Iterative reconstruction technique for reducing body radiation dose at CT: feasibility study. AJR Am J Roentgenol. 2009;193:764-771. [PMID: 19696291 DOI: 10.2214/ajr.09.2397]

Establishing the effect of computed tomography reconstruction kernels on the measure of bone mineral density in opportunistic osteoporosis screening

Opportunistic computed tomography (CT) scans, which can assess relevant bones of interest, offer a potential solution for identifying osteoporotic individuals. However, it has been well documented that image protocol parameters, such as reconstruction kernel, impact the quantitative analysis of volumetric bone mineral density (vBMD) from CT scans. The purpose of this study was to investigate the impact that CT reconstruction kernels have on quantitative results for vBMD from clinical CT scans using phantom and internal calibration. 45 clinical CT scans were reconstructed using the standard kernel and seven alternative kernels: soft, chest, detail, edge, bone, bone plus and lung [GE HealthCare]. Two methods of image calibration, internal and phantom, were used to calibrate the scans. The total hip and fourth lumbar vertebra (L4) were extracted from the scans via deep learning segmentation. Integral vBMD was calculated based on both calibration techniques from CT scans reconstructed with the eight kernels. Linear regression and Bland-Altman analyses were used to determine the coefficient of determination [Formula: see text] and to quantify the agreement between the different kernels. Differences between the reconstruction kernels were determined using paired t tests, and mean differences from the standard were computed. Using internal calibration, the smoothest kernel (soft) yielded a mean difference of -0.95 mg/cc (-0.33%) compared to the reference standard at the L4 vertebra and 2.07 mg/cc (0.51%) at the left femur. The sharpest kernel (lung) yielded a mean difference of 25.36 mg/cc (9.63%) at the L4 vertebra and -25.10 mg/cc (-5.98%) at the left femur. Alternatively, using phantom calibration soft yielded higher mean differences than internal calibration at both locations, with mean differences of 1.21 mg/cc (0.42%) at the L4 vertebra and 2.53 mg/cc (0.65%) at the left femur. The most error-prone results stemmed from the use of the lung kernel, as this kernel displayed a mean difference of -21.90 mg/cc (-7.38%) and -17.24 mg/cc (-4.34%) at the L4 vertebra and femur, respectively. These results indicate when performing opportunistic CT analysis, errors due to interchanging smoothing kernels soft, chest and detail are negligible, but that interchanging between sharpening kernels (lung, bone, bone plus, edge) results in large errors that can significantly impact vBMD measures for osteoporosis screening and diagnosis.

State-of-the-Art Deep Learning CT Reconstruction Algorithms in Abdominal Imaging

The implementation of deep neural networks has spurred the creation of deep learning reconstruction (DLR) CT algorithms. DLR CT techniques encompass a spectrum of deep learning-based methodologies that operate during the different steps of the image creation, prior to or after the traditional image formation process (eg, filtered backprojection [FBP] or iterative reconstruction [IR]), or alternatively by fully replacing FBP or IR techniques. DLR algorithms effectively facilitate the reduction of image noise associated with low photon counts from reduced radiation dose protocols. DLR methods have emerged as an effective solution to ameliorate limitations observed with prior CT image reconstruction algorithms, including FBP and IR algorithms, which are not able to preserve image texture and diagnostic performance at low radiation dose levels. An additional advantage of DLR algorithms is their high reconstruction speed, hence targeting the ideal triad of features for a CT image reconstruction (ie, the ability to consistently provide diagnostic-quality images and achieve radiation dose imaging levels as low as reasonably possible, with high reconstruction speed). An accumulated body of evidence supports the clinical use of DLR algorithms in abdominal imaging across multiple CT imaging tasks. The authors explore the technical aspects of DLR CT algorithms and examine various approaches to image synthesis in DLR creation. The clinical applications of DLR algorithms are highlighted across various abdominal CT imaging domains, with emphasis on the supporting evidence for diverse clinical tasks. An overview of the current limitations of and outlook for DLR algorithms for CT is provided. ©RSNA, 2024.

Adversarial EM for variational deep learning: Application to semi-supervised image quality enhancement in low-dose PET and low-dose CT

In positron emission tomography (PET) and X-ray computed tomography (CT), reducing radiation dose can cause significant degradation in image quality. For image quality enhancement in low-dose PET and CT, we propose a novel theoretical adversarial and variational deep neural network (DNN) framework relying on expectation maximization (EM) based learning, termed adversarial EM (AdvEM). AdvEM proposes an encoder-decoder architecture with a multiscale latent space, and generalized-Gaussian models enabling datum-specific robust statistical modeling in latent space and image space. The model robustness is further enhanced by including adversarial learning in the training protocol. Unlike typical variational-DNN learning, AdvEM proposes latent-space sampling from the posterior distribution, and uses a Metropolis-Hastings scheme. Unlike existing schemes for PET or CT image enhancement which train using pairs of low-dose images with their corresponding normal-dose versions, we propose a semi-supervised AdvEM (ssAdvEM) framework that enables learning using a small number of normal-dose images. AdvEM and ssAdvEM enable per-pixel uncertainty estimates for their outputs. Empirical analyses on real-world PET and CT data involving many baselines, out-of-distribution data, and ablation studies show the benefits of the proposed framework.

Optimizing computed tomography image reconstruction for focal hepatic lesions: Deep learning image reconstruction vs iterative reconstruction

Background

Deep learning image reconstruction (DLIR) is a novel computed tomography (CT) reconstruction technique that minimizes image noise, enhances image quality, and enables radiation dose reduction. This study aims to compare the diagnostic performance of DLIR and iterative reconstruction (IR) in the evaluation of focal hepatic lesions.

Methods

We conducted a retrospective study of 216 focal hepatic lesions in 109 adult participants who underwent abdominal CT scanning at our institution. We used DLIR (low, medium, and high strength) and IR (0 %, 10 %, 20 %, and 30 %) techniques for image reconstruction. Four experienced abdominal radiologists independently evaluated focal hepatic lesions based on five qualitative aspects (lesion detectability, lesion border, diagnostic confidence level, image artifact, and overall image quality). Quantitatively, we measured and compared the level of image noise for each technique at the liver and aorta.

Results

There were significant differences (p < 0.001) among the seven reconstruction techniques in terms of lesion borders, image artifacts, and overall image quality. Low-strength DLIR (DLIR-L) exhibited the best overall image quality. Although high-strength DLIR (DLIR-H) had the least image noise and fewest artifacts, it also had the lowest scores for lesion borders and overall image quality. Image noise showed a weak to moderate positive correlation with participants' body mass index and waist circumference.

Conclusions

The optimal-strength DLIR significantly improved overall image quality for evaluating focal hepatic lesions compared to the IR technique. DLIR-L achieved the best overall image quality while maintaining acceptable levels of image noise and quality of lesion borders.

DeCoGAN: MVCT image denoising via coupled generative adversarial network

Objective.In helical tomotherapy, image-guided radiotherapy employs megavoltage computed tomography (MVCT) for precise targeting. However, the high voltage of megavoltage radiation introduces substantial noise, significantly compromising MVCT image clarity. This study aims to enhance MVCT image quality using a deep learning-based denoising method.Approach.We propose an unpaired MVCT denoising network using a coupled generative adversarial network framework (DeCoGAN). Our approach assumes that a universal latent code within a shared latent space can reconstruct any given pair of images. By employing an encoder, we enforce this shared-latent space constraint, facilitating the conversion of low-quality (noisy) MVCT images into high-quality (denoised) counterparts. The network learns the joint distribution of images from both domains by leveraging samples from their respective marginal distributions, enhanced by adversarial training for effective denoising.Main Results.Compared to an analytical algorithm (BM3D) and three deep learning-based methods (RED-CNN, WGAN-VGG and CycleGAN), the proposed method excels in preserving image details and enhancing human visual perception by removing most noise and retaining structural features. Quantitative analysis demonstrates that our method achieves the highest peak signal-to-noise ratio and Structural Similarity Index Measurement values, indicating superior denoising performance.Significance.The proposed DeCoGAN method shows remarkable MVCT denoising performance, making it a promising tool in the field of radiation therapy.

Development and validation of the effective CNR analysis method for evaluating the contrast resolution of CT images

Contrast resolution is an important index for evaluating the signal detectability of computed tomographic (CT) images. Recently, various noise reduction algorithms, such as iterative reconstruction (IR) and deep learning reconstruction (DLR), have been proposed to reduce the image noise in CT images. However, these algorithms cause changes in the image noise texture and blurred image signals in CT images. Furthermore, the contrast-to-noise ratio (CNR) cannot be accurately evaluated in CT images reconstructed using noise reduction methods. Therefore, in this study, we devised a new method, namely, "effective CNR analysis," for evaluating the contrast resolution of CT images. We verified whether the proposed algorithm could evaluate the effective contrast resolution based on the signal detectability of CT images. The findings showed that the effective CNR values obtained using the proposed method correlated well with the subjective visual impressions of CT images. To investigate whether signal detectability was appropriately evaluated using effective CNR analysis, the conventional CNR analysis method was compared with the proposed method. The CNRs of the IR and DLR images calculated using conventional CNR analysis were 13.2 and 10.7, respectively. By contrast, those calculated using the effective CNR analysis were estimated to be 0.7 and 1.1, respectively. Considering that the signal visibility of DLR images was superior to that of IR images, our proposed effective CNR analysis was shown to be appropriate for evaluating the contrast resolution of CT images.

Contribution of CT scan to patient's radiation exposure in parathyroid SPECT/CT scintigraphy

INTRODUCTION

Dual phase technetium-99mTc-methoxy isobutyl isonitrile (MIBI) single-photon emission computed tomography with computed tomography (SPECT/CT) may be the most accurate conventional imaging approach for localization of enlarged parathyroid gland (EPG). The imaging is based on the radiopharmaceutical (RP) retention in EPG compared to washout from normal thyroid and normal parathyroid glands. This study aimed to estimate and optimize the contribution of computed tomography (CT) scan and scan range to effective dose (ED) in dual-phase MIBI SPECT/CT parathyroid scintigraphy.

METHODS

The study included seventy-four patients; thirty-seven with reduced and thirty-seven with extended CT scan range. The ED caused by the CT scan was calculated using Dose Length Product (DLP) data and estimated using the Imaging Performance Assessment of CT scanners (ImPACT) calculator.

RESULTS

For all patients, the contribution of CT to the ED in a combined SPECT/CT examination was 2.62 ± 0.29 mSv (48%). The contribution of CT to the total ED was 1.8 ± 0.18 mSv (33%) when using reduced and 3.44 ± 0.23 mSv (64%) when using extended scan range. The DLP and ED were statistically significantly different between the reduced and extended CT scan range (p < 0.001) in the first and second phases. The individual organ dose was reduced from 8% to 94%.

CONCLUSION

The hybrid SPECT/CT improves the interpretation of nuclear medicine images and also increases the radiation dose to the patient. An adequately defined CT scan range on SPECT/CT imaging, can significantly reduce a patient's ED.

IMPLICATIONS FOR PRACTICE

The research findings showed that knowledge of anatomy, pathology and technology can provide optimising diagnostic procedures and reduce patient ED after SPECT/CT scans.

Influence of deep learning image reconstruction algorithm for reducing radiation dose and image noise compared to iterative reconstruction and filtered back projection for head and chest computed tomography examinations: a systematic review

Background

The most recent advances in Computed Tomography (CT) image reconstruction technology are Deep learning image reconstruction (DLIR) algorithms. Due to drawbacks in Iterative reconstruction (IR) techniques such as negative image texture and nonlinear spatial resolutions, DLIRs are gradually replacing them. However, the potential use of DLIR in Head and Chest CT has to be examined further. Hence, the purpose of the study is to review the influence of DLIR on Radiation dose (RD), Image noise (IN), and outcomes of the studies compared with IR and FBP in Head and Chest CT examinations.

Methods

We performed a detailed search in PubMed, Scopus, Web of Science, Cochrane Library, and Embase to find the articles reported using DLIR for Head and Chest CT examinations between 2017 to 2023. Data were retrieved from the short-listed studies using Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines.

Results

Out of 196 articles searched, 15 articles were included. A total of 1292 sample size was included. 14 articles were rated as high and 1 article as moderate quality. All studies compared DLIR to IR techniques. 5 studies compared DLIR with IR and FBP. The review showed that DLIR improved IQ, and reduced RD and IN for CT Head and Chest examinations.

Conclusions

DLIR algorithm have demonstrated a noted enhancement in IQ with reduced IN for CT Head and Chest examinations at lower dose compared with IR and FBP. DLIR showed potential for enhancing patient care by reducing radiation risks and increasing diagnostic accuracy.

Optimization of the "Perth CT" Protocol for Preoperative Planning and Postoperative Evaluation in Total Knee Arthroplasty

Background and Objectives: Total knee arthroplasty (TKA) has become the treatment of choice for advanced osteoarthritis. The aim of this paper was to show the possibilities of optimizing the Perth CT protocol, which is highly effective for preoperative planning and postoperative assessment of alignment. Materials and Methods: The cross-sectional study comprised 16 patients for preoperative planning or postoperative evaluation of TKA. All patients were examined with the standard and optimized Perth CT protocol using advance techniques, including automatic exposure control (AEC), iterative image reconstruction (IR), as well as a single-energy projection-based metal artifact reduction algorithm for eliminating prosthesis artifacts. The effective radiation dose (E) was determined based on the dose report. Imaging quality is determined according to subjective and objective (values of signal to noise ratio (SdNR) and figure of merit (FOM)) criteria. Results: The effective radiation dose with the optimized protocol was significantly lower compared to the standard protocol (p < 0.001), while in patients with the knee prosthesis, E increased significantly less with the optimized protocol compared to the standard protocol. No significant difference was observed in the subjective evaluation of image quality between protocols (p > 0.05). Analyzing the objective criteria for image quality optimized protocols resulted in lower SdNR values and higher FOM values. No significant difference of image quality was determined using the SdNR and FOM as per the specified protocols and parts of extremities, and for the presence of prothesis. Conclusions: Retrospecting the ALARA ('As Low As Reasonably Achievable') principles, it is possible to optimize the Perth CT protocol by reducing the kV and mAs values and by changing the collimation and increasing the pitch factor. Advanced IR techniques were used in both protocols, and AEC was used in the optimized protocol. The effective dose of radiation can be reduced five times, and the image quality will be satisfactory.

The Use of Low-Dose Chest Computed Tomography for the Diagnosis and Monitoring of Pulmonary Infections in Patients with Hematologic Malignancies

The study aimed to assess the image quality and diagnostic performance of low-dose Chest Computed Tomography (LDCCT) in detecting pulmonary infections in patients with hematologic malignancies. A total of 164 neutropenic patients underwent 256 consecutive CT examinations, comparing 149 LDCCT and 107 Standard-Dose Chest CT (SDCCT) between May 2015 and June 2019. LDCCT demonstrated a 47% reduction in radiation dose while maintaining acceptable image noise and quality compared to SDCCT. However, LDCCT exhibited lower sensitivity in detecting consolidation (27.5%) and ground glass opacity (64.4%) compared to SDCCT (45.8% and 82.2%, respectively) with all the respective p-values from unadjusted and adjusted for sex, age, and BMI analyses being lower than 0.006 and the corresponding Odds Ratios of detection ranging from 0.30 to 0.34. Similar trends were observed for nodules ≥3 mm and ground glass halo in nodules but were not affected by sex, age and BMI. No significant differences were found for cavitation in nodules, diffuse interlobular septal thickening, pleural effusion, pericardial effusion, and lymphadenopathy. In conclusion, LDCCT achieved substantial dose reduction with satisfactory image quality but showed limitations in detecting specific radiologic findings associated with pulmonary infections in neutropenic patients compared to SDCCT.

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

BACKGROUND

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.

OBJECTIVE

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).

METHODS

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).

RESULTS

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).

CONCLUSION

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.

CLINICAL IMPACT

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.

Multi-Scale Feature Fusion Network for Low-Dose CT Denoising

Computed tomography (CT) is an imaging technique extensively used in medical treatment, but too much radiation dose in a CT scan will cause harm to the human body. Decreasing the dose of radiation will result in increased noise and artifacts in the reconstructed image, blurring the internal tissue and edge details. To get high-quality CT images, we present a multi-scale feature fusion network (MSFLNet) for low-dose CT (LDCT) denoising. In our MSFLNet, we combined multiple feature extraction modules, effective noise reduction modules, and fusion modules constructed using the attention mechanism to construct a horizontally connected multi-scale structure as the overall architecture of the network, which is used to construct different levels of feature maps at all scales. We innovatively define a composite loss function composed of pixel-level loss based on MS-SSIM-L1 and edge-based edge loss for LDCT denoising. In short, our approach learns a rich set of features that combine contextual information from multiple scales while maintaining the spatial details of denoised CT images. Our laboratory results indicate that compared with the existing methods, the peak signal-to-noise ratio (PSNR) value of CT images of the AAPM dataset processed by the new model is 33.6490, and the structural similarity (SSIM) value is 0.9174, which also achieves good results on the Piglet dataset with different doses. The results also show that the method removes noise and artifacts while effectively preserving CT images' architecture and grain information.

How to Evaluate Fibrosis in IBD?

In this review, we will describe the importance of fibrosis in inflammatory bowel disease (IBD) by discussing its distinct impact on Crohn's disease (CD) and ulcerative colitis (UC) through their translation to histopathology. We will address the existing knowledge on the correlation between inflammation and fibrosis and the still not fully explained inflammation-independent fibrogenesis. Finally, we will compile and discuss the recent advances in the noninvasive assessment of intestinal fibrosis, including imaging and biomarkers. Based on the available data, none of the available cross-sectional imaging (CSI) techniques has proved to be capable of measuring CD fibrosis accurately, with MRE showing the most promising performance along with elastography. Very recent research with radiomics showed encouraging results, but further validation with reliable radiomic biomarkers is warranted. Despite the interesting results with micro-RNAs, further advances on the topic of fibrosis biomarkers depend on the development of robust clinical trials based on solid and validated endpoints. We conclude that it seems very likely that radiomics and AI will participate in the future non-invasive fibrosis assessment by CSI techniques in IBD. However, as of today, surgical pathology remains the gold standard for the diagnosis and quantification of intestinal fibrosis in IBD.

Dual-domain fusion deep convolutional neural network for low-dose CT denoising

BACKGROUND

In view of the underlying health risks posed by X-ray radiation, the main goal of the present research is to achieve high-quality CT images at the same time as reducing x-ray radiation. In recent years, convolutional neural network (CNN) has shown excellent performance in removing low-dose CT noise. However, previous work mainly focused on deepening and feature extraction work on CNN without considering fusion of features from frequency domain and image domain.

OBJECTIVE

To address this issue, we propose to develop and test a new LDCT image denoising method based on a dual-domain fusion deep convolutional neural network (DFCNN).

METHODS

This method deals with two domains, namely, the DCT domain and the image domain. In the DCT domain, we design a new residual CBAM network to enhance the internal and external relations of different channels while reducing noise to promote richer image structure information. For the image domain, we propose a top-down multi-scale codec network as a denoising network to obtain more acceptable edges and textures while obtaining multi-scale information. Then, the feature images of the two domains are fused by a combination network.

RESULTS

The proposed method was validated on the Mayo dataset and the Piglet dataset. The denoising algorithm is optimal in both subjective and objective evaluation indexes as compared to other state-of-the-art methods reported in previous studies.

CONCLUSIONS

The study results demonstrate that by applying the new fusion model denoising, denoising results in both image domain and DCT domain are better than other models developed using features extracted in the single image domain.

Iterative Reconstruction: State-of-the-Art and Future Perspectives

ABSTRACT

Image reconstruction processing in computed tomography (CT) has evolved tremendously since its creation, succeeding at optimizing radiation dose while maintaining adequate image quality. Computed tomography vendors have developed and implemented various technical advances, such as automatic noise reduction filters, automatic exposure control, and refined imaging reconstruction algorithms.Focusing on imaging reconstruction, filtered back-projection has represented the standard reconstruction algorithm for over 3 decades, obtaining adequate image quality at standard radiation dose exposures. To overcome filtered back-projection reconstruction flaws in low-dose CT data sets, advanced iterative reconstruction algorithms consisting of either backward projection or both backward and forward projections have been developed, with the goal to enable low-dose CT acquisitions with high image quality. Iterative reconstruction techniques play a key role in routine workflow implementation (eg, screening protocols, vascular and pediatric applications), in quantitative CT imaging applications, and in dose exposure limitation in oncologic patients.Therefore, this review aims to provide an overview of the technical principles and the main clinical application of iterative reconstruction algorithms, focusing on the strengths and weaknesses, in addition to integrating future perspectives in the new era of artificial intelligence.

Technical note: Phantom-based training framework for convolutional neural network CT noise reduction

BACKGROUND

Deep artificial neural networks such as convolutional neural networks (CNNs) have been shown to be effective models for reducing noise in CT images while preserving anatomic details. A practical bottleneck for developing CNN-based denoising models is the procurement of training data consisting of paired examples of high-noise and low-noise CT images. Obtaining these paired data are not practical in a clinical setting where the raw projection data is not available. This work outlines a technique to optimize CNN denoising models using methods that are available in a routine clinical setting.

PURPOSE

To demonstrate a phantom-based training framework for CNN noise reduction that can be efficiently implemented on any CT scanner.

METHODS

The phantom-based training framework uses supervised learning in which training data are synthesized using an image-based noise insertion technique. Ten patient image series were used for training and validation (9:1) and noise-only images obtained from anthropomorphic phantom scans. Phantom noise-only images were superimposed on patient images to imitate low-dose CT images for use in training. A modified U-Net architecture was used with mean-squared-error and feature reconstruction loss. The training framework was tested for clinically indicated whole-body-low-dose CT images, as well as routine abdomen-pelvis exams for which projection data was unavailable. Performance was assessed based on root-mean-square error, structural similarity, line profiles, and visual assessment.

RESULTS

When the CNN was tested on five reserved quarter-dose whole-body-low-dose CT images, noise was reduced by 75%, root-mean-square-error reduced by 34%, and structural similarity increased by 60%. Visual analysis and line profiles indicated that the method significantly reduced noise while maintaining spatial resolution of anatomic features.

CONCLUSION

The proposed phantom-based training framework demonstrated strong noise reduction while preserving spatial detail. Because this method is based within the image domain, it can be easily implemented without access to projection data.

No-reference perceptual CT image quality assessment based on a self-supervised learning framework

Accurate image quality assessment (IQA) is crucial to optimize computed tomography (CT) image protocols while keeping the radiation dose as low as reasonably achievable. In the medical domain, IQA is based on how well an image provides a useful and efficient presentation necessary for physicians to make a diagnosis. Moreover, IQA results should be consistent with radiologists’ opinions on image quality, which is accepted as the gold standard for medical IQA. As such, the goals of medical IQA are greatly different from those of natural IQA. In addition, the lack of pristine reference images or radiologists’ opinions in a real-time clinical environment makes IQA challenging. Thus, no-reference IQA (NR-IQA) is more desirable in clinical settings than full-reference IQA (FR-IQA). Leveraging an innovative self-supervised training strategy for object detection models by detecting virtually inserted objects with geometrically simple forms, we propose a novel NR-IQA method, named deep detector IQA (D2IQA), that can automatically calculate the quantitative quality of CT images. Extensive experimental evaluations on clinical and anthropomorphic phantom CT images demonstrate that our D2IQA is capable of robustly computing perceptual image quality as it varies according to relative dose levels. Moreover, when considering the correlation between the evaluation results of IQA metrics and radiologists’ quality scores, our D2IQA is marginally superior to other NR-IQA metrics and even shows performance competitive with FR-IQA metrics.

Contrast-Enhanced Chest Computed Tomography (CT) Scan with Low Radiation and Total Iodine Dose for Lung Cancer Detection Using Adaptive Statistical Iterative Reconstruction

Background: Contrast-enhanced chest computed tomography (CT) is useful for the detection and follow-up of patients with lung cancer. However, reaching balance between diagnostic image quality, radiation dose, and iodixanol dose is a cause of concern. Objectives: To investigate the clinical value of adaptive statistical iterative reconstruction (ASIR) in reducing the iodixanol content and radiation dose during contrast-enhanced chest CT scan for patients diagnosed with lung masses/nodules based on the analysis of image quality. Methods: This prospective study was conducted on 80 patients diagnosed with nodules or masses, who required contrast-enhanced chest CT scans. The experimental group (n = 40) was subjected to iohexol at a high concentration (350 mgI/L) with a tube voltage of 120 kVp and a filter back projection (FBP) reconstruction algorithm. The comparison group (n = 40) was subject to iodixanol at a lower concentration (270 mgI/L) with a tube voltage of 100 kVp and ASIR (blending ratio, 40%). The radiation dose and total iodixanol content, as well as subjective and objective evaluations of image quality, were analyzed and compared. Results: The two groups obtained non-significantly different subjective scores for five structures detected in the lung window and five structures detected in the mediastinal window, as well as the overall image (P > 0.05 for all). Both the two-group images obtained diagnosis-acceptable scores (≥ 3 points) on displays of 10 structures and overall image quality. The mean CT value of vessels (100 kVp vs. 120 kVp: 314.90 ± 23.42 vs. 308.93 ± 21.40; P > 0.05), standard deviation (13.03 ± 0.88 vs.12.83 ± 0.90; P > 0.05), and contrast-to-noise ratio (20.77 ± 2.20 vs. 20.36 ± 1.94; P > 0.05) were not significantly different between two groups. However, the CT dose index, dose-length product, effective dose, and total iodine dose were reduced by 27.58%, 36.65%, 36.59%, and 22.86% in the 100-kVp group compared to the 120-kVp group. Conclusions: The ASIR showed great potential in reducing the radiation dose and iodine contrast dose, while maintaining good image quality and providing strong confidence for the diagnosis of lung cancer.

Using barium as an internal radioprotective shield for pregnant patients undergoing CT pulmonary angiography: A retrospective study

PURPOSE

The purpose of our retrospective study was to assess the effect of barium sulfate contrast medium on radiation dose and diagnostic quality of CT Pulmonary Angiography (CTPA) in an in-vivo study of pregnant patients.

METHODS

Our retrospective study included 33 pregnant patients who underwent CTPA to exclude pulmonary embolism. The patients received oral 40% w/v barium solution just prior to the acquisition of their planning radiograph. All CTPA were performed on 64-slice, single-source CT scanners with AEC with noise index = 28.62-31.64 and the allowed mA range of 100-450. However, only 5/33 patients had mA modulation (AEC 100-450 mA range), while 28/33 patients had mA maxed out at the set maximum mA of 450 over the entire scan range. We recorded CTDIvol (mGy), DLP (mGy.cm) and scan length. The same information was recorded in weight-and scanner-matched, non-pregnant patients. Statistical tests included descriptive data (median and interquartile range) and Mann-Whitney test.

RESULTS

There were no significant differences in CTDIvol and DLP between the barium and control group patients (p > 0.1). The median mA below the diaphragm was significantly higher in each patient with barium compared to the weight and scanner-matched patient without barium. Evaluation of lung and subsegmental lower lobe pulmonary arteries was limited in 85% barium group. Due to thin prospective section thickness (1.25 mm), most patients were scanned at maximum allowed mA for AEC.

CONCLUSION

Use of AEC with thick barium in pregnant patients undergoing CTPA as an internal radioprotective shield produces counterproductive artifacts and tube current increments.

Quantitative Computed Tomography: What Clinical Questions Can it Answer in Chronic Lung Disease?

Quantitative computed tomography (QCT) has recently gained an important role in the functional assessment of chronic lung disease. Its capacity in diagnostic, staging, and prognostic evaluation in this setting is similar to that of traditional pulmonary function testing. Furthermore, it can demonstrate lung injury before the alteration of pulmonary function test parameters, and it enables the classification of disease phenotypes, contributing to the customization of therapy and performance of comparative studies without the intra- and inter-observer variation that occurs with qualitative analysis. In this review, we address technical issues with QCT analysis and demonstrate the ability of this modality to answer clinical questions encountered in daily practice in the management of patients with chronic lung disease.

Image quality and radiologists' subjective acceptance using model-based iterative and deep learning reconstructions as adjuncts to ultrahigh-resolution CT in low-dose contrast-enhanced abdominopelvic CT: phantom and clinical pilot studies

Purpose

In contrast-enhanced abdominopelvic CT (CE-APCT) for oncologic follow-up, ultrahigh-resolution CT (UHRCT) may improve depiction of fine lesions and low-dose scans are desirable for minimizing the potential adverse effects by ionizing radiation. We compared image quality and radiologists’ acceptance of model-based iterative (MBIR) and deep learning (DLR) reconstructions of low-dose CE-APCT by UHRCT.

Methods

Using our high-resolution (matrix size: 1024) and low-dose (tube voltage 100 kV; noise index: 20–40 HU) protocol, we scanned phantoms to compare the modulation transfer function and noise power spectrum between MBIR and DLR and assessed findings in 36 consecutive patients who underwent CE-APCT (noise index: 35 HU; mean CTDI_vol: 4.2 ± 1.6 mGy) by UHRCT. We used paired t-test to compare objective noise and contrast-to-noise ratio (CNR) and Wilcoxon signed-rank test to compare radiologists’ subjective acceptance regarding noise, image texture and appearance, and diagnostic confidence between MBIR and DLR using our routine protocol (matrix size: 512; tube voltage: 120 kV; noise index: 15 HU) for reference.

Results

Phantom studies demonstrated higher spatial resolution and lower low-frequency noise by DLR than MBIR at equal doses. Clinical studies indicated significantly worse objective noise, CNR, and subjective noise by DLR than MBIR, but other subjective characteristics were better (P < 0.001 for all). Compared with the routine protocol, subjective noise was similar or better by DLR, and other subjective characteristics were similar or worse by MBIR.

Conclusion

Image quality, except regarding noise characteristics, and acceptance by radiologists were better by DLR than MBIR in low-dose CE-APCT by UHRCT.

Graphical abstract

Clinical evaluation of a phantom-based deep convolutional neural network for whole-body-low-dose and ultra-low-dose CT skeletal surveys

OBJECTIVE

This study evaluated the clinical utility of a phantom-based convolutional neural network noise reduction framework for whole-body-low-dose CT skeletal surveys.

MATERIALS AND METHODS

The CT exams of ten patients with multiple myeloma were retrospectively analyzed. Exams were acquired with routine whole-body-low-dose CT protocol and projection noise insertion was used to simulate 25% dose exams. Images were reconstructed with either iterative reconstruction or filtered back projection with convolutional neural network post-processing. Diagnostic quality and structure visualization were blindly rated (subjective scale ranging from 0 [poor] to 100 [excellent]) by three musculoskeletal radiologists for iterative reconstruction and convolutional neural network images at routine whole-body-low-dose and 25% dose CT.

RESULTS

For the diagnostic quality rating, the convolutional neural network outscored iterative reconstruction at routine whole-body-low-dose CT (convolutional neural network: 95 ± 5, iterative reconstruction: 85 ± 8) and at the 25% dose level (convolutional neural network: 79 ± 10, iterative reconstruction: 22 ± 13). Convolutional neural network applied to 25% dose was rated inferior to iterative reconstruction applied to routine dose. Similar trends were observed in rating experiments focusing on structure visualization.

CONCLUSION

Results indicate that the phantom-based convolutional neural network noise reduction framework can improve visualization of critical structures within CT skeletal surveys. At matched dose level, the convolutional neural network outscored iterative reconstruction for all conditions studied. The image quality improvement of convolutional neural network applied to 25% dose indicates a potential for dose reduction; however, the 75% dose reduction condition studied is not currently recommended for clinical implementation.

Noise Conscious Training of Non Local Neural Network Powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising

The explosive rise of the use of Computer tomography (CT) imaging in medical practice has heightened public concern over the patient's associated radiation dose. On the other hand, reducing the radiation dose leads to increased noise and artifacts, which adversely degrades the scan's interpretability. In recent times, the deep learning-based technique has emerged as a promising method for low dose CT(LDCT) denoising. However, some common bottleneck still exists, which hinders deep learning-based techniques from furnishing the best performance. In this study, we attempted to mitigate these problems with three novel accretions. First, we propose a novel convolutional module as the first attempt to utilize neighborhood similarity of CT images for denoising tasks. Our proposed module assisted in boosting the denoising by a significant margin. Next, we moved towards the problem of non-stationarity of CT noise and introduced a new noise aware mean square error loss for LDCT denoising. The loss mentioned above also assisted to alleviate the laborious effort required while training CT denoising network using image patches. Lastly, we propose a novel discriminator function for CT denoising tasks. The conventional vanilla discriminator tends to overlook the fine structural details and focus on the global agreement. Our proposed discriminator leverage self-attention and pixel-wise GANs for restoring the diagnostic quality of LDCT images. Our method validated on a publicly available dataset of the 2016 NIH-AAPM-Mayo Clinic Low Dose CT Grand Challenge performed remarkably better than the existing state of the art method. The corresponding source code is available at: https://github.com/reach2sbera/ldct_nonlocal.

Noise reduction profile: A new method for evaluation of noise reduction techniques in CT

Purpose

Noise power spectrum (NPS) is a commonly used performance metric to evaluate noise‐reduction techniques (NRT) in imaging systems. The images reconstructed with and without an NRT can be compared via their NPS to better understand the NRT's effects on image noise. However, when comparing NPSs, simple visual assessments or a comparison of NPS peaks or medians are often used. These assessments make it difficult to objectively evaluate the effect of noise reduction across all spatial frequencies. In this work, we propose a new noise reduction profile (NRP) to facilitate a more complete and objective evaluation of NPSs for a range of NRTs used specifically in computed tomography (CT).

Methods and materials

The homogeneous section of the ACR or Catphan phantoms was scanned on different CT scanners equipped with the following NRTs: AIDR3D, AiCE, ASiR, ASiR‐V, TrueFidelity, iDose, SAFIRE, and ADMIRE. The images were then reconstructed with all strengths of each NRT in reference to the baseline filtered back projection (FBP) images. One set of the baseline FBP images was also processed with PixelShine, an NRT based on artificial intelligence. The NPSs of the images before and after noise reduction were calculated in both the xy‐plane and along the z‐direction. The difference in the logarithmic scale between each NPS (baseline FBP and NRT) was then calculated and deemed the NRP. Furthermore, the relationship between the NRP and NPS peak positions was mathematically analyzed.

Results

Each NRT has its own unique NRP. By comparing the NPS and NRP for each NRT, it was found that NRP is related to the peak shift of NPS. Additionally, under the assumption that the NPS has one peak and is differentiable, a relationship was mathematically derived between the slope of the NRP at the peak position of the NPS before noise reduction and the shift of the NPS peak position after noise reduction.

Conclusions

A new metric, NRP, was proposed based on NPS to objectively evaluate and compare methods for noise reduction in CT. The NRP can be used to compare the effects of various NRTs on image noise in both the xy‐plane and z‐direction. It also enables unbiased assessment of the detailed noise reduction properties of each NRT over all relevant spatial frequencies.

Conditional Generative Adversarial Networks for low-dose CT image denoising aiming at preservation of critical image content

X-ray Computed Tomography (CT) is an imaging modality where patients are exposed to potentially harmful ionizing radiation. To limit patient risk, reduced-dose protocols are desirable, which inherently lead to an increased noise level in the reconstructed CT scans. Consequently, noise reduction algorithms are indispensable in the reconstruction processing chain. In this paper, we propose to leverage a conditional Generative Adversarial Networks (cGAN) model, to translate CT images from low-to-routine dose. However, when aiming to produce realistic images, such generative models may alter critical image content. Therefore, we propose to employ a frequency-based separation of the input prior to applying the cGAN model, in order to limit the cGAN to high-frequency bands, while leaving low-frequency bands untouched. The results of the proposed method are compared to a state-of-the-art model within the cGAN model as well as in a single-network setting. The proposed method generates visually superior results compared to the single-network model and the cGAN model in terms of quality of texture and preservation of fine structural details. It also appeared that the PSNR, SSIM and TV metrics are less important than a careful visual evaluation of the results. The obtained results demonstrate the relevance of defining and separating the input image into desired and undesired content, rather than blindly denoising entire images. This study shows promising results for further investigation of generative models towards finding a reliable deep learning-based noise reduction algorithm for low-dose CT acquisition.

Image Quality Assessment of Low-Dose CT using Hybrid Iterative Reconstruction

Abstract Background: X-ray computed tomography is the first imaging technology that supports accurate nondestructive interior image reconstruction of an object from sufficient projection data. Low-dose computed tomography (LDCT) has been considered to relieve the harm to patients caused by X-ray radiation. However, LDCT images can be degraded by quantum noise and streak artifacts.Methods: The objective of the authors’ study is to evaluate the optimal level of the hybrid iterative reconstruction (HIR) that generates images with the best diagnostic quality on different dose and noise levels. HIR with optimizations is proposed to reduce image noise and provide better performance at a low dose. The Catphan®504 phantom is employed to assess various image qualities (IQ).Results: For any given scanning protocols, there is linear noise reduction and linear increase of contrast-to-noise ratio (CNR) using optimal HIR. The evidence from various module tests demonstrates that the shape of the noise power spectrum is continuously shifted to low frequency with increasing HIR levels compared with that of filtered-back-projection (FBP). This may describe the difference between the human observer performance and features of the ideal low-contrast objects.Conclusion: Optimal HIR is clearly demonstrated to be a superior method for reducing image noise and improving CNR compared to FBP. Optimal HIR also inhibits texture change or spectrum shift compared with the pure IR method. Even though there are continuous noise reduction and CNR increase with HIR at increasing levels, the human observer performance does not seem to improve simultaneously due to coarser noise (low-frequency noise). HIR level 3 to 5 is optimal for their study. It is possible for the optimal HIR to offer equivalent diagnostic IQ at a lower dose compared with FBP at a routine dose.

Evaluating a Convolutional Neural Network Noise Reduction Method When Applied to CT Images Reconstructed Differently Than Training Data

OBJECTIVE

The aim of this study was to evaluate a narrowly trained convolutional neural network (CNN) denoising algorithm when applied to images reconstructed differently than training data set.

METHODS

A residual CNN was trained using 10 noise inserted examinations. Training images were reconstructed with 275 mm of field of view (FOV), medium smooth kernel (D30), and 3 mm of thickness. Six examinations were reserved for testing; these were reconstructed with 100 to 450 mm of FOV, smooth to sharp kernels, and 1 to 5 mm of thickness.

RESULTS

When test and training reconstruction settings were not matched, there was either reduced denoising efficiency or resolution degradation. Denoising efficiency was reduced when FOV was decreased or a smoother kernel was used. Resolution loss occurred when the network was applied to an increased FOV, sharper kernel, or decreased image thickness.

CONCLUSIONS

The CNN denoising performance was degraded with variations in FOV, kernel, or decreased thickness. Denoising performance was not affected by increased thickness.

CT Noise-Reduction Methods for Lower-Dose Scanning: Strengths and Weaknesses of Iterative Reconstruction Algorithms and New Techniques

Iterative reconstruction (IR) algorithms are the most widely used CT noise-reduction method to improve image quality and have greatly facilitated radiation dose reduction within the radiology community. Various IR methods have different strengths and limitations. Because IR algorithms are typically nonlinear, they can modify spatial resolution and image noise texture in different regions of the CT image; hence traditional image-quality metrics are not appropriate to assess the ability of IR to preserve diagnostic accuracy, especially for low-contrast diagnostic tasks. In this review, the authors highlight emerging IR algorithms and CT noise-reduction techniques and summarize how these techniques can be evaluated to help determine the appropriate radiation dose levels for different diagnostic tasks in CT. In addition to advanced IR techniques, we describe novel CT noise-reduction methods based on convolutional neural networks (CNNs). CNN-based noise-reduction techniques may offer the ability to reduce image noise while maintaining high levels of image detail but may have unique drawbacks. Other novel CT noise-reduction methods are being developed to leverage spatial and/or spectral redundancy in multiphase or multienergy CT. Radiologists and medical physicists should be familiar with these different alternatives to adapt available CT technology for different diagnostic tasks. The scope of this article is (a) to review the clinical applications of IR algorithms as well as their strengths, weaknesses, and methods of assessment and (b) to explore new CT image reconstruction and noise-reduction techniques that promise to facilitate radiation dose reduction. ^©RSNA, 2021.

Dose reduction potential of vendor-agnostic deep learning model in comparison with deep learning-based image reconstruction algorithm on CT: a phantom study

Objectives

To compare the dose reduction potential (DRP) of a vendor-agnostic deep learning model (DLM, ClariCT.AI) with that of a vendor-specific deep learning–based image reconstruction algorithm (DLR, TrueFidelity™).

Methods

Computed tomography (CT) images of a multi-sized image quality phantom (Mercury v4.0) were acquired under six radiation dose levels (0.48/0.97/1.93/3.87/7.74/15.47 mGy) and were reconstructed using filtered back projection (FBP) and three strength levels of the DLR (low/medium/high). The FBP images were denoised using the DLM. For all DLM and DLR images, the detectability index (d′) (a task-based detection performance metric) was obtained, under various combinations of three target sizes (10/5/1 mm), five inlets (CT value difference with the background; −895/50/90/335/1000 HU), five phantom diameters (36/31/26/21/16 cm), and six radiation dose levels. Dose reduction potential (DRP) measures the dose reduction made by using DLM or DLR, while yielding d′ equivalent to that of FBP at full dose.

Results

The DRPs of the DLM, DLR-low, DLR-medium, and DLR-high were 86% (81–88%), 60% (46–67%), 76% (60–81%), and 87% (78–92%), respectively. For 10-mm targets, the DRP of the DLM (87%) was higher than that of all DLR algorithms (58–86%). However, for smaller targets (5 mm/1 mm), the DRPs of the DLR-high (89/88%) were greater than those of the DLM (87/84%).

Conclusion

The dose reduction potential of the vendor-agnostic DLM was shown to be comparable to that of the vendor-specific DLR at high strength and superior to those of the DLRs at medium and low strengths.

Key Points

• DRP of the vendor-agnostic model was comparable to that of high-strength vendor-specific model and superior to those of medium- and low-strength models.

• Under various radiation dose levels, the deep learning model shows higher detectability indexes compared to FBP.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-08199-9.

Artificial intelligence in medical imaging: implications for patient radiation safety

Artificial intelligence, including deep learning, is currently revolutionising the field of medical imaging, with far reaching implications for almost every facet of diagnostic imaging, including patient radiation safety. This paper introduces basic concepts in deep learning and provides an overview of its recent history and its application in tomographic reconstruction as well as other applications in medical imaging to reduce patient radiation dose, as well as a brief description of previous tomographic reconstruction techniques. This review also describes the commonly used deep learning techniques as applied to tomographic reconstruction and draws parallels to current reconstruction techniques. Finally, this paper reviews some of the estimated dose reductions in CT and positron emission tomography in the recent literature enabled by deep learning, as well as some of the potential problems that may be encountered such as the obscuration of pathology, and highlights the need for additional clinical reader studies from the imaging community.

Improved dynamic imaging of multiphase flow by constrained tomographic reconstruction

Dynamic tomography has become an important technique to study fluid flow processes in porous media. The use of laboratory X-ray tomography instruments is, however, limited by their low X-ray brilliance. The prolonged exposure times, in turn, greatly limit temporal resolution. We have developed a tomographic reconstruction algorithm that maintains high image quality, despite reducing the exposure time and the number of projections significantly. Our approach, based on the Simultaneous Iterative Reconstruction Technique, mitigates the problem of few and noisy exposures by utilising a high-quality scan of the system before the dynamic process is started. We use the high-quality scan to initialise the first time step of the dynamic reconstruction. We further constrain regions of the dynamic reconstruction with a segmentation of the static system. We test the performance of the algorithm by reconstructing the dynamics of fluid separation in a multiphase system. The algorithm is compared quantitatively and qualitatively with several other reconstruction algorithms and we show that it can maintain high image quality using only a fraction of the normally required number of projections and with a substantially larger noise level. By robustly allowing fewer projections and shorter exposure, our algorithm enables the study of faster flow processes using laboratory tomography instrumentation but it can also be used to improve the reconstruction quality of dynamic synchrotron experiments.

Best Practices: Imaging Strategies for Reduced-Dose Chest CT in the Management of Cystic Fibrosis-Related Lung Disease

OBJECTIVE. Cystic fibrosis (CF) is a multisystemic life-limiting disorder. The leading cause of morbidity in CF is chronic pulmonary disease. Chest CT is the reference standard for detection of bronchiectasis. Cumulative ionizing radiation limits the use of CT, particularly as treatments improve and life expectancy increases. The purpose of this article is to summarize the evidence on low-dose chest CT and its effect on image quality to determine best practices for imaging in CF. CONCLUSION. Low-dose chest CT is technically feasible, reduces dose, and renders satisfactory image quality. There are few comparison studies of low-dose chest CT and standard chest CT in CF; however, evidence suggests equivalent diagnostic capability. Low-dose chest CT with iterative reconstructive algorithms appears superior to chest radiography and equivalent to standard CT and has potential for early detection of bronchiectasis and infective exacerbations, because clinically significant abnormalities can develop in patients who do not have symptoms. Infection and inflammation remain the primary causes of morbidity requiring early intervention. Research gaps include the benefits of replacing chest radiography with low-dose chest CT in terms of improved diagnostic yield, clinical decision making, and patient outcomes. Longitudinal clinical studies comparing CT with MRI for the monitoring of CF lung disease may better establish the complementary strengths of these imaging modalities.

Protocol Optimization Considerations for Implementing Deep Learning CT Reconstruction

OBJECTIVE. Previous advances over filtered back projection (FBP) have incorporated model-based iterative reconstruction. The purpose of this study was to characterize the latest advance in image reconstruction, that is, deep learning. The focus was on applying characterization results of a deep learning approach to decisions about clinical CT protocols. MATERIALS AND METHODS. A proprietary deep learning image reconstruction (DLIR) method was characterized against an existing advanced adaptive statistical iterative reconstruction method (ASIR-V) and FBP from the same vendor. The metrics used were contrast-to-noise ratio, spatial resolution as a function of contrast level, noise texture (i.e., noise power spectra [NPS]), noise scaling as a function of slice thickness, and CT number consistency. The American College of Radiology accreditation phantom and a uniform water phantom were used at a range of doses and slice thicknesses for both axial and helical acquisition modes. RESULTS. ASIR-V and DLIR were associated with improved contrast-to-noise ratio over FBP for all doses and slice thicknesses. No dose or contrast dependencies of spatial resolution were observed for ASIR-V or DLIR. NPS results showed DLIR maintained an FBP-like noise texture whereas ASIR-V shifted the NPS to lower frequencies. Noise changed with dose and slice thickness in the same manner for ASIR-V and FBP. DLIR slice thickness noise scaling differed from FBP, exhibiting less noise penalty with decreasing slice thickness. No clinically significant changes were observed in CT numbers for any measurement condition. CONCLUSION. In a phantom model, DLIR does not suffer from the concerns over reduction in spatial resolution and introduction of poor noise texture associated with previous methods.

Low-dose CT urography using deep learning image reconstruction: a prospective study for comparison with conventional CT urography

OBJECTIVES

To compare the image quality of low-dose CT urography (LD-CTU) using deep learning image reconstruction (DLIR) with conventional CTU (C-CTU) using adaptive statistical iterative reconstruction (ASIR-V).

METHODS

This was a prospective, single-institutional study using the excretory phase CTU images for analysis. Patients were assigned to the LD-DLIR group (100kV and automatic mA modulation for noise index (NI) of 23) and C-ASIR-V group (100kV and NI of 10) according to the scan protocols in the excretory phase. Two radiologists independently assessed the overall image quality, artifacts, noise and sharpness of urinary tracts. Additionally, the mean CT attenuation, signal-to-noise ratio (SNR) and contrast-to-noise (CNR) in the urinary tracts were evaluated.

RESULTS

26 patients each were included in the LD-DLIR group (10 males and 16 females; mean age: 57.23 years, range: 33-76 years) and C-ASIR-V group (14 males and 12 females; mean age: 60 years, range: 33-77 years). LD-DLIR group used a significantly lower effective radiation dose compared with the C-ASIR-V group (2.01 ± 0.44 mSv vs 6.9 ± 1.46 mSv, p < 0.001). LD-DLIR group showed good overall image quality with average score >4 and was similar to that of the C-ASIR-V group. Both groups had adequate and similar attenuation value, SNR and CNR in most segments of urinary tracts.

CONCLUSION

It is feasibility to provide comparable image quality while reducing 71% radiation dose in low-dose CTU with a deep learning image reconstruction algorithm compared to the conventional CTU with ASIR-V.

ADVANCES IN KNOWLEDGE

(1) CT urography with deep learning reconstruction algorithm can reduce the radiation dose by 71% while still maintaining image quality.

Low-dose whole-body CT using deep learning image reconstruction: image quality and lesion detection

OBJECTIVES

To evaluate image quality and lesion detection capabilities of low-dose (LD) portal venous phase whole-body computed tomography (CT) using deep learning image reconstruction (DLIR).

METHODS

The study cohort of 59 consecutive patients (mean age, 67.2 years) who underwent whole-body LD CT and a prior standard-dose (SD) CT reconstructed with hybrid iterative reconstruction (SD-IR) within one year for surveillance of malignancy were assessed. The LD CT images were reconstructed with hybrid iterative reconstruction of 40% (LD-IR) and DLIR (LD-DLIR). The radiologists independently evaluated image quality (5-point scale) and lesion detection. Attenuation values in Hounsfield units (HU) of the liver, pancreas, spleen, abdominal aorta, and portal vein; the background noise and signal-to-noise ratio (SNR) of the liver, pancreas, and spleen were calculated. Qualitative and quantitative parameters were compared between the SD-IR, LD-IR, and LD-DLIR images. The CT dose-index volumes (CTDI_vol) and dose-length product (DLP) were compared between SD and LD scans.

RESULTS

The image quality and lesion detection rate of the LD-DLIR was comparable to the SD-IR. The image quality was significantly better in SD-IR than in LD-IR (p < 0.017). The attenuation values of all anatomical structures were comparable between the SD-IR and LD-DLIR (p = 0.28-0.96). However, background noise was significantly lower in the LD-DLIR (p < 0.001) and resulted in improved SNRs (p < 0.001) compared to the SD-IR and LD-IR images. The mean CTDI_vol and DLP were significantly lower in the LD (2.9 mGy and 216.2 mGy•cm) than in the SD (13.5 mGy and 1011.6 mGy•cm) (p < 0.0001).

CONCLUSION

LD CT images reconstructed with DLIR enable radiation dose reduction of >75% while maintaining image quality and lesion detection rate and superior SNR in comparison to SD-IR.

ADVANCES IN KNOWLEDGE

Deep learning image reconstruction algorithm enables around 80% reduction in radiation dose while maintaining the image quality and lesion detection compared to standard-dose whole-body CT.

A prospective study on the use of ultralow-dose computed tomography with iterative reconstruction for the follow-up of patients liver and renal abscess

Background

Radiation dose reduction is a major concern in patients who undergo computed tomography (CT) to follow liver and renal abscess.

Objectives

The purpose of this study is to investigate the feasibility of ultralow-dose CT with iterative reconstruction (IR) to follow patients with liver and renal abscess.

Methods

This prospective study included 18 patients who underwent ultralow-dose CT with IR to follow abscesses (liver abscesses in 10 patients and renal abscesses in 8 patients; ULD group). The control group consisted of 14 patients who underwent follow-up standard-dose CT for liver abscesses during the same period. The objective image noise was evaluated by measuring standard deviation (SD) in the liver and subcutaneous fat to select a specific IR for qualitative analysis. Two radiologists independently evaluated subjective image quality, noise, and diagnostic confidence to evaluate abscess using a five-point Likert scale. Qualitative parameters were compared between the ULD and control groups with the Mann-Whitney U test.

Results

The mean CT dose index volume and dose length product of standard-dose CT were 8.7 ± 1.8 mGy and 555.8 ± 142.8 mGy·cm, respectively. Mean dose reduction of ultralow-dose CT was 71.8% compared to standard-dose CT. After measuring SDs, iDose level 5, which showed similar SD to standard-dose CT in both the subcutaneous fat and liver (P = 0.076, and P = 0.124), was selected for qualitative analysis. Ultralow-dose CT showed slightly worse subjective image quality (P < 0.001 for reader 1, and P = 0.005 for reader 2) and noise (P = 0.004 for reader 1, and P = 0.001 for reader 2) than standard-dose CT. However, the diagnostic confidence of ultralow-dose CT for evaluating abscess was comparably excellent to standard-dose CT (P = 0.808 for reader 1, and P = 0.301 for reader 2).

Conclusions

Ultralow-dose CT with IR can be used in the follow-up of liver and renal abscess with comparable diagnostic confidence.

Simulated Radiation Dose Reduction in Whole-Body CT on a 3rd Generation Dual-Source Scanner: An Intraindividual Comparison

To evaluate the effect of radiation dose reduction on image quality and diagnostic confidence in contrast-enhanced whole-body computed tomography (WBCT) staging. We randomly selected March 2016 for retrospective inclusion of 18 consecutive patients (14 female, 60 ± 15 years) with clinically indicated WBCT staging on the same 3rd generation dual-source CT. Using low-dose simulations, we created data sets with 100, 80, 60, 40, and 20% of the original radiation dose. Each set was reconstructed using filtered back projection (FBP) and Advanced Modeled Iterative Reconstruction (ADMIRE^®, Siemens Healthineers, Forchheim, Germany) strength 1–5, resulting in 540 datasets total. ADMIRE 2 was the reference standard for intraindividual comparison. The effective radiation dose was calculated using commercially available software. For comparison of objective image quality, noise assessments of subcutaneous adipose tissue regions were performed automatically using the software. Three radiologists blinded to the study evaluated image quality and diagnostic confidence independently on an equidistant 5-point Likert scale (1 = poor to 5 = excellent). At 100%, the effective radiation dose in our population was 13.3 ± 9.1 mSv. At 20% radiation dose, it was possible to obtain comparably low noise levels when using ADMIRE 5 (p = 1.000, r = 0.29). We identified ADMIRE 3 at 40% radiation dose (5.3 ± 3.6 mSv) as the lowest achievable radiation dose with image quality and diagnostic confidence equal to our reference standard (p = 1.000, r > 0.4). The inter-rater agreement for this result was almost perfect (ICC ≥ 0.958, 95% CI 0.909–0.983). On a 3rd generation scanner, it is feasible to maintain good subjective image quality, diagnostic confidence, and image noise in single-energy WBCT staging at dose levels as low as 40% of the original dose (5.3 ± 3.6 mSv), when using ADMIRE 3.

Impact of preset and postset adaptive statistical iterative reconstruction-V on image quality in nonenhanced abdominal-pelvic CT on wide-detector revolution CT

Background

Adaptive statistical iterative reconstruction-V technique (ASIR-V) is usually set at different strengths according to the different clinical requirements and scenarios encountered when setting scanning protocols, such as setting a more aggressive tube current reduction (defined as preset ASIR-V). Reconstruction with ASIR-V is useful after scanning using image algorithms to improve image quality (defined as postset ASIR-V). The aim of this study was to investigate the quality of images reconstructed with preset and postset ASIR-V, using the same noncontrast abdominal-pelvic computed tomography (CT) protocols in the same individual on a wide detector CT.

Methods

We prospectively enrolled 141 patients. The scan protocols in Groups A-E were 0%, 20%, 40%, 60%, and 80% preset ASIR-V, respectively, in the 256 wide-detector row Revolution CT (GE Healthcare, Waukesha, WI, USA). Each group was further divided into 5 subgroups with 0%, 20%, 40%, 60%, and 80% postset ASIR-V, respectively. The 64-detector Discovery 750 HDCT (GE, USA) was used for Group F as a control group, using 0%, 20%, 40%, 60%, and 80% ASIR, respectively. Image noise was measured in the spleen, aorta, and muscle. The CT attenuation and image noise were analyzed using the paired t-test; analysis of variance and post hoc multiple comparisons were made using the Student-Newman-Keuls (SNK) method.

Results

The CT attenuation in Groups A-F exhibited no significant difference between subgroups in three organs (P>0.05). Only with increasing preset ASIR-V% (Groups A to E), did the image noise decrease, except in Group B in the aorta and muscle (Noise_B > Noise_A, P_muscleA&B=0.233, P_aortaA&B=0.796). Only with increasing postset ASIR-V or ASIR% (Groups A and F), did the image noise decrease in the three organs. After preset and postset ASIR-V were combined, with preset ASIR-V% being equal to postset ASIR-V%, the image become similar to the corresponding preset ASIR-V part with the line of postset ASIR-V 0% (baseline of each group). When preset ASIR-V% was greater than the postset ASIR-V%, the image noise was higher than the baseline of each group. When preset ASIR-V% was less than the postset ASIR-V%, the image noise was lower than the baseline of each group. The radiation dose from B to E decreased from 11.2% to 57.1%. The CT dose index volume (CTDI_vol) and dose length product (DLP) in Group F were significantly higher than those in Group A.

Conclusions

Using both preset and postset ASIR-V allows dose reduction, with a potential to improve image quality only when postset ASIR-V% is higher than or equal to preset ASIR-V%. The image quality depends on postset ASIR-V%, whereas the decrease of radiation dose depends on preset ASIR-V%.

Whole Body Low Dose Computed Tomography Using Third-Generation Dual-Source Multidetector With Spectral Shaping: Protocol Optimization and Literature Review

For decades, the main imaging tool for multiple myeloma (MM) patient's management has been the conventional skeleton survey. In 2014 international myeloma working group defined the advantages of the whole-body low dose computed tomography (WBLDCT) as a gold standard, among imaging modalities, for bone disease assessment and subsequently implemented this technique in the MM diagnostic workflow. The aim of this study is to investigate, in a group of 30 patients with a new diagnosis of MM, the radiation dose (CT dose index, dose-length product, effective dose), the subjective image quality score and osseous/extra-osseous findings rate with a modified WBLDCT protocol. Spectral shaping and third-generation dual-source multidetector CT scanner was used for the assessment of osteolytic lesions due to MM, and the dose exposure was compared with the literature findings reported until 2020. Mean radiation dose parameters were reported as follows: CT dose index 0.3 ± 0.1 mGy, Dose-Length Product 52.0 ± 22.5 mGy*cm, effective dose 0.44 ± 0.19 mSv. Subjective image quality was good/excellent in all subjects. 11/30 patients showed osteolytic lesions, with a percentage of extra-osseous findings detected in 9/30 patients. Our data confirmed the advantages of WBLDCT in the diagnosis of patients with MM, reporting an effective dose for our protocol as the lowest among previous literature findings.

REDUCING ABSORBED DOSE TO THYROID IN NECK CT EXAMINATIONS: THE EFFECTS OF SABA SHIELDING

Bi shielding has been used for the protection of radiosensitive organs during computed tomography (CT) for 20 years. In 2017, American Association of Physicists in Medicine recommended against Bi shielding due to its degrading effects on image quality. Saba shielding introduced recently protecting organs as Bi shielding without degrading image quality. In this study, the Saba shield was modified and primary radiation attenuation values of the shields and entrance skin dose (ESD) on the thyroid were measured with and without shielding. Furthermore, the quality of images obtained using Saba shielding was investigated quantitatively and qualitatively. Saba and Bi shielding reduced the ESD on the thyroid by about 50%. Saba shielding had about 5-7 HU less noise and about 51-65 HU less CT numbers shift in comparison with Bi shielding at a distance of 1 cm from the shields. Saba shielding had no degrading effects on image quality in the patient study.

Low-Dose Abdominal CT Using a Deep Learning-Based Denoising Algorithm: A Comparison with CT Reconstructed with Filtered Back Projection or Iterative Reconstruction Algorithm

Objective

To compare the image quality of low-dose (LD) computed tomography (CT) obtained using a deep learning-based denoising algorithm (DLA) with LD CT images reconstructed with a filtered back projection (FBP) and advanced modeled iterative reconstruction (ADMIRE).

Materials and Methods

One hundred routine-dose (RD) abdominal CT studies reconstructed using FBP were used to train the DLA. Simulated CT images were made at dose levels of 13%, 25%, and 50% of the RD (DLA-1, -2, and -3) and reconstructed using FBP. We trained DLAs using the simulated CT images as input data and the RD CT images as ground truth. To test the DLA, the American College of Radiology CT phantom was used together with 18 patients who underwent abdominal LD CT. LD CT images of the phantom and patients were processed using FBP, ADMIRE, and DLAs (LD-FBP, LD-ADMIRE, and LD-DLA images, respectively). To compare the image quality, we measured the noise power spectrum and modulation transfer function (MTF) of phantom images. For patient data, we measured the mean image noise and performed qualitative image analysis. We evaluated the presence of additional artifacts in the LD-DLA images.

Results

LD-DLAs achieved lower noise levels than LD-FBP and LD-ADMIRE for both phantom and patient data (all p < 0.001). LD-DLAs trained with a lower radiation dose showed less image noise. However, the MTFs of the LD-DLAs were lower than those of LD-ADMIRE and LD-FBP (all p < 0.001) and decreased with decreasing training image dose. In the qualitative image analysis, the overall image quality of LD-DLAs was best for DLA-3 (50% simulated radiation dose) and not significantly different from LD-ADMIRE. There were no additional artifacts in LD-DLA images.

Conclusion

DLAs achieved less noise than FBP and ADMIRE in LD CT images, but did not maintain spatial resolution. The DLA trained with 50% simulated radiation dose showed the best overall image quality.

The use of artificial intelligence in computed tomography image reconstruction - A literature review

BACKGROUND AND PURPOSE

The use of AI in the process of CT image reconstruction may improve image quality of resultant images and therefore facilitate low-dose CT examinations.

METHODS

Articles in this review were gathered from multiple databases (Google Scholar, Ovid and Monash University Library Database). A total of 17 articles regarding AI use in CT image reconstruction was reviewed, including 1 white paper from GE Healthcare.

RESULTS

DLR algorithms performed better in terms of noise reduction abilities, and image quality preservation at low doses when compared to other reconstruction techniques.

CONCLUSION

Further research is required to discuss clinical application and diagnostic accuracy of DLR algorithms, but AI is a promising dose-reduction technique with future computational advances.

Development of Upright Computed Tomography With Area Detector for Whole-Body Scans: Phantom Study, Efficacy on Workflow, Effect of Gravity on Human Body, and Potential Clinical Impact

OBJECTIVES

Multiple human systems are greatly affected by gravity, and many disease symptoms are altered by posture. However, the overall anatomical structure and pathophysiology of the human body while standing has not been thoroughly analyzed due to the limitations of various upright imaging modalities, such as low spatial resolution, low contrast resolution, limited scan range, or long examination time. Recently, we developed an upright computed tomography (CT), which enables whole-torso cross-sectional scanning with 3-dimensional acquisition within 15 seconds. The purpose of this study was to evaluate the performance, workflow efficacy, effects of gravity on a large circulation system and the pelvic floor, and potential clinical impact of upright CT.

MATERIALS AND METHODS

We compared noise characteristics, spatial resolution, and CT numbers in a phantom between supine and upright CT. Thirty-two asymptomatic volunteers (48.4 ± 11.5 years) prospectively underwent both CT examinations with the same scanning protocols on the same day. We conducted a questionnaire survey among these volunteers who underwent the upright CT examination to determine their opinions regarding the stability of using the pole throughout the acquisition (closed question), as well as safety and comfortability throughout each examination (both used 5-point scales). The total access time (sum of entry time and exit time) and gravity effects on a large circulation system and the pelvic floor were evaluated using the Wilcoxon signed-rank test and the Mann-Whitney U test. For a large circulation system, the areas of the vena cava and aorta were evaluated at 3 points (superior vena cava or ascending aorta, at the level of the diaphragm, and inferior vena cava or abdominal aorta). For the pelvic floor, distances were evaluated from the bladder neck to the pubococcygeal line and the anorectal junction to the pubococcygeal line. We also examined the usefulness of the upright CT in patients with functional diseases of spondylolisthesis, pelvic floor prolapse, and inguinal hernia.

RESULTS

Noise characteristics, spatial resolution, and CT numbers on upright CT were comparable to those of supine CT. In the volunteer study, all volunteers answered yes regarding the stability of using the pole, and most reported feeling safe (average rating of 4.2) and comfortable (average rating of 3.8) throughout the upright CT examination. The total access time for the upright CT was significantly reduced by 56% in comparison with that of supine CT (upright: 41 ± 9 seconds vs supine: 91 ± 15 seconds, P < 0.001). In the upright position, the area of superior vena cava was 80% smaller than that of the supine position (upright: 39.9 ± 17.4 mm vs supine: 195.4 ± 52.2 mm, P < 0.001), the area at the level of the diaphragm was similar (upright: 428.3 ± 87.9 mm vs supine: 426.1 ± 82.0 mm, P = 0.866), and the area of inferior vena cava was 37% larger (upright: 346.6 ± 96.9 mm vs supine: 252.5 ± 93.1 mm, P < 0.001), whereas the areas of aortas did not significantly differ among the 3 levels. The bladder neck and anorectal junction significantly descended (9.4 ± 6.0 mm and 8.0 ± 5.6 mm, respectively, both P < 0.001) in the standing position, relative to their levels in the supine position. This tendency of the bladder neck to descend was more prominent in women than in men (12.2 ± 5.2 mm in women vs 6.7 ± 5.6 mm in men, P = 0.006). In 3 patients, upright CT revealed lumbar foraminal stenosis, bladder prolapse, and inguinal hernia; moreover, it clarified the grade or clinical significance of the disease in a manner that was not apparent on conventional CT.

CONCLUSIONS

Upright CT was comparable to supine CT in physical characteristics, and it significantly reduced the access time for examination. Upright CT was useful in clarifying the effect of gravity on the human body: gravity differentially affected the volume and shape of the vena cava, depending on body position. The pelvic floor descended significantly in the standing position, compared with its location in the supine position, and the descent of the bladder neck was more prominent in women than in men. Upright CT could potentially aid in objective diagnosis and determination of the grade or clinical significance of common functional diseases.

A comprehensive review of dual-energy and multi-spectral computed tomography

This review will provide a brief introduction to the development of the first Computed Tomography (CT) scan, from the beginnings of x-ray imaging to the first functional CT system introduced by Godfrey Houndsfield. The principles behind photon interactions and the methods by which they can be leveraged to generate dual-energy or multi-spectral CT images are discussed. The clinical applications of these methodologies are investigated, showing the immense potential for dual-energy or multi-spectral CT to change the fields of in-vivo and non-destructive imaging for quantitative analysis of tissues and materials. Lastly the current trends of research for dual-energy and multi-spectral CT are covered, showing that the majority of instrument development is focused on photon counting detectors for mutli-spectral CT and that clinical research is dominated by validation studies for the implementation of dual-energy and multi-spectral CT.

In vivo noninvasive three-dimensional (3D) assessment of microwave thermal ablation zone using non-contrast-enhanced x-ray CT

PURPOSE

To develop an image processing methodology for noninvasive three-dimensional (3D) quantification of microwave thermal ablation zones in vivo using x-ray computed tomography (CT) imaging without injection of a contrast enhancing material.

METHODS

Six microwave (MW) thermal ablation procedures were performed in three pigs. The ablations were performed with a constant heating duration of 8 min and power level of 30 W. During the procedure images from sixty 1 mm thick slices were acquired every 30 s. At the end of all ablation procedures for each pig, a contrast-enhanced scan was acquired for reference. Special algorithms for addressing challenges stemming from the 3D in vivo setup and processing the acquired images were prepared. The algorithms first rearranged the data to account for the oblique needle orientation and for breathing motion. Then, the gray level variance changes were analyzed, and optical flow analysis was applied to the treated volume in order to obtain the ablation contours and reconstruct the ablation zone in 3D. The analysis also included a special correction algorithm for eliminating artifacts caused by proximal major blood vessels and blood flow. Finally, 3D reference reconstructions from the contrast-enhanced scan were obtained for quantitative comparison.

RESULTS

For four ablations located >3 mm from a large blood vessel, the mean dice similarity coefficient (DSC) and the mean absolute radial discrepancy between the contours obtained from the reference contrast-enhanced images and the contours produced by the algorithm were 0.82 ± 0.03 and 1.92 ± 1.47 mm, respectively. In two cases of ablation adjacent to large blood vessels, the average DSC and discrepancy were: 0.67 ± 0.6 and 2.96 ± 2.15 mm, respectively. The addition of the special correction algorithm utilizing blood vessels mapping improved the mean DSC and the mean absolute discrepancy to 0.85 ± 0.02 and 1.19 ± 1.00 mm, respectively.

CONCLUSIONS

The developed algorithms provide highly accurate detailed contours in vivo (average error < 2.5 mm) and cope well with the challenges listed above. Clinical implementation of the developed methodology could potentially provide real time noninvasive 3D accurate monitoring of MW thermal ablation in-vivo, provided that the radiation dose can be reduced.

Magnetic Resonance Rectal Enema Versus Computed Tomographic Colonography in the Diagnosis of Rectosigmoid Endometriosis

OBJECTIVES

Rectosigmoid involvement by endometriosis causes intestinal symptoms such as constipation, diarrhea, and dyschezia. A precise diagnosis about the presence, location, and extent of bowel implants is required to plan the most appropriate treatment. The aim of the study was to compare the accuracy of magnetic resonance with distension of the rectosigmoid (MR-e) with computed colonography (CTC) for diagnosing rectosigmoid endometriosis.

METHODS

This study was based on the retrospective analysis of a prospectively collected database of patients with suspicion of rectosigmoid endometriosis who underwent both MR-e and CTC, and subsequently were treated by laparoscopy. The findings of imaging techniques were compared with surgical and histological results.

RESULTS

Of 90 women included in the study, 44 (48.9%) had rectosigmoid nodules and underwent bowel surgery. Sensitivity, specificity, positive predictive value, negative predictive value, and accuracy for the diagnosis of rectosigmoid endometriosis were 88.6%, 93.5%, 92.9%, 89.6%, and 91.1% for CTC, and 93.2%, 97.9%, 97.6%, 93.8%, and 95.6% for MR-e. There was no significant difference in the accuracy of both radiologic examinations for diagnosing rectosigmoid endometriosis (P = 0.344). However, MR-e was more accurate than CTC in estimating the largest diameter of the main rectosigmoid nodule (P < 0.001). The pain perceived by the patients was significantly lower during MR-e than during CTC (P < 0.001).

CONCLUSIONS

MR-e and CTC have similar diagnostic performance for the diagnosis of rectosigmoid involvement of endometriosis. However, MR-e is more accurate in the estimation of the largest diameter of main rectosigmoid nodule and more tolerated than CTC.

Optimization of Pediatric Body CT Angiography: What Radiologists Need to Know

OBJECTIVE. Pediatric CT angiography (CTA) presents unique challenges compared with adult CTA. Because of the ionizing radiation exposure, CTA should be used judiciously in children. The pearls offered here are observations gleaned from the authors' experience in the use of pediatric CTA. We also present some potential follies to be avoided. CONCLUSION. Understanding the underlying principles and paying meticulous attention to detail can substantially optimize dose and improve the diagnostic quality of pediatric CTA.

Incremental Image Noise Reduction in Coronary CT Angiography Using a Deep Learning-Based Technique with Iterative Reconstruction

Objective

To assess the feasibility of applying a deep learning-based denoising technique to coronary CT angiography (CCTA) along with iterative reconstruction for additional noise reduction.

Materials and Methods

We retrospectively enrolled 82 consecutive patients (male:female = 60:22; mean age, 67.0 ± 10.8 years) who had undergone both CCTA and invasive coronary artery angiography from March 2017 to June 2018. All included patients underwent CCTA with iterative reconstruction (ADMIRE level 3, Siemens Healthineers). We developed a deep learning based denoising technique (ClariCT.AI, ClariPI), which was based on a modified U-net type convolutional neural net model designed to predict the possible occurrence of low-dose noise in the originals. Denoised images were obtained by subtracting the predicted noise from the originals. Image noise, CT attenuation, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were objectively calculated. The edge rise distance (ERD) was measured as an indicator of image sharpness. Two blinded readers subjectively graded the image quality using a 5-point scale. Diagnostic performance of the CCTA was evaluated based on the presence or absence of significant stenosis (≥ 50% lumen reduction).

Results

Objective image qualities (original vs. denoised: image noise, 67.22 ± 25.74 vs. 52.64 ± 27.40; SNR [left main], 21.91 ± 6.38 vs. 30.35 ± 10.46; CNR [left main], 23.24 ± 6.52 vs. 31.93 ± 10.72; all p < 0.001) and subjective image quality (2.45 ± 0.62 vs. 3.65 ± 0.60, p < 0.001) improved significantly in the denoised images. The average ERDs of the denoised images were significantly smaller than those of originals (0.98 ± 0.08 vs. 0.09 ± 0.08, p < 0.001). With regard to diagnostic accuracy, no significant differences were observed among paired comparisons.

Conclusion

Application of the deep learning technique along with iterative reconstruction can enhance the noise reduction performance with a significant improvement in objective and subjective image qualities of CCTA images.

The Feasibility of Contrast-to-Noise Ratio on Measurements to Evaluate CT Image Quality in Terms of Low-Contrast Detailed Detectability

Background: To evaluate contrast-to-noise ratio (CNR) measurements in assessing image quality, in the context of the detectability performance of low-contrast detail (LCD), in computed tomography (CT) images, since exposure to elevated ionising-type radiation is considered to present excessive carcinogenic risk, whilst also causing distress in study subjects. Methods: An LCD phantom module (CTP515) was utilised in the study. Three dissimilar contrast items were used to analyse the ramifications of the proportions of an object on the CNR. Three multidetector CT (MDCT) scanners were used, with 16-MDCT, 64-MDCT and 80-MDCT frameworks, respectively. The CT scans were recreated using three dissimilar remaking algorithms—soft, standard and lung. The effects exerted on the CNR by various remodelling algorithms, as well as the contrast of various objects along with the size of the objects, were explored. The Hounsfield units of each chosen object (one unit representing the outer portion of the object) and the background and the standard deviation of the noise parameter were quantified, and algorithms were developed using MATLAB. Results: The CNR information was greatly influenced by changing the image recreation calculations and was very much increased in the soft-tissue recreation images using 16-MDCT and 64-MDCT. The CNR information was also increased more in the optimum recreation images than in the reproduced images from the computational procedure used in the 80-MDCT. The results did not show any remarkable contrasts in the CNR values between the different object sizes. Overall, a higher kVp produced an improved CNR in all the CT scanners. In particular, there were prominent upgrades in the CNR information when the kVp was increased from 80 to 120. Higher mAs levels gave better CNR values overall, especially for greater section thicknesses. Based on the CNR estimations, the 64-MDCT provided the best correlation among the CT scanners. Conclusions: The objective LCD appraisal method, based on CNR measurements, was confirmed as being useful for checking the different impacts of kVp, mAs and section thickness on the nature of the picture. This procedure was similarly viable in assessing the impacts of the different reconstruction calculations and the different differentiation questions on the nature of the image.