noise) and reader confidence, while preserving detectability of bone structure.

Effect of iterative sparse-view CT reconstruction with task-specific projection angles on dimensional measurements

X-ray computed tomography based on a small number of radiographic projections (sparse-view CT) is relevant for several application cases in industry, where reducing the measurement time plays a major role (e.g. for in-line CT). Because of low data quality of sparse-view CT scans due to insufficient sampling, new concepts are needed to reduce measurement uncertainties for dimensional metrology. Iterative image reconstruction techniques provide a promising opportunity for this purpose as they are in principle able to handle limited data or noise well and give the possibility to select specific projection angles (i.e. perspective views) for circular scan trajectories. In this paper, the influence of task-specific projection angles on dimensional measurements is discussed using algebraic and statistical iterative reconstruction of simulated and experimentally obtained sparse-view scans. It is shown that measurement deviations for specific dimensional measurands can be reduced by selecting projection angles which are expected to have a high contribution to a good imaging of relevant geometric features.

Full model-based iterative reconstruction (MBIR) in abdominal CT increases objective image quality, but decreases subjective acceptance.

Evaluate and compare the image quality and acceptance of a full MBIR algorithm to that of an earlier full IR hybrid algorithm and filtered back projection (FBP). Acquisitions were performed with a 320 detector-row CT scanner with seven different dose levels. Images were reconstructed with three algorithms: FBP, full hybrid iterative reconstruction (HIR), and a full model-based iterative reconstruction algorithm (full MBIR). The sensitometry, spatial resolution, image texture, and low-contrast detectability of these algorithms were compared. Subjective analysis of low-contrast detectability was performed. Ten radiologists answered a questionnaire on image quality and confidence in full MBIR images in clinical practice. The contrast-to-noise ratio of full MBIR was significantly higher than in the other algorithms (p < 0.0015). The spatial resolution was also higher with full MBIR at high frequencies (> 0.3lp/mm). Full MBIR at low dose levels led to better low-contrast detectability and more inserts being identified with a higher confidence (p < 0.0001). Full MBIR was associated with a change in image texture compared to HIR and FBP. Eighty percent of radiologists judged general appearance and texture of full MBIR images worse than HIR. Moreover, compared with HIR, for 50% of radiologists, the diagnostic confidence on full MBIR images was worse. Questionnaire reliability was considered acceptable (Cronbach alpha 0.7). Compared to conventional iterative reconstruction algorithms, full MBMIR presented a higher image quality and low-contrast detectability and a worse acceptance among radiologists. • Full MBIR used led to an overall improvement in image quality compared with FBP and HIR. • Full MBIR leads to image texture change which reduces the confidence in these images among radiologists. • Awareness of the image texture change and improved quality of full MBIR reconstructed images could improve the acceptance of this technique in clinical practice.

The Application of a New Model-Based Iterative Reconstruction in Low-Dose Upper Abdominal CT

To compare upper abdominal computed tomography (CT) image quality of new model-based iterative reconstruction (MBIR) with low-contrast resolution preference (MBIRNR40), conventional MBIR (MBIRc), and adaptive statistical iterative reconstruction (ASIR) at low dose with ASIR at routine-dose. Study included phantom and 60 patients who had initial and follow-up CT scans. For patients, the delay phase was acquired at routine-dose (noise index = 10 HU) for the initial scan and low dose (noise index = 20 HU) for the follow-up. The low-dose CT was reconstructed with 40% and 60% ASIR, MBIRc, and MBIRNR40, while routine-dose CT was reconstructed with 40% ASIR. CT value and noise measurements of the subcutaneous fat, back muscle, liver, and spleen parenchyma were compared using one-way ANOVA. Two radiologists used semiquantitative 7-scale (-3 to +3) to rate image quality and artifacts. The phantom study revealed superior low-contrast resolution with MBIRNR40. For patient scans, the CT dose index for the low-dose CT was 3.00 ± 1.32 mGy, 75% lower than the 11.90 ± 4.75 mGy for the routine-dose CT. Image noise for the low-dose MBIRNR40 images was significantly lower than the low-dose MBIRc and ASIR images, and routine-dose ASIR images (p < 0.05). Subjective ratings showed higher image quality for low-dose MBIRNR40, with lower noise, better low-contrast resolution for abdominal structures, and finer lesion contours than those of low-dose MBIRc and ASIR images, and routine-dose ASIR images (p < 0.05). MBIRNR40 with low-contrast resolution preference provides significantly lower noise and better image quality than MBIRc and ASIR in low-dose abdominal CT; significantly better objective and subjective image quality than the routine-dose ASIR with 75% dose reduction.

Feasibility of radiation dose reduction with iterative reconstruction in abdominopelvic CT for patients with inappropriate arm positioning.

BackgroundThe arms-down position increases computed tomography (CT) radiation dose. Iterative reconstruction (IR) could enhance image quality without increasing radiation dose in patients with arms-down position.AimTo investigate the feasibility of reduced-dose CT with IR for patients with inappropriate arm positioningMethodsTwenty patients who underwent two-phase abdominopelvic CT including standard-dose and reduced-dose CT (performed with 80% of the radiation dose of the standard protocol) with their arms positioned in the abdominal area were included in this study. Reduced-dose CT images were reconstructed using filtered back projection (FBP), hybrid IR, and iterative model reconstruction (IMR). These images were compared with standard-dose CT images reconstructed with FBP. Objective image noise in the liver and subcutaneous fat was measured by standard deviation for the quantitative analysis. Then, two radiologists qualitatively assessed beam hardening artifacts, artificial texture, noise, sharpness, and overall image quality in consensus.ResultsReduced-dose CT with all IR levels had lower objective image noise compared to standard-dose CT with FBP reconstruction (P < 0.05). Quantitatively measured beam hardening artifacts were similar in reduced-dose CT with iDose levels 5–6 and fewer with IMR compared to standard-dose CT. In the qualitative analysis, beam hardening artifacts and noise decreased as the IR levels increased. However, artificial texture was significantly aggravated with iDose 5–6 and IMR, and overall image quality significantly worsened with IMR.ConclusionsIR algorithms can reduce beam hardening artifacts in a reduced-dose CT setting in patients with arms-down position, and an intermediate level of hybrid IR allows radiologists to obtain the best image quality. Because the retrospective and single-center nature of our study limited the number of patients, multicenter prospective clinical studies are required to validate our results.

Assessment of iterative image reconstruction on kidney and liver donors: Potential role of adaptive iterative dose reduction 3D (AIDR 3D) technology

ObjectiveThe aim of this study was to evaluate the radiation exposure levels in two different types of subjects including liver and kidney donors in diagnostic assessment of transplant operation and also the significance of dose reduction on total effective dose. Materials and methodsA number of Sixty subjects (40 males and 20 females, average age of 35 ± 10 years) were randomly prospectively recruited and equally divided into two distinct groups namely kidney donors (KD, 24 M and 6 F) and liver donors (LD, 21 M and 9 female). Kidney donors were divided into full dose (KFD, n = 20) group and low dose (KLD, n = 10) group. They had undergone dynamic renal scan using Tc99 m-DTPA, CT renal angiography and x-ray plain radiograph. Liver donors were divided into full dose (LFD, n = 20) and low dose (LLD, n = 10) groups and performed CT liver volumetry. The CT dose index (CTDIvol), dose length product (DLP), total milli-ampere product time mAs, effective dose and image noise index were measured in all subjects of kidney and liver donors comparing full dose and low dose protocols. ResultsIn comparison of all subjects of kidney donor groups (KFD vs KLD), the parameters (mAs = 16386.8 ± 3140.7 vs 2830.286 ± 831.676), (CTDIvol = 183.19 ± 32.58 mGy vs. 45.5 ± 13.3 mGy), DLP = 2884 ± 859.0 mGy.cm vs. 1437.5 ± 399 mGy.cm) and (effective dose = 49.0 ± 9.0 mSv vs. 18.9 mSv±5.7 mSv) were significant, p < 0.0005. Statistical evaluation of liver donors groups (LFD vs LLD) showed that (mAs = 14348.8 ± 4571.8 vs 3123.357 ± 794.5), (CTDIvol = 333.6 ± 59.5 mGy vs. 51.4 ± 13 mGy), (DLP = 3268.3 ± 604.3 mGy.cm vs 1260.5 ± 404.6 mGy.cm) and (effective dose = 43.3 mSv±12.9 mSv vs. 21.6 ± 5.9 mSv) are statistically significant, p < 0.0005. Nevertheless, the comparative evaluation of the image quality noise index of KFD vs KLD groups and LFD vs LLD showed a no statistical significance p > 0.05. ConclusionRenal and liver donors bear a relatively significant radiation dose due to diagnostic evaluation and patient management. The CT iterative reconstruction using AIDR3D proved very valuable tool in dose reduction such that it can reduce 37% in kidney donors and 48% in liver donors while able to maintain an acceptable image quality. Monitoring of those subjects on the clinical and radiobiological levels are recommended.

Parameter Tuning in Regularization-Based Iterative CT Reconstruction Via Deep Reinforcement Learning

Regularization-based iterative CT reconstruction has demonstrated its tremendous power. Formulated under an optimization approach, regularization-based iterative CT reconstruction considers an objective function containing a data-fidelity term and a regularization term. With the latter introduced to enforce image quality, high quality images can be reconstructed under clinically desirable conditions, such as reduced imaging dose to patients. Yet there are always parameters in the problem, which govern tradeoffs between the two terms and impact solution image quality. Manual parameter tuning is not only tedious, but become impractical when many parameters exist. Motivated by recent advancements in deep-learning area that can accomplish tasks in a human-like manner, such as playing computer games, we propose to employ deep reinforcement learning (DRL) to develop a system that automatically adjusts parameters with human-level intelligence, such that the intensive efforts of manual parameter tuning can be released. We consider an example problem of CT reconstruction with pixel-wise total-variation (TV) regularization. We set up a parameter tuning policy network (PTPN). It maps an image patch to a decision that specifies the direction and amplitude of parameter adjustment for the pixel at the patch center. To train PTPN, a reward function is defined that favors improvement in image quality, as quantified by the difference between the solution image and the ground truth image, which is known at the training stage. We train PTPN via end-to-end deep DRL with experience replay technique. Once PTPN is trained, we test it in simulation and real experimental cases. During a reconstruction process, we initiate parameters randomly. PTPN continuously observes the intermediate reconstructed image and make decision to adjust the parameters, until the image quality cannot be further improved. In simulation studies, PTPN can intelligently guide the reconstruction process, yielding images with 3% lower error than that under the randomly initialized parameters. The resulting image is slightly better than that under manually tuned parameter (∼0.5% lower error). Similar behavior is observed in experimental data. For the problem of CT reconstruction with pixel-wise TV regularization, closed form solution of the optimal parameter values can be derived. The parameters tuned by PTPN appeared similar to the optimal parameters, demonstrating the effectiveness of PTPN. Under DRL, we have developed PTPN that can adjust parameters of an iterative CT reconstruction problem in a human-like manner. The resulting image is similar or better than those under manual parameter tuning.

A phantom study of the performance of model-based iterative reconstruction in low-dose chest and abdominal CT: When are benefits maximized?

IntroductionThe aim of this study was to assess and compare the effects of CT image reconstruction techniques on low-dose CT image quality using phantoms. MethodsAnthropomorphic torso and spatial/contrast-resolution phantoms were scanned at decreasing tube currents between 400 and 10 mA. CT thorax and abdomen/pelvis series were reconstructed with filtered back projection (FBP) alone, combined 40% adaptive statistical iterative reconstruction & FBP (ASIR40), and model-based iterative reconstruction (MBIR) [(resolution-preference 05 (RP05) and RP20 in the thorax and RP05 and noise-reduction 05 (NR05) in the abdomen)]. Two readers rated image quality quantitatively and qualitatively. ResultsIn thoracic CT, objective image noise on MBIR RP05 data sets outperformed FBP at 200, 100, 50 and 10 mA and outperformed ASIR40 at 50 and 10 mA (p < 0.001). MBIR RP20 outperformed FBP at 50 and 10 mA and outperformed ASIR40 at 10 mA (p < 0.001). Compared with both FBP and ASIR40, MBIR RP05 demonstrated significantly better signal-to-noise ratio (SNR) at 10 mA. In abdomino-pelvic CT, MBIR RP05 and NR05 outperformed FBP and ASIR at all tube current levels for objective image noise. NR05 demonstrated greater SNR at 200, 100, 50 and 10 mA and RP05 demonstrated greater SNR at 50 and 10 mA compared with both FBP and ASIR. MBIR images demonstrated better subjective image quality scores. Spatial resolution, low-contrast detectability and contrast-to-noise ratio (CNR) were comparable between image reconstruction techniques. ConclusionCTs reconstructed with MBIR have lower image noise and improved image quality compared with FBP and ASIR. These effects increase with reduced radiation exposure confirming optimal use for low-dose CT imaging.

Optimizing a Parameterized Plug-and-Play ADMM for Iterative Low-Dose CT Reconstruction.

Reducing the exposure to X-ray radiation while maintaining a clinically acceptable image quality is desirable in various CT applications. To realize low-dose CT (LdCT) imaging, model-based iterative reconstruction (MBIR) algorithms are widely adopted, but they require proper prior knowledge assumptions in the sinogram and/or image domains and involve tedious manual optimization of multiple parameters. In this paper, we propose a deep learning (DL)-based strategy for MBIR to simultaneously address prior knowledge design and MBIR parameter selection in one optimization framework. Specifically, a parameterized plug-and-play alternating direction method of multipliers (3pADMM) is proposed for the general penalized weighted least-squares model, and then, by adopting the basic idea of DL, the parameterized plug-and-play (3p) prior and the related parameters are optimized simultaneously in a single framework using a large number of training data. The main contribution of this paper is that the 3p prior and the related parameters in the proposed 3pADMM framework can be supervised and optimized simultaneously to achieve robust LdCT reconstruction performance. Experimental results obtained on clinical patient datasets demonstrate that the proposed method can achieve promising gains over existing algorithms for LdCT image reconstruction in terms of noise-induced artifact suppression and edge detail preservation.