Statistical Iterative Reconstruction Research Articles

Evaluation of low-dose computed tomography reconstruction using spatial-radon domain total generalized variation regularization

The x-ray radiation dose in computed tomography (CT) examination has been a major concern for patients. Lowing the tube current and exposure time in data acquisition is a straightforward and cost-effective strategy to reduce the x-ray radiation dose. However, this will inevitably increase the noise fluctuations in measured projection data, and the corresponding CT image quality will be severely degraded if noise suppression is not performed during image reconstruction. To reconstruct high-quality low-dose CT image, we present a spatial-radon domain total generalized variation (SRDTGV) regularization for statistical iterative reconstruction based on penalized weighted least-squares (PWLS) principle, which is called PWLS-SRDTGV for simplicity. The presented PWLS-SRDTGV model can simultaneously reconstruct high-quality CT image in space domain and its corresponding projection in radon domain. An efficient split Bregman algorithm was applied to minimize the cost function of the proposed reconstruction model. Qualitative and quantitative studies were performed to evaluate the effectiveness of the PWLS-SRDTGV image reconstruction algorithm using a digital 3D XCAT phantom and an anthropomorphic torso phantom. The experimental results demonstrate that PWLS-SRDTGV algorithm achieves notable gains in noise reduction, streak artifact suppression, and edge preservation compared with competing reconstruction approaches.

The application value of a vendor-specific deep learning image reconstruction algorithm in "triple low" head and neck computed tomography angiography.

Head and neck computed tomography angiography (CTA) technology has become the noninvasive imaging method of choice for the diagnosis and long-term follow-up of vascular lesions of the head and neck. However, issues of radiation safety and contrast nephropathy associated with CTA examinations remain concerns. In recent years, deep learning image reconstruction (DLIR) algorithms have been increasingly used in clinical studies, demonstrating their potential for dose optimization. This study aimed to investigate the value of using a DLIR algorithm to reduce radiation and contrast doses in head and neck CTA. A total of 100 patients were prospectively enrolled and randomly divided into two groups. Group A (50 patients) consisted of those who underwent 70-kVp CTA with a low contrast volume and injection rate and who were classified according to the reconstruction algorithm into subgroups A1 [DLIR at high weighting (DLIR-H)], A2 [DLIR at low weighting (DLIR-L)], and A3 [volume-based adaptive statistical iterative reconstruction with 50% weighting (ASIR-V50%)]. Meanwhile, group B (50 patients) consisted of those who underwent standard radiation and contrast doses at 100 kVp with ASIR-V50% reconstruction. The computed tomography (CT) attenuation, background noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and subjective image quality score (SIQS) were statistically compared for several vessels among the four groups. Group A showed significant reductions in contrast dosage, injection rate, and radiation dose of 36.09%, 20.88%, and 47.80%, respectively, compared to group B (all P<0.001). The four groups differed significantly in terms of background noise (all P<0.05) with group A1 having the lowest value. Group A1 also had significantly higher SNR and CNR values compared to group B in all vessels (all P<0.05) except the M1 of the middle cerebral artery for the SNR. Group A1 also had the highest SIQS, followed by the A2, B, and A3 groups. The SIQS showed good agreement between the two reviewers in all groups, with κ values between 0.88 and 1. Compared to the standard-dose protocol using 100 kVp and ASIR-V50%, a protocol of 70 kVp combined with DLIR-H significantly reduces the radiation dose, contrast dose, and injection rate in head and neck CTA while still significantly improving image quality for patients with a standard body size.

A CT deep learning reconstruction algorithm: Image quality evaluation for brain protocol at decreasing dose indexes in comparison with FBP and statistical iterative reconstruction algorithms

PurposeTo characterise the impact of Precise Image (PI) deep learning reconstruction algorithm on image quality, compared to filtered back-projection (FBP) and iDose4 iterative reconstruction for brain computed tomography (CT) phantom images. MethodsCatphan-600 phantom was acquired with an Incisive CT scanner using a dedicated brain protocol, at six different dose levels (volume computed tomography dose index (CTDIvol): 7/14/29/49/56/67 mGy). Images were reconstructed using FBP, levels 2/5 of iDose4, and PI algorithm (Sharper/Sharp/Standard/Smooth/Smoother). Image quality was assessed by evaluating CT numbers, image histograms, noise, image non-uniformity (NU), noise power spectrum, target transfer function, and detectability index. ResultsThe five PI levels did not significantly affect the mean CT number. For a given CTDIvol using Sharper-to-Smoother levels, the spatial resolution for all the investigated materials and the detectability index increased while the noise magnitude decreased, slightly affecting noise texture. For a fixed PI level increasing the CTDIvol the detectability index increased, the noise magnitude decreased. From 29 mGy, NU values converged within 1 Hounsfield Unit from each other without a substantial improvement at higher CTDIvol values. ConclusionsThe improved performances of intermediate PI levels in brain protocols compared to conventional algorithms seem to suggest a potential reduction of CTDIvol.

Improved image quality in CT pulmonary angiography using deep learning-based image reconstruction

We investigated the effect of deep learning-based image reconstruction (DLIR) compared to iterative reconstruction on image quality in CT pulmonary angiography (CTPA) for suspected pulmonary embolism (PE). For 220 patients with suspected PE, CTPA studies were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction (ASiR-V 30%, 60% and 90%) and DLIR (low, medium and high strength). Contrast-to-noise ratio (CNR) served as the primary parameter of objective image quality. Subgroup analyses were performed for normal weight, overweight and obese individuals. For patients with confirmed PE (n = 40), we further measured PE-specific CNR. Subjective image quality was assessed independently by two experienced radiologists. CNR was lowest for FBP and enhanced with increasing levels of ASiR-V and, even more with increasing strength of DLIR. High strength DLIR resulted in an additional improvement in CNR by 29–67% compared to ASiR-V 90% (p < 0.05). PE-specific CNR increased by 75% compared to ASiR-V 90% (p < 0.05). Subjective image quality was significantly higher for medium and high strength DLIR compared to all other image reconstructions (p < 0.05). In CT pulmonary angiography, DLIR significantly outperforms iterative reconstruction for increasing objective and subjective image quality. This may allow for further reductions in radiation exposure in suspected PE.

Deep convolutional dictionary learning network for sparse view CT reconstruction with a group sparse prior

Purpose Numerous techniques based on deep learning have been utilized in sparse view computed tomography (CT) imaging. Nevertheless, the majority of techniques are instinctively constructed utilizing state-of-the-art opaque convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields and neglect nonlocal self-similarity prior information. Obtaining diagnostically valuable images from sparsely sampled projections is a challenging and ill-posed task.Method To address this issue, we propose a unique and understandable model named DCDL-GS for sparse view CT imaging. This model relies on a network comprised of convolutional dictionary learning and a nonlocal group sparse prior. To enhance the quality of image reconstruction, we utilize a neural network in conjunction with a statistical iterative reconstruction framework and perform a set number of iterations. Inspired by group sparsity priors, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Furthermore, our DCDL-GS model incorporates filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight and interpretable convolutional dictionary learning network to enhance the applicability of the model.Results The efficiency of our proposed DCDL-GS model in preserving edges and recovering features is demonstrated by the visual results obtained on the LDCT-P and UIH datasets. Compared to the results of the most advanced techniques, the quantitative results are enhanced, with increases of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse prior.Conclusion In this paper, we create a consolidated and enhanced mathematical model by integrating projection data and prior knowledge of images into a deep iterative model. The model is more practical and interpretable than existing approaches. The results from the experiment show that the proposed model performs well in comparison to the others.

MB-DECTNet: a model-based unrolling network for accurate 3D dual-energy CT reconstruction from clinically acquired helical scans

Objective. Over the past several decades, dual-energy CT (DECT) imaging has seen significant advancements due to its ability to distinguish between materials. DECT statistical iterative reconstruction (SIR) has exhibited potential for noise reduction and enhanced accuracy. However, its slow convergence and substantial computational demands render the elapsed time for 3D DECT SIR often clinically unacceptable. The objective of this study is to accelerate 3D DECT SIR while maintaining subpercentage or near-subpercentage accuracy. Approach. We incorporate DECT SIR into a deep-learning model-based unrolling network for 3D DECT reconstruction (MB-DECTNet), which can be trained end-to-end. This deep learning-based approach is designed to learn shortcuts between initial conditions and the stationary points of iterative algorithms while preserving the unbiased estimation property of model-based algorithms. MB-DECTNet comprises multiple stacked update blocks, each containing a data consistency layer (DC) and a spatial mixer layer, with the DC layer functioning as a one-step update from any traditional iterative algorithm. Main results. The quantitative results indicate that our proposed MB-DECTNet surpasses both the traditional image-domain technique (MB-DECTNet reduces average bias by a factor of 10) and a pure deep learning method (MB-DECTNet reduces average bias by a factor of 8.8), offering the potential for accurate attenuation coefficient estimation, akin to traditional statistical algorithms, but with considerably reduced computational costs. This approach achieves 0.13% bias and 1.92% mean absolute error and reconstructs a full image of a head in less than 12 min. Additionally, we show that the MB-DECTNet output can serve as an initializer for DECT SIR, leading to further improvements in results. Significance. This study presents a model-based deep unrolling network for accurate 3D DECT reconstruction, achieving subpercentage error in estimating virtual monoenergetic images for a full head at 60 and 150 keV in 30 min, representing a 40-fold speedup compared to traditional approaches. These findings have significant implications for accelerating DECT SIR and making it more clinically feasible.

Quantitative analysis evaluation of image reconstruction algorithms between digital and analog PET-CT

Positron emission tomography – computed tomography (PET-CT) is a non-invasive diagnostic tool that is widely used in oncology imaging. High quality diagnostic images and quantitative accuracy are often restricted by image noise, adequate spatial resolution and contrast ratio.Ordered Subset Expectation Maximisation (OSEM) is a widely used statistical iterative reconstruction algorithm in PET-CT due to its dependability, reconstruction quality and adequate signal-to-noise ratio. However, OSEM requires a large number of iterations to achieve high quantitative accuracy which results in increasing image noise. A novel algorithm, HYPER DPR (developed by United Imaging Healthcare) is an artificial intelligence-based reconstruction method that aims to provide increased sensitivity, higher spatial resolution and less noise.This study evaluates the accuracy and sensitivity of HYPER DPR against OSEM using reconstructed images from analog and digital PET-CT. Results demonstrate that both OSEM and HYPER DPR reconstruction algorithms in digital PET-CT has greater spatial resolution, increased detection sensitivity and less image noise when compared to analog PET-CT. Digital PET-CT and HYPER DPR enables better small lesion detection and increased resolution, thus resulting in better disease detection and improved patient management. Increased sensitivity of digital PET-CT results in low dose scans from reduced radiotracer injections, therefore having higher patient output.

The value of metal artifact reduction and iterative algorithms in dual energy CT angiography in patients after complex endovascular aortic aneurysm repair

Rationale and objectivesEvaluation of the diagnostic value of linearly blended (LB) and virtual monoenergetic images (VMI) reconstruction techniques with and without metal artifacts reduction (MAR) and of adaptive statistical iterative reconstructions (ASIR) in the assessment of target vessels after branched/fenestrated endovascular aortic repair (f/brEVAR) procedures. Materials and methodsCT scans of 28 patients were used in this study. Arterial phase of examination was obtained using a dual-energy fast-kVp switching scanner. CT numbers in the aorta, celiac trunk, superior mesenteric artery, and renal arteries were measured in the following reconstructions: LB, VMI 60 keV, VMI MAR 60 keV, VMI ASIR 60 % 60 keV. Contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR) were calculated for each reconstruction. Luminal diameters (measurements at 2 levels of stent) and subjective image quality (5-point Likert scale) were assessed (2 readers, blinded to the type of reconstruction). ResultsThe highest mean values of CNR and SNR in vascular structures were obtained in VMI MAR 60 keV (CNR 12.526 ± 2.46, SNR 17.398 ± 2.52), lower in VMI 60 keV (CNR 11.508 ± 2.01, SNR 16.524 ± 2.07) and VMI ASIR (CNR 11.086 ± 1.78, SNR 15.928 ± 1.82), and the lowest in LB (CNR 6.808 ± 0.79, SNR 11.492 ± 0.79) reconstructions. There were no statistically significant differences in the measurements of the stent width between reconstructions (p > 0.05). The highest subjective image quality was obtained in the ASIR VMI (4.25 ± 0.44) and the lowest in the MAR VMI (1.57 ± 0.5) reconstruction. ConclusionDespite obtaining the highest values of SNR and CNR in the MAR VMI reconstruction, the subjective diagnostic value was the lowest for this technique due to significant artifacts. The type of reconstruction did not significantly affect vessel diameter measurements (p > 0.05). Iterative reconstructions raised both objective and subjective image quality.

The impact of deep learning reconstruction in low dose computed tomography on the evaluation of interstitial lung disease.

To evaluate the effect of the deep learning model reconstruction (DLM) method in terms of image quality and diagnostic agreement in low-dose computed tomography (LDCT) for interstitial lung disease (ILD), 193 patients who underwent LDCT for suspected ILD were retrospectively reviewed. Datasets were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction Veo (ASiR-V), and DLM. For image quality analysis, the signal, noise, signal-to-noise ratio (SNR), blind/referenceless image spatial quality evaluator (BRISQUE), and visual scoring were evaluated. Also, CT patterns of usual interstitial pneumonia (UIP) were classified according to the 2022 idiopathic pulmonary fibrosis (IPF) diagnostic criteria. The differences between CT images subjected to FBP, ASiR-V 30%, and DLM were evaluated. The image noise and BRISQUE scores of DLM images was lower and SNR was higher than that of the ASiR-V and FBP images (ASiR-V vs. DLM, p < 0.001 and FBP vs. DLR-M, p < 0.001, respectively). The agreement of the diagnostic categorization of IPF between the three reconstruction methods was almost perfect (κ = 0.992, CI 0.990-0.994). Image quality was improved with DLM compared to ASiR-V and FBP.

Informasi Anatomi dan Dosis Radiasi pada MSCT Brain Pediatric Menggunakan Adaptive Statistical Iterative Reconstruction (ASiR)-V

Background: Multislice CT Scan (MSCT) brain examination in pediatric cases should pay attention to the lowest possible dose but still provide optimal anatomical information. Pediatric has a higher risk of developing cancer compared to adults who receive the same dose. The purpose of this study is to obtain the optimal value of the use of the Adaptive Statistical Iterative Reconstruction (ASIR)-V technique with variations in tube current strength and Iterative Reconstruction value which is implemented in pediatric patients under the age of 5 (five) years. Methods: This research was experimental with brain image samples of pediatric patients at the Radiology Installation of RSUD dr. Moewardi Surakarta. The variations of the tube currents selected were 80, 100, and 165 mA with a combination of AR20, AR40, AR60, and AR80 variations. Anatomical information processed descriptively sourced from the assessment of 3 (three) radiologists who were experienced in assessing MSCT images. Meanwhile, the effect of tube current variation on radiation dose was tested using linear regression. Results: The results showed differences in anatomical information between the combinations of 165 mA-AR60 and 165 mA-AR80 "very clear", 165 mA-AR20 "clear", 80 mA-AR20 "fairly clear" and 100 mA-AR80 "less clear". There was an effect of strong variation of tube current on radiation dose with a regression coefficient value of 0.690. The estimated effective doses of the three tube current values were still below the national Dose Reference Level (DRL). Conclusions: It was concluded that there were differences in anatomical information on the MSCT brain pediatric examination with variations in tube current and ASiR-V, there was an effect of variations in mA on radiation dose and mA values and the optimal value of the combination of techniques studied is 80 mA and 20% Iterative Reconstruction.

Dose Optimization Using a Deep Learning Tool in Various CT Protocols for Urolithiasis: A Physical Human Phantom Study.

Background and Objectives: We attempted to determine the optimal radiation dose to maintain image quality using a deep learning application in a physical human phantom. Materials and Methods: Three 5 × 5 × 5 mm3 uric acid stones were placed in a physical human phantom in various locations. Three tube voltages (120, 100, and 80 kV) and four current-time products (100, 70, 30, and 15 mAs) were implemented in 12 scans. Each scan was reconstructed with filtered back projection (FBP), statistical iterative reconstruction (IR, iDose), and knowledge-based iterative model reconstruction (IMR). By applying deep learning to each image, we took 12 more scans. Objective image assessments were calculated using the standard deviation of the Hounsfield unit (HU). Subjective image assessments were performed by one radiologist and one urologist. Two radiologists assessed the subjective assessment and found the stone under the absence of information. We used this data to calculate the diagnostic accuracy. Results: Objective image noise was decreased after applying a deep learning tool in all images of FBP, iDose, and IMR. There was no statistical difference between iDose and deep learning-applied FBP images (10.1 ± 11.9, 9.5 ± 18.5 HU, p = 0.583, respectively). At a 100 kV-30 mAs setting, deep learning-applied FBP obtained a similar objective noise in approximately one third of the radiation doses compared to FBP. In radiation doses with settings lower than 100 kV-30 mAs, the subject image assessment (image quality, confidence level, and noise) showed deteriorated scores. Diagnostic accuracy was increased when the deep learning setting was lower than 100 kV-30 mAs, except for at 80 kV-15 mAs. Conclusions: At the setting of 100 kV-30 mAs or higher, deep learning-applied FBP did not differ in image quality compared to IR. At the setting of 100 kV-30 mAs, the radiation dose can decrease by about one third while maintaining objective noise.

Low-dose liver CT: image quality and diagnostic accuracy of deep learning image reconstruction algorithm

ObjectivesTo perform a comprehensive within-subject image quality analysis of abdominal CT examinations reconstructed with DLIR and to evaluate diagnostic accuracy compared to the routinely applied adaptive statistical iterative reconstruction (ASiR-V) algorithm.Materials and methodsOncologic patients were prospectively enrolled and underwent contrast-enhanced CT. Images were reconstructed with DLIR with three intensity levels of reconstruction (high, medium, and low) and ASiR-V at strength levels from 10 to 100% with a 10% interval. Three radiologists characterized the lesions and two readers assessed diagnostic accuracy and calculated signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), figure of merit (FOM), and subjective image quality, the latter with a 5-point Likert scale.ResultsFifty patients (mean age: 70 ± 10 years, 23 men) were enrolled and 130 liver lesions (105 benign lesions, 25 metastases) were identified. DLIR_H achieved the highest SNR and CNR, comparable to ASiR-V 100% (p ≥ .051). DLIR_M returned the highest subjective image quality (score: 5; IQR: 4–5; p ≤ .001) and significant median increase (29%) in FOM (p < .001). Differences in detection were identified only for lesions ≤ 0.5 cm: 32/33 lesions were detected with DLIR_M and 26 lesions were detected with ASiR-V 50% (p = .031). Lesion accuracy of was 93.8% (95% CI: 88.1, 97.3; 122 of 130 lesions) for DLIR and 87.7% (95% CI: 80.8, 92.8; 114 of 130 lesions) for ASiR-V 50%.ConclusionsDLIR yields superior image quality and provides higher diagnostic accuracy compared to ASiR-V in the assessment of hypovascular liver lesions, in particular for lesions ≤ 0.5 cm.Clinical relevance statementDeep learning image reconstruction algorithm demonstrates higher diagnostic accuracy compared to iterative reconstruction in the identification of hypovascular liver lesions, especially for lesions ≤ 0.5 cm.Key Points• Iterative reconstruction algorithm impacts image texture, with negative effects on diagnostic capabilities.• Medium-strength deep learning image reconstruction algorithm outperforms iterative reconstruction in the diagnostic accuracy of ≤ 0.5 cm hypovascular liver lesions (93.9% vs 78.8%), also granting higher objective and subjective image quality.• Deep learning image reconstruction algorithm can be safely implemented in routine abdominal CT protocols in place of iterative reconstruction.

The influence of image reconstruction methods on the diagnosis of pulmonary emphysema with convolutional neural network.

This study investigated the influence of iterative reconstruction (IR) methods on computed tomography (CT) images when training convolutional neural network (CNN) models to diagnose pulmonary emphysema. To evaluate the influence of the IR algorithm on CNN, the present study comprised two steps: the comparison of noise reduction by IR algorithms using phantom examinations and the change in performance of CNN with IR algorithms using patient data. We retrospectively analyzed 97 patients. Raw CT data were reconstructed using the filtered back-projection (FBP) and adaptive statistical iterative reconstruction V (ASIR-V) algorithms with blending levels of 30%, 50%, and 70%. The models were trained using reconstructed CT images and were named the FBP, ASIR-V30, ASIR-V50, and ASIR-V70 models. The mean and the standard deviation of the CT values were 11.3 ± 21.2 at FBP, 11.0 ± 17.3 at ASIR-V30, 11.0 ± 14.4 at ASIR-V50, and 11.0 ± 11.8 at ASIR-V70. For all the evaluation metrics, the best values were obtained with the FBP model applied to the ASIR-V70 test images. The worst values were obtained with the ASIR-V70 model applied to the FBP test images. The model trained with FBP images exhibited significantly better performance than the models trained using IR images. The reduction in image noise with the IR algorithm on the test images contributed to improving the accuracy of the classification of emphysema subtypes using CNN.

Image Quality Improvement in Deep Learning Image Reconstruction of Head Computed Tomography Examination.

In this study, we assess image quality in computed tomography scans reconstructed via DLIR (Deep Learning Image Reconstruction) and compare it with iterative reconstruction ASIR-V (Adaptive Statistical Iterative Reconstruction) in CT (computed tomography) scans of the head. The CT scans of 109 patients were subjected to both objective and subjective evaluation of image quality. The objective evaluation was based on the SNR (signal-to-noise ratio) and CNR (contrast-to-noise ratio) of the brain's gray and white matter. The regions of interest for our study were set in the BGA (basal ganglia area) and PCF (posterior cranial fossa). Simultaneously, a subjective assessment of image quality, based on brain structure visibility, was conducted by experienced radiologists. In the assessed scans, we obtained up to a 54% increase in SNR for gray matter and a 60% increase for white matter using DLIR in comparison to ASIR-V. Moreover, we achieved a CNR increment of 58% in the BGA structures and 50% in the PCF. In the subjective assessment of the obtained images, DLIR had a mean rating score of 2.8, compared to the mean score of 2.6 for ASIR-V images. In conclusion, DLIR shows improved image quality compared to the standard iterative reconstruction of CT images of the head.

Image Quality Improvement of Low-dose Abdominal CT Using Deep Learning Image Reconstruction Compared With the Second Generation Iterative Reconstruction.

Whether deep learning-based CT reconstruction could improve lesion conspicuity on abdominal CT when the radiation dose is reduced is controversial. To determine whether DLIR can provide better image quality and reduce radiation dose in contrast-enhanced abdominal CT compared with the second generation of adaptive statistical iterative reconstruction [ASiR-V]. This study aims to determine whether deep-learning image reconstruction [DLIR] can improve image quality. In this retrospective study, a total of 102 patients were included, who underwent abdominal CT using a DLIR-equipped 256-row scanner and routine CT of the same protocol on the same vendor's 64-row scanner within four months. The CT data from the 256-row scanner were reconstructed into ASiR-V with three blending levels [AV30, AV60, and AV100], and DLIR images with three strength levels [DLIR-L, DLIR-M, and DLIR-H]. The routine CT data were reconstructed into AV30, AV60, and AV100. The contrast-to-noise ratio [CNR] of the liver, overall image quality, subjective noise, lesion conspicuity, and plasticity in the portal venous phase [PVP] of ASiR-V from both scanners and DLIR were compared. The mean effective radiation dose of PVP of the 256-row scanner was significantly lower than that of the routine CT [6.3±2.0 mSv vs. 2.4±0.6 mSv; p< 0.001]. The mean CNR, image quality, subjective noise, and lesion conspicuity of ASiR-V images of the 256-row scanner were significantly lower than those of ASiR-V images at the same blending factor of routine CT, but significantly improved with DLIR algorithms. DLIR-H showed higher CNR, better image quality, and subjective noise than AV30 from routine CT, whereas plasticity was significantly better for AV30. DLIR can be used for improving image quality and reducing radiation dose in abdominal CT, compared with ASIR-V.

Motion-compensated scheme for sequential scanned statistical iterative dual-energy CT reconstruction

Objective. Dual-energy computed tomography (DECT) has been widely used to reconstruct numerous types of images due its ability to better discriminate tissue properties. Sequential scanning is a popular dual-energy data acquisition method as it requires no specialized hardware. However, patient motion between two sequential scans may lead to severe motion artifacts in DECT statistical iterative reconstructions (SIR) images. The objective is to reduce the motion artifacts in such reconstructions. Approach. We propose a motion-compensation scheme that incorporates a deformation vector field into any DECT SIR. The deformation vector field is estimated via the multi-modality symmetric deformable registration method. The precalculated registration mapping and its inverse or adjoint are then embedded into each iteration of the iterative DECT algorithm. Main results. Results from a simulated and clinical case show that the proposed framework is capable of reducing motion artifacts in DECT SIRs. Percentage mean square errors in regions of interest in the simulated and clinical cases were reduced from 4.6% to 0.5% and 6.8% to 0.8%, respectively. A perturbation analysis was then performed to determine errors in approximating the continuous deformation by using the deformation field and interpolation. Our findings show that errors in our method are mostly propagated through the target image and amplified by the inverse matrix of the combination of the Fisher information and Hessian of the penalty term. Significance. We have proposed a novel motion-compensation scheme to incorporate a 3D registration method into the joint statistical iterative DECT algorithm in order to reduce motion artifacts caused by inter-scan motion, and successfully demonstrate that interscan motion corrections can be integrated into the DECT SIR process, enabling accurate imaging of radiological quantities on conventional SECT scanners, without significant loss of either computational efficiency or accuracy.

Can 1.25 mm thin-section images generated with Deep Learning Image Reconstruction technique replace standard-of-care 5 mm images in abdominal CT?

CT image reconstruction has evolved from filtered back projection to hybrid- and model-based iterative reconstruction. Deep learning-based image reconstruction is a relatively new technique that uses deep convolutional neural networks to improve image quality. To evaluate and compare 1.25 mm thin-section abdominal CT images reconstructed with deep learning image reconstruction (DLIR) with 5 mm thick images reconstructed with adaptive statistical iterative reconstruction (ASIR-V). This retrospective study included 52 patients (31 F; 56.9±16.9 years) who underwent abdominal CT scans between August-October 2019. Image reconstruction was performed to generate 5 mm images at 40% ASIR-V and 1.25 mm DLIR images at three strengths (low [DLIR-L], medium [DLIR-M], and high [DLIR-H]). Qualitative assessment was performed to determine image noise, contrast, visibility of small structures, sharpness, and artifact based on a 5-point-scale. Image preference determination was based on a 3-point-scale. Quantitative assessment included measurement of attenuation, image noise, and contrast-to-noise ratios (CNR). Thin-section images reconstructed with DLIR-M and DLIR-H yielded better image quality scores than 5 mm ASIR-V reconstructed images. Mean qualitative scores of DLIR-H for noise (1.77 ± 0.71), contrast (1.6 ± 0.68), small structure visibility (1.42 ± 0.66), sharpness (1.34 ± 0.55), and image preference (1.11 ± 0.34) were the best (p<0.05). DLIR-M yielded intermediate scores. All DLIR reconstructions showed superior ratings for artifacts compared to ASIR-V (p<0.05), whereas each DLIR group performed comparably (p>0.05, 0.405-0.763). In the quantitative assessment, there were no significant differences in attenuation values between all reconstructions (p>0.05). However, DLIR-H demonstrated the lowest noise (9.17 ± 3.11) and the highest CNR (CNRliver = 26.88 ± 6.54 and CNRportal vein = 7.92 ± 3.85) (all p<0.001). DLIR allows generation of thin-section (1.25 mm) abdominal CT images, which provide improved image quality with higher inter-reader agreement compared to 5 mm thick images reconstructed with ASIR-V. Improved image quality of thin-section CT images reconstructed with DLIR has several benefits in clinical practice, such as improved diagnostic performance without radiation dose penalties.

Comparison of noise-power spectrum and modulation-transfer function for CT images reconstructed with iterative and deep learning image reconstructions: An initial experience study

Abstract Introduction Deep learning image reconstruction (DLIR) is a very recent image reconstruction method that is already available for commercial use. We evaluated the quality of DLIR images and compared it to the quality of images from the latest adaptive statistical iterative reconstruction (ASIR-V) algorithm in terms of noise-power spectrum (NPS) and modulation-transfer function (MTF). Methods We scanned a Revolution QA phantom (GE Healthcare, USA) and a 20 cm water phantom (GE Healthcare, USA) with our 512 multi-slice computed tomography (CT) scanner. Images of the tungsten wire within the Revolution QA phantom were reconstructed with a 50 mm field of view (FOV). The images were reconstructed with various ASIR-V strengths (i.e. 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100%) and DLIRs (i.e. low, medium, and high) to assess the MTF. The images from the 20 cm water phantom were reconstructed with the same configuration to assess the NPS. Results The MTF was similar for both reconstruction algorithms of DLIR and ASiR-V. The peak frequency (fp) of the DLIR low was comparable to that from ASIR-V at 50, 60, 70%; the DLIR medium was comparable to ASIR-V at 80%; and the DLIR high was comparable to ASIR-V at 100%. The average frequency (fA) of the DLIR low was comparable to that from ASIR-V at 40%; the DLIR medium was comparable to ASIR-V at 50%; and the DLIR high was comparable to ASIR-V at 70%. Both the DLIR and ASIR-V were able to reduce noise, but they had a different texture. Conclusions The noise in the DLIR images was more homogenous at high and low frequencies, while in the ASIR-V images, the noise was more concentrated at high frequencies. The MTF was similar for both reconstruction algorithms. The DLIR method showed a better noise reduction than the ASIR-V reconstruction.

The efficacy of low-dose CT with deep learning image reconstruction in the surveillance of incidentally detected pancreatic cystic lesions.

To evaluate the efficacy of low-dose CT (LDCT) with deep learning image reconstruction (DLIR) for the surveillance of pancreatic cystic lesions (PCLs) compared with standard-dose CT (SDCT) with adaptive statistical iterative reconstruction (ASIR-V). The study enrolled 103 patients who underwent pancreatic CT for follow-up of incidentally detected PCLs. The CT protocol included LDCT in the pancreatic phase with 40% ASIR-V, DLIR at medium (DLIR-M) and high levels (DLIR-H), and SDCT in the portal-venous phase with 40% ASIR-V. The overall image quality and conspicuity of PCLs were qualitatively assessed using five-point scales by two radiologists. The size of PCLs, presence of thickened/enhancing walls, enhancing mural nodules, and main pancreatic duct dilatation were reviewed. CT noise and cyst-to-pancreas contrast-to-noise ratio (CNR) were measured. Qualitative and quantitative parameters were analyzed using the chi-squared test, one-way ANOVA, and t-test. Additionally, interobserver agreement was analyzed using the kappa and weighted-kappa statistics. The volume CT dose-indexes in LDCT and SDCT were 3.0 ± 0.6mGy and 8.4 ± 2.9mGy, respectively. LDCT with DLIR-H showed the highest overall image quality, the lowest noise, and the highest CNR. The PCL conspicuity in LDCT with either DLIR-M or DLIR-H was not significantly different from that in SDCT with ASIR-V. Other findings depicting PCLs also revealed no significant differences between LDCT with DLIR and SDCT with ASIR-V. Moreover, the results revealed good or excellent interobserver agreement. LDCT with DLIR has a comparable performance with SDCT for the follow-up of incidentally detected PCLs.

New-Generation ASiR-V for Dose Reduction While Maintaining Image Quality in CT: A Phantom Study

Over the last few decades, the need to reduce and optimize patient medical radiation exposure has prompted the introduction of novel reconstruction algorithms in computed tomography (CT). Against this backdrop, the present study aimed to assess whether reduced radiation dose CT images reconstructed with the new-generation adaptive statistical iterative reconstruction (ASiR-V) maintain the same image quality as that of routine image reconstruction. In addition, the optimization of image quality parameters for the ASiR-V algorithm (e.g., an optimal combination of blending percentage and noise index (NI)) was investigated. An abdominal reference phantom was imaged using the routine clinical protocol (fixed noise index of 18 and 40% ASiR reconstruction). Reduced radiation dose CT scans were performed with varying NI (22, 24, and 30) and using the ASiR-V reconstruction algorithm. Quantitative and qualitative analyses of image noise, contrast, and resolution were performed against NI and reconstruction blending percentages. Our results confirm the ability of the ASiR-V algorithm to provide images of high diagnostic quality while reducing the patient dose. All the parameters were improved in ASiR-V images as compared to ASiR. Both quantitative and qualitative analyses showed that the best agreement was obtained for the images reconstructed using ASiR-V with NI24 and a high percentage of blending (70–100%). This preliminary study results show that ASiR-V allows for a significant reduction in patient dose (about 40%) while maintaining a good overall image quality when appropriate NI (i.e., 24) is used.