CT radiation dose and iterative reconstruction techniques. AJR Am J Roentgenol. 2015;204:W384-W392. [PMID: 25794087 DOI: 10.2214/ajr.14.13241]

Evolving and Novel Applications of Artificial Intelligence in Thoracic Imaging

The advent of artificial intelligence (AI) is revolutionizing medicine, particularly radiology. With the development of newer models, AI applications are demonstrating improved performance and versatile utility in the clinical setting. Thoracic imaging is an area of profound interest, given the prevalence of chest imaging and the significant health implications of thoracic diseases. This review aims to highlight the promising applications of AI within thoracic imaging. It examines the role of AI, including its contributions to improving diagnostic evaluation and interpretation, enhancing workflow, and aiding in invasive procedures. Next, it further highlights the current challenges and limitations faced by AI, such as the necessity of 'big data', ethical and legal considerations, and bias in representation. Lastly, it explores the potential directions for the application of AI in thoracic radiology.

Deep learning CT reconstruction improves liver metastases detection

OBJECTIVES

Detection of liver metastases is crucial for guiding oncological management. Computed tomography through iterative reconstructions is widely used in this indication but has certain limitations. Deep learning image reconstructions (DLIR) use deep neural networks to achieve a significant noise reduction compared to iterative reconstructions. While reports have demonstrated improvements in image quality, their impact on liver metastases detection remains unclear. Our main objective was to determine whether DLIR affects the number of detected liver metastasis. Our secondary objective was to compare metastases conspicuity between the two reconstruction methods.

METHODS

CT images of 121 patients with liver metastases were reconstructed using a 50% adaptive statistical iterative reconstruction (50%-ASiR-V), and three levels of DLIR (DLIR-low, DLIR-medium, and DLIR-high). For each reconstruction, two double-blinded radiologists counted up to a maximum of ten metastases. Visibility and contour definitions were also assessed. Comparisons between methods for continuous parameters were performed using mixed models.

RESULTS

A higher number of metastases was detected by one reader with DLIR-high: 7 (2-10) (median (Q₁-Q₃); total 733) versus 5 (2-10), respectively for DLIR-medium, DLIR-low, and ASiR-V (p < 0.001). Ten patents were detected with more metastases with DLIR-high simultaneously by both readers and a third reader for confirmation. Metastases visibility and contour definition were better with DLIR than ASiR-V.

CONCLUSION

DLIR-high enhanced the detection and visibility of liver metastases compared to ASiR-V, and also increased the number of liver metastases detected.

CRITICAL RELEVANCE STATEMENT

Deep learning-based reconstruction at high strength allowed an increase in liver metastases detection compared to hybrid iterative reconstruction and can be used in clinical oncology imaging to help overcome the limitations of CT.

KEY POINTS

Detection of liver metastases is crucial but limited with standard CT reconstructions. More liver metastases were detected with deep-learning CT reconstruction compared to iterative reconstruction. Deep learning reconstructions are suitable for hepatic metastases staging and follow-up.

Simulated deep CT characterization of liver metastases with high-resolution filtered back projection reconstruction

Early diagnosis and accurate prognosis of colorectal cancer is critical for determining optimal treatment plans and maximizing patient outcomes, especially as the disease progresses into liver metastases. Computed tomography (CT) is a frontline tool for this task; however, the preservation of predictive radiomic features is highly dependent on the scanning protocol and reconstruction algorithm. We hypothesized that image reconstruction with a high-frequency kernel could result in a better characterization of liver metastases features via deep neural networks. This kernel produces images that appear noisier but preserve more sinogram information. A simulation pipeline was developed to study the effects of imaging parameters on the ability to characterize the features of liver metastases. This pipeline utilizes a fractal approach to generate a diverse population of shapes representing virtual metastases, and then it superimposes them on a realistic CT liver region to perform a virtual CT scan using CatSim. Datasets of 10,000 liver metastases were generated, scanned, and reconstructed using either standard or high-frequency kernels. These data were used to train and validate deep neural networks to recover crafted metastases characteristics, such as internal heterogeneity, edge sharpness, and edge fractal dimension. In the absence of noise, models scored, on average, 12.2% ( α = 0.012 ) and 7.5% ( α = 0.049 ) lower squared error for characterizing edge sharpness and fractal dimension, respectively, when using high-frequency reconstructions compared to standard. However, the differences in performance were statistically insignificant when a typical level of CT noise was simulated in the clinical scan. Our results suggest that high-frequency reconstruction kernels can better preserve information for downstream artificial intelligence-based radiomic characterization, provided that noise is limited. Future work should investigate the information-preserving kernels in datasets with clinical labels.

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

OBJECTIVES

To 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 METHODS

Oncologic 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.

RESULTS

Fifty 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%.

CONCLUSIONS

DLIR 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 STATEMENT

Deep 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.

Low Dose Pediatric CT Head Protocol using Iterative Reconstruction Techniques: A Comparison with Standard Dose Protocol

PURPOSE

Pediatric computed tomography (CT) head examination has also increased in recent years with the advancement in CT technology; however, children exposed to radiation at the youngest age are more vulnerable to the risks of radiation. The aim of the study is to evaluate radiation dose and image quality of low dose pediatric CT head protocol compared to standard dose pediatric CT head protocol.

METHODS

This was a prospective study. Group 1 included 73 patients aged < 1 year and 70 patients in the 1-5 years age group and had undergone CT head examination using the standard dose protocol. Group 2 included 31 patients aged < 1 year and 40 patients in the 1-5 years age group and had undergone CT head examination using the low dose protocol. The radiation dose was measured and image quality was assessed quantitatively and qualitatively.

RESULTS

There was a significant difference in radiation dose between the standard and low dose protocols (p > 0.05) with lower radiation dose for low dose group. The qualitative analysis did not show a significant difference between the standard and low dose protocols. The gray-white matter differentiation (GWMD), attenuation, contrast to noise ratio (CNR) and figure of merit (FOM) were higher in the low dose protocol compared to the standard dose with a significant difference (p > 0.05).

CONCLUSION

The study concludes that a low dose protocol at 80 kV tube voltage/150 mAs tube current exposure time product/iterative reconstruction-iDose4 (level 3) for < 1 year age group and 100 kV/200m As/iDose4 (level 3) for 1-5 years age group provides ultra-low effective dose with diagnostically acceptable image quality for pediatric CT head examination compared with standard dose protocol.

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.

Interdisciplinary perspectives on computed tomography in sepsis: survey among medical doctors at a large university medical center

OBJECTIVES

This study aims to describe physicians' perspectives on the use of computed tomography (CT) in patients with sepsis.

METHODS

In January 2022, physicians of a large European university medical center were surveyed using a web-based questionnaire asking about their views on the role of CT in sepsis. A total of 371 questionnaires met the inclusion criteria and were analyzed using work experience, workplace, and medical specialty of physicians as variables. Chi-square tests were performed.

RESULTS

Physicians considered the ability to detect an unknown focus as the greatest benefit of CT scans in sepsis (70.9%, n = 263/371). Two clinical criteria - "signs of decreased vigilance" (89.2%, n = 331/371) and "increased catecholamine demand" (84.7%, n = 314/371) - were considered highly relevant for a CT request. Elevated procalcitonin (82.7%, n = 307/371) and lactate levels (83.6%, n = 310/371) were consistently found to be critical laboratory values to request a CT. As long as there is evidence of infection in one organ region, most physicians (42.6%, n = 158/371) would order a CT scan based on clinical assessment. Combined examination of the chest, abdomen, and pelvis was favored (34.8%, n = 129/371) in cases without clinical clues of an infection source. A time window of ≥ 1-6 h was preferred for both CT examinations (53.9%, n = 200/371) and CT-guided interventions (59.3%, n = 220/371) in patients with sepsis.

CONCLUSION

Despite much consensus, there are significant differences in attitudes towards the use of CT in septic patients among physicians from different workplaces and medical specialties. Knowledge of these perspectives may improve patient management and interprofessional communication.

KEY POINTS

Despite interdisciplinary consensus on the use of CT in sepsis, statistically significant differences in the responses are apparent among physicians from different workplaces and medical specialties. The detection of a previously unknown source of infection and the ability to plan interventions and/or surgery based on CT findings are considered key advantages of CT in septic patients. Timing of CT reflects the requirements of specific disciplines.

Evaluation of three-dimensional dual-energy CT cholangiopancreatography image quality in patients with pancreatobiliary dilatation: Comparison with conventional single-energy CT

Objective

This study aimed to evaluate three-dimensional (3D) negative-contrast CT cholangiopancreatography (nCTCP) image quality using dual-energy CT (DECT) with iterative reconstruction (IR) technique in patients with pancreatobiliary dilatation compared with single-energy CT (SECT).

Methods

Of the patients, 67 and 56 underwent conventional SECT (SECT set) and DECT with IR technique (DECT set), respectively. All patients were retrospectively analyzed during the portal phase to compare objective image quality and other data including patient demographics, hepatic and pancreatic parenchymal enhancement, noise, and attenuation difference (AD) between dilated ducts and enhanced hepatic parenchyma, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and CT volume dose index (CTDIvol). Two radiologists used the five-point Likert scale to evaluate the subjective image quality of 3D nCTCP regarding image noise, sharpness of dilated ducts, and overall image quality. Statistical analyses used the Mann-Whitney U test.

Results

No significant difference in patient demographics in either CT set was showed during objective evaluation (p > 0.05). However, higher hepatic and pancreatic parenchymal enhancement, AD, SNR, and CNR and lower hepatic and pancreatic noise (p < 0.005) as well as CTDIvol (p = 0.005) on DECT than on SECT were observed. Higher mean grades on DECT than on SECT were showed for image noise (4.65 vs 3.92), sharpness of dilated ducts (4.52 vs 3.94), and overall image quality (4.45 vs 3.91; p < 0.001), respectively during subjective evaluation.

Conclusion

A higher overall image quality and lower radiation dose on 3D nCTCP can be obtained by DECT with IR technique than with conventional SECT in patients with pancreatobiliary dilatation.

Diagnostic performance of artificial intelligence for pediatric pulmonary nodule detection on chest computed tomography: comparison of simulated lower radiation doses

The combination of low dose CT and AI performance in the pediatric population has not been explored. Understanding this relationship is relevant for pediatric patients given the potential radiation risks. Here, the objective was to determine the diagnostic performance of commercially available Computer Aided Detection (CAD) for pulmonary nodules in pediatric patients at simulated lower radiation doses. Retrospective chart review of 30 sequential patients between 12-18 years old who underwent a chest CT on the Siemens SOMATOM Force from December 20, 2021, to April 12, 2022. Simulated lower doses at 75%, 50%, and 25% were reconstructed in lung kernel at 3 mm slice thickness using ReconCT and imported to Syngo CT Lung CAD software for analysis. Two pediatric radiologists reviewed the full dose CTs to determine the reference read. Two other pediatric radiologists compared the Lung CAD results at 100% dose and each simulated lower dose level to the reference on a nodule by nodule basis. The sensitivity (Sn), positive predictive value (PPV), and McNemar test were used for comparison of Lung CAD performance based on dose. As reference standard, 109 nodules were identified by the two radiologists. At 100%, and simulated 75%, 50%, and 25% doses, lung CAD detected 60, 62, 58, and 62 nodules, respectively; 28, 28, 29, and 26 were true positive (Sn = 26%, 26%, 27%, 24%), 30, 32, 27, and 34 were false positive (PPV = 48%, 47%, 52%, 43%). No statistically significance difference of Lung CAD performance at different doses was found, with p-values of 1.0, 1.0, and 0.7 at simulated 75%, 50%, and 25% doses compared to standard dose.

CONCLUSION

The Lung CAD shows low sensitivity at all simulated lower doses for the detection of pulmonary nodules in this pediatric population. However, radiation dose may be reduced from standard without further compromise to the Lung CAD performance.

WHAT IS KNOWN

• High diagnostic performance of Lung CAD for detection of pulmonary nodules in adults. • Several imaging techniques are applied to reduce pediatric radiation dose.

WHAT IS NEW

• Low sensitivity at all simulated lower doses for the detection of pulmonary nodules in our pediatric population. • Radiation dose may be reduced from standard without further compromise to the Lung CAD performance.

Value of deep-learning image reconstruction at submillisievert CT for evaluation of the female pelvis

AIM

To assess the value of deep-learning reconstruction (DLR) at submillisievert computed tomography (CT) for the evaluation of the female pelvis, with standard dose (SD) hybrid iterative reconstruction (IR) images as reference.

MATERIALS AND METHODS

The present study enrolled 50 female patients consecutively who underwent contrast-enhanced abdominopelvic CT for clinically indicated reasons. Submillisievert pelvic images were acquired using a noise index of 15 for low-dose (LD) scans, which were reconstructed with DLR (body and body sharp), hybrid-IR, and model-based IR (MBIR). Additionally, SD scans were reconstructed with a noise index of 7.5 using hybrid-IR. Radiation dose, quantitative image quality, overall image quality, image appearance using a five-point Likert scale (1-5: worst to best), and lesion evaluation in both SD and LD images were analysed and compared.

RESULTS

The submillisievert pelvic CT examinations showed a 61.09 ± 4.13% reduction in the CT dose index volume compared to SD examinations. Among the LD images, DLR (body sharp) had the highest quantitative quality, followed by DLR (body), MBIR, and hybrid-IR. LD DLR (body) had overall image quality comparable to the reference (p=0.084) and favourable image appearance (p=0.209). In total, 40 pelvic lesions were detected in both SD and LD images. LD DLR (body and body sharp) exhibited similar diagnostic confidence (p=0.317 and 0.096) compared with SD hybrid-IR.

CONCLUSION

DLR algorithms, providing comparable image quality and diagnostic confidence, are feasible in submillisievert abdominopelvic CT. The DLR (body) algorithm with favourable image appearance is recommended in clinical settings.

Implementation of AI image reconstruction in CT-how is it validated and what dose reductions can be achieved

CT reconstruction has undergone a substantial change over the last decade with the introduction of iterative reconstruction (IR) and now with deep learning reconstruction (DLR). In this review, DLR will be compared to IR and filtered back-projection (FBP) reconstructions. Comparisons will be made using image quality metrics such as noise power spectrum, contrast-dependent task-based transfer function, and non-prewhitening filter detectability index (dNPW'). Discussion on how DLR has impacted CT image quality, low-contrast detectability, and diagnostic confidence will be provided. DLR has shown the ability to improve in areas that IR is lacking, namely: noise magnitude reduction does not alter noise texture to the degree that IR did, and the noise texture found in DLR is more aligned with noise texture of an FBP reconstruction. Additionally, the dose reduction potential for DLR is shown to be greater than IR. For IR, the consensus was dose reduction should be limited to no more than 15-30% to preserve low-contrast detectability. For DLR, initial phantom and patient observer studies have shown acceptable dose reduction between 44 and 83% for both low- and high-contrast object detectability tasks. Ultimately, DLR is able to be used for CT reconstruction in place of IR, making it an easy "turnkey" upgrade for CT reconstruction. DLR for CT is actively being improved as more vendor options are being developed and current DLR options are being enhanced with second generation algorithms being released. DLR is still in its developmental early stages, but is shown to be a promising future for CT reconstruction.

Pediatric low-dose head CT: Image quality improvement using iterative model reconstruction

PURPOSE

To evaluate the differences in pediatric non-contrast low-dose head computed tomography (CT) between filtered-back projection and iterative model reconstruction using objective and subjective image quality evaluation.

METHODS

A retrospective study evaluated children undergoing low-dose non-contrast head CT. All CT scans were reconstructed using both filtered-back projection and iterative model reconstruction. Objective image quality analysis was performed using contrast and signal-to-noise ratios for the supra- and infratentorial brain regions of identical regions of interest on the two reconstruction methods. Two experienced pediatric neuroradiologists evaluated subjective image quality, visibility of structures, and artifacts.

RESULTS

We evaluated 233 low-dose brain CT scans of 148 pediatric patients. There was a ∼2-fold improvement in the contrast-to-noise ratio between gray and white matter in the infra- and supratentorial regions (p < 0.001) using iterative model reconstruction compared to filtered-back projection. The white and gray matter signal-to-noise ratio improved more than 2-fold using iterative model reconstruction (p < 0.001). Furthermore, radiologists graded anatomical details, gray-white matter differentiation, beam hardening artifacts, and image quality using iterative model reconstructions as superior to filtered-back projection reconstructions.

CONCLUSION

Iterative model reconstructions had better contrast-to-noise and signal-to-noise ratios with fewer artifacts in pediatric CT brain scans using low-dose radiation protocols. This image quality improvement was demonstrated in the supra- and infratentorial regions. This method thus comprises an important tool for reducing children's exposure while maintaining diagnostic capability.

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.

Reducing contrast-agent volume and radiation dose in CT with 90-kVp tube voltage, high tube current modulation, and advanced iteration algorithm

Increasing utilization of computed tomography (CT) has raised concerns regarding CT radiation dose and technology has been developed to achieve an appropriate balance between image quality, radiation dose, and the amount of contrast material. This study was planned to evaluate the image quality and radiation dose in pancreatic dynamic computed tomography (PDCT) with 90-kVp tube voltage and reduction of the standard amount of contrast agent, compared with 100-kVp PDCT of the research hospital's convention. Total of 51 patients with both CT protocols were included. The average Hounsfield units (HU) values of the abdominal organs and image noise were measured for objective image quality analysis. Two radiologists evaluated five categories of image qualities such as subjective image noise, visibility of small structure, beam hardening or streak artifact, lesion conspicuity and overall diagnostic performance for subjective image quality analysis. The total amount of contrast agent, radiation dose, and image noise decreased in the low-kVp group, by 24.4%, 31.7%, and 20.6%, respectively (p < 0.001). The intraobserver and interobserver agreements were moderate to substantial (k = 0.4-0.8). The contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), and figure of merit of the almost organs except psoas muscle in the low-kVp group were significantly higher (p < 0.001). Except for lesion conspicuity, both reviewers judged that subjective image quality of the 90-kVp group was better (p < 0.001). With 90-kVp tube voltage, 25% reduced contrast agent volume with advanced iteration algorithm and high tube current modulation achieved radiation dose reduction of 31.7%, as well as better image quality and diagnostic confidence.

FACTORS INFLUENCING SIZE-SPECIFIC DOSE ESTIMATES OF SELECTED COMPUTED TOMOGRAPHY PROTOCOLS AT TWO CLINICAL PRACTICES IN SOUTH AFRICA

The study aimed to determine the factors that impact the size-specific dose estimate (SSDE) for computed tomography (CT) examinations of the chest-abdomen-pelvis and abdomen-pelvis protocols in two clinical radiology practices and evaluate the image quality of these protocols. Imaging parameters, protocols, dose metrics from the CT units and size-related parameters to calculate the SSDE were documented. The image quality of the CT images was assessed using an image subtraction algorithm. The SSDE increased as the volumetric CT dose index (CTDIvol), and the patient's body mass index increased, respectively. Significant differences (p < 0.001) occurred between the two hospitals regarding image quality. However, these differences were not indicative of differences in the diagnostic performances for task-based imaging protocols. Different clinical protocols should be reviewed to optimise dose. The inclusion of the pre-monitoring sequence, age of the machine and the scan requisition parameters impacted the SSDEs. Image quality should be assessed to evaluate the consistency of image quality between protocols applied by different CT units when assessing SSDEs.

Deep Learning Denoising of Low-Dose Computed Tomography Chest Images: A Quantitative and Qualitative Image Analysis

PURPOSE

To assess deep learning denoised (DLD) computed tomography (CT) chest images at various low doses by both quantitative and qualitative perceptual image analysis.

METHODS

Simulated noise was inserted into sinogram data from 32 chest CTs acquired at 100 mAs, generating anatomically registered images at 40, 20, 10, and 5 mAs. A DLD model was developed, with 23 scans selected for training, 5 for validation, and 4 for test.Quantitative analysis of perceptual image quality was assessed with Structural SIMilarity Index (SSIM) and Fréchet Inception Distance (FID). Four thoracic radiologists graded overall diagnostic image quality, image artifact, visibility of small structures, and lesion conspicuity. Noise-simulated and denoised image series were evaluated in comparison with one another, and in comparison with standard 100 mAs acquisition at the 4 mAs levels. Statistical tests were conducted at the 2-sided 5% significance level, with multiple comparison correction.

RESULTS

At the same mAs levels, SSIM and FID between noise-simulated and reconstructed DLD images indicated that images were closer to a perfect match with increasing mAs (closer to 1 for SSIM, and 0 for FID).In comparing noise-simulated and DLD images to standard-dose 100-mAs images, DLD improved SSIM and FID. Deep learning denoising improved SSIM of 40-, 20-, 10-, and 5-mAs simulations in comparison with standard-dose 100-mAs images, with change in SSIM from 0.91 to 0.94, 0.87 to 0.93, 0.67 to 0.87, and 0.54 to 0.84, respectively. Deep learning denoising improved FID of 40-, 20-, 10-, and 5-mAs simulations in comparison with standard-dose 100-mAs images, with change in FID from 20 to 13, 46 to 21, 104 to 41, and 148 to 69, respectively.Qualitative image analysis showed no significant difference in lesion conspicuity between DLD images at any mAs in comparison with 100-mAs images. Deep learning denoising images at 10 and 5 mAs were rated lower for overall diagnostic image quality ( P < 0.001), and at 5 mAs lower for overall image artifact and visibility of small structures ( P = 0.002), in comparison with 100 mAs.

CONCLUSIONS

Deep learning denoising resulted in quantitative improvements in image quality. Qualitative assessment demonstrated DLD images at or less than 10 mAs to be rated inferior to standard-dose images.

Transfer learning framework for low-dose CT reconstruction based on marginal distribution adaptation in multiscale

BACKGROUND

With the increasing use of computed tomography (CT) in clinical practice, limiting CT radiation exposure to reduce potential cancer risks has become one of the important directions of medical imaging research. As the dose decreases, the reconstructed CT image will be severely degraded by projection noise.

PURPOSE

As an important method of image processing, supervised deep learning has been widely used in the restoration of low-dose CT (LDCT) in recent years. However, the normal-dose CT (NDCT) corresponding to a specific LDCT (it is regarded as the label of the LDCT, which is necessary for supervised learning) is very difficult to obtain so that the application of supervised learning methods in LDCT reconstruction is limited. It is necessary to construct a unsupervised deep learning framework for LDCT reconstruction that does not depend on paired LDCT-NDCT datasets.

METHODS

We presented an unsupervised learning framework for the transferring from the identity mapping to the low-dose reconstruction task, called marginal distribution adaptation in multiscale (MDAM). For NDCTs as source domain data, MDAM is an identity map with two parts: firstly, it establishes a dimensionality reduction mapping, which can obtain the same feature distribution from NDCTs and LDCTs; and then NDCTs is retrieved by reconstructing the image overview and details from the low-dimensional features. For the purpose of the feature transfer between source domain and target domain (LDCTs), we introduce the multiscale feature extraction in the MDAM, and then eliminate differences in probability distributions of these multiscale features between NDCTs and LDCTs through wavelet decomposition and domain adaptation learning.

RESULTS

Image quality evaluation metrics and subjective quality scores show that, as an unsupervised method, the performance of the MDAM approaches or even surpasses some state-of-the-art supervised methods. Especially, MDAM has been favorably evaluated in terms of noise suppression, structural preservation, and lesion detection.

CONCLUSIONS

We demonstrated that, the MDAM framework can reconstruct corresponding NDCTs from LDCTs with high accuracy, and without relying on any labeles. Moreover, it is more suitable for clinical application compared with supervised learning methods.

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.

As low as diagnostically acceptable dose imaging in maxillofacial trauma: a reference quality approach

OBJECTIVES

As-low-as-diagnostically-acceptable (ALADA) doses are substantially lower than current diagnostic reference levels. To improve dose management, a reference quality approach was tested in which phantom quality metrics of a clinical ALADA dose reference protocol were used to benchmark potential ALADA dose protocols for various scanner models.

METHODS

Spatial resolution, contrast resolution, contrast-to-noise ratio (CNR) and subjective noise and sharpness were evaluated for a clinical ALADA dose reference protocol at 80 kV and 40 mA (CTDIvol 2.66 mGy) and compared with test protocols of two CT scanners at 100 kV and 35 mA (3.08-3.44 mGy), 80 kV and 54-61 mA (2.65 mGy), 80 kV and 40 mA (1.73-1.92 mGy), and 80 kV and 21-23 mA (1.00-1.03 mGy) using different kernels, filtered backprojection and iterative reconstructions. The test protocols with the lowest dose showing quality metrics non-inferior to the reference protocol were verified in a cadaver study by determining the diagnostic accuracy of detection of maxillofacial fractures and CNR of the optical nerve and rectus inferior muscle.

RESULTS

36 different image series were analysed in the phantom study. Based on the phantom quality metrics, potential ALADA dose protocols at 1.73-1.92 mGy were selected. Compared with the reference images, the selected protocols showed non-inferiority in the detection and classification of maxillofacial fractures and non-inferior CNR of orbital soft tissues in the cadaver study.

CONCLUSIONS

Reference quality metrics from clinical ALADA dose protocols may be used to guide selection of potential ALADA dose protocols of different CT scanners.

Deep learning image reconstruction algorithm reduces image noise while alters radiomics features in dual-energy CT in comparison with conventional iterative reconstruction algorithms: a phantom study

OBJECTIVES

To compare image quality between a deep learning image reconstruction (DLIR) algorithm and conventional iterative reconstruction (IR) algorithms in dual-energy CT (DECT) and to assess the impact of these algorithms on radiomics robustness.

METHODS

A phantom with clinical-relevant densities was imaged on seven DECT scanners with the same voxel size using typical abdominal-pelvis examination protocols. On one DECT scanner, raw data were reconstructed using both conventional IR (adaptive statistical iterative reconstruction-V, ASIR-V) and DLIR. Nine sets of corresponding images were generated on other six DECT scanners using scanner-equipped conventional IR. Regions of interest were delineated through rigid registrations. Image quality was compared. Pyradiomics platform was used for radiomics feature extraction. Test-retest repeatability was assessed by Bland-Altman analysis for repeated scans. Inter-reconstruction algorithm reproducibility between conventional IR and DLIR was tested by intraclass correlation coefficient (ICC) and concordance correlation coefficient (CCC). Inter-scanner reproducibility was evaluated by coefficient of variation (CV) and quartile coefficient of dispersion (QCD). Robust features were identified.

RESULTS

DLIR significantly improved image quality. Ninety-four radiomics features were extracted and nine features were considered as robust. 93.87% features were repeatable between repeated scans. ASIR-V images showed higher reproducibility to other conventional IR than DLIR (ICC mean, 0.603 vs 0.558, p = 0.001; CCC mean, 0.554 vs 0.510, p = 0.004). 7.45% and 26.83% features were reproducible among scanners evaluated by CV and QCD, respectively.

CONCLUSIONS

DLIR improves quality of DECT images but may alter radiomics features compared to conventional IR. Nine robust DECT radiomics features were identified.

KEY POINTS

• DLIR improves DECT image quality in terms of signal-to-noise ratio and contrast-to-noise ratio compared with ASIR-V and showed the highest noise reduction rate and lowest peak frequency shift. • Most of radiomics features are repeatable between repeated DECT scans, while inter-reconstruction algorithm reproducibility between conventional IR and DLIR, and inter-scanner reproducibility, are low. • Although DLIR may alter radiomics features compared to IR algorithms, nine radiomics features survived repeatability and reproducibility analysis among DECT scanners and reconstruction algorithms, which allows further validation and clinical-relevant analysis.

Artificial Intelligence in Emergency Radiology: Where Are We Going?

Emergency Radiology is a unique branch of imaging, as rapidity in the diagnosis and management of different pathologies is essential to saving patients' lives. Artificial Intelligence (AI) has many potential applications in emergency radiology: firstly, image acquisition can be facilitated by reducing acquisition times through automatic positioning and minimizing artifacts with AI-based reconstruction systems to optimize image quality, even in critical patients; secondly, it enables an efficient workflow (AI algorithms integrated with RIS-PACS workflow), by analyzing the characteristics and images of patients, detecting high-priority examinations and patients with emergent critical findings. Different machine and deep learning algorithms have been trained for the automated detection of different types of emergency disorders (e.g., intracranial hemorrhage, bone fractures, pneumonia), to help radiologists to detect relevant findings. AI-based smart reporting, summarizing patients' clinical data, and analyzing the grading of the imaging abnormalities, can provide an objective indicator of the disease's severity, resulting in quick and optimized treatment planning. In this review, we provide an overview of the different AI tools available in emergency radiology, to keep radiologists up to date on the current technological evolution in this field.

Deep learning image reconstruction algorithm for carotid dual-energy computed tomography angiography: evaluation of image quality and diagnostic performance

Objectives

To evaluate image quality and diagnostic performance of carotid dual-energy computed tomography angiography (DECTA) using deep learning image reconstruction (DLIR) compared with images using adaptive statistical iterative reconstruction-Veo (ASIR-V).

Methods

Carotid DECTA datasets of 28 consecutive patients were reconstructed at 50 keV using DLIR at low, medium, and high levels (DLIR-L, DLIR-M, and DLIR-H) and 80% ASIR-V algorithms. Mean attenuation, image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) at different levels of arteries were measured and calculated. Image quality for noise and texture, depiction of arteries, and diagnostic performance toward carotid plaques were assessed subjectively by two radiologists. Quantitative and qualitative parameters were compared between the ASIR-V, DLIR-L, DLIR-M, and DLIR-H groups.

Results

The image noise at aorta and common carotid artery, SNR, and CNR at all level arteries of DLIR-H images were significantly higher than those of ASIR-V images (p = 0.000–0.040). The quantitative analysis of DLIR-L and DLIR-M showed comparable denoise capability with ASIR-V. The overall image quality (p = 0.000) and image noise (p = 0.000–0.014) were significantly better in the DLIR-M and DLIR-H images. The image texture was improved by DLR at all level compared to ASIR-V images (p = 0.000–0.008). Depictions of head and neck arteries and diagnostic performance were comparable between four groups (p > 0.05).

Conclusions

Compared with 80% ASIR-V, we recommend DLIR-H for clinical carotid DECTA reconstruction, which can significantly improve the image quality of carotid DECTA at 50 keV but maintain a desirable diagnostic performance and arterial depiction.

Cardiac CTA image quality of adaptive statistical iterative reconstruction-V versus deep learning reconstruction "TrueFidelity" in children with congenital heart disease

BACKGROUND

Several recent studies have reported that deep learning reconstruction "TrueFidelity" (TF) improves computed tomography (CT) image quality. However, no study has compared adaptive statistical repeated reconstruction (ASIR-V) using TF in pediatric cardiac CT angiography (CTA) with a low peak kilovoltage.

OBJECTIVE

This study aimed to determine whether ASIR-V or TF CTA image quality is superior in children with congenital heart disease (CHD).

MATERIALS AND METHODS

Fifty children (median age, 2 months; interquartile range, 0-5 months; 28 men) with CHD who underwent CTA were enrolled between June and September 2020. Images were reconstructed using 2 ASIR-V blending factors (80% and 100% [AV-100]) and 3 TF settings (low, medium, and high [TF-H] strength levels). For the quantitative analyses, 3 objective image qualities (attenuation, noise, and signal-to-noise ratio [SNR]) were measured of the great vessels and heart chambers. The contrast-to-noise ratio (CNR) was also evaluated between the left ventricle and the dial wall. For the qualitative analyses, the degree of quantum mottle and blurring at the upper level to the first branch of the main pulmonary artery was assessed independently by 2 radiologists.

RESULTS

When the ASIR-V blending factor level and TF strength were higher, the noise was lower, and the SNR was higher. The image noise and SNR of TF-H were significantly lower and higher than those of AV-100 (P < .01), except for noise in the right atrium and left pulmonary artery and SNR of the right ventricle. Regarding CNR, TF-H was significantly better than AV-100 (P < .01). In addition, in the objective assessment of the degree of quantum mottle and blurring, TF-H had the best score among all examined image sets (P < .01).

CONCLUSION

TF-H is superior to AV-100 in terms of objective and subjective image quality. Consequently, TF-H was the best image set for cardiac CTA in children with CHD.

The Value of Deep Learning Image Reconstruction in Improving the Quality of Low-Dose Chest CT Images

This study aimed to evaluate the value of the deep learning image reconstruction (DLIR) algorithm (GE Healthcare’s TrueFidelity™) in improving the image quality of low-dose computed tomography (LDCT) of the chest. First, we retrospectively extracted raw data of chest LDCT from 50 patients and reconstructed them by using model-based adaptive statistical iterative reconstruction-Veo at 50% (ASIR-V 50%) and DLIR at medium and high strengths (DLIR-M and DLIR-H). Three sets of images were obtained. Next, two radiographers measured the mean CT value/image signal and standard deviation (SD) in Hounsfield units at the region of interest (ROI) and calculated the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Two radiologists subjectively evaluated the image quality using a 5-point Likert scale. The differences between the groups of data were analyzed through a repeated measures ANOVA or the Friedman test. Last, our result show that the three reconstructions did not differ significantly in signal (p > 0.05) but had significant differences in noise, SNR, and CNR (p < 0.001). The subjective scores significantly differed among the three reconstruction modalities in soft tissue (p < 0.001) but not in lung tissue (p > 0.05). DLIR-H had the best noise reduction ability and improved SNR and CNR without distorting the image texture, followed by DLIR-M and ASIR-V 50%. In summary, DLIR can provide a higher image quality at the same dose, enhancing the physicians’ diagnostic confidence and improving the diagnostic efficacy of LDCT for lung cancer screening.

Application of deep learning reconstruction of ultra-low-dose abdominal CT in the diagnosis of renal calculi

BACKGROUND

Renal calculi are a common and recurrent urological disease and are usually detected by CT. In this study, we evaluated the diagnostic capability, image quality, and radiation dose of abdominal ultra-low-dose CT (ULDCT) with deep learning reconstruction (DLR) for detecting renal calculi.

METHODS

Sixty patients with suspected renal calculi were prospectively enrolled. Low-dose CT (LDCT) images were reconstructed with hybrid iterative reconstruction (LD-HIR) and was regarded as the standard for stone and lesion detection. ULDCT images were reconstructed with HIR (ULD-HIR) and DLR (ULD-DLR). We then compared stone detection rate, abdominal lesion detection rate, image quality and radiation dose between LDCT and ULDCT.

RESULTS

A total of 130 calculi were observed on LD-HIR images. Stone detection rates of ULD-HIR and ULD-DLR images were 93.1% (121/130) and 95.4% (124/130). A total of 129 lesions were detected on the LD-HIR images. The lesion detection rate on ULD-DLR images was 92.2%, with 10 cysts < 5 mm in diameter missed. The CT values of organs on ULD-DLR were similar to those on LD-HIR and lower than those on ULD-HIR. Signal-to-noise ratio was highest and noise lowest on ULD-DLR. The subjective image quality of ULD-DLR was similar to that of LD-HIR and better than that of ULD-HIR. The effective radiation dose of ULDCT (0.64 ± 0.17 mSv) was 77% lower than that of LDCT (2.75 ± 0.50 mSv).

CONCLUSION

ULDCT combined with DLR could significantly reduce radiation dose while maintaining suitable image quality and stone detection rate in the diagnosis of renal calculi.

Low-dose abdominopelvic computed tomography in patients with lymphoma: An image quality and radiation dose reduction study

This study aimed to evaluate image quality, the detection rate of enlarged lymph nodes, and radiation dose exposure of ultralow-dose and low-dose abdominopelvic computed tomography (CT) in patients with lymphoma. Patients with lymphoma who underwent abdominopelvic CT using dual-source scanner were retrospectively recruited from a single center. CT images were obtained at 90 kVp dual-source mode reformatted in three data sets using the advanced modelled iterative reconstruction algorithm: 100% (standard-dose CT), 66.7% (low-dose CT), and 33.3% (ultralow-dose CT). Two radiologists analyzed subjective image quality and detection of abdominal enlarged lymph nodes on ultralow-dose, low-dose, and standard-dose CT blindly and independently. The results were compared with reference standards. Three readers (two radiologists and one hematologist) reviewed overall image quality and spleen size. In total, 128 consecutive CT scans (77 complete response, 44 partial response, 6 progressive disease, and 1 initial evaluation) from 86 patients (64 B-cell lymphoma, 14 T/NK-cell lymphoma, and 8 Hodgkin’s lymphoma cases) were assessed. The enlarged lymph node-based detection rates for two readers were 97.0% (96/99) and 94.0% (93/99) on standard-dose CT, 97.0% (96/99) and 94.0% (93/99) on low-dose CT, and 94.0% (93/99) and 89.9% (89/99) on ultralow-dose CT. Overall image quality was 3.8 ± 0.5, 3.9 ± 0.5, and 4.1 ± 0.5 on ultralow-dose CT; 4.7 ± 0.4, 4.6 ± 0.5, and 4.8 ± 0.3 on low-dose CT; and 4.8 ± 0.4, 4.7 ± 0.4, and 4.9 ± 0.2 on standard-dose CT, according to two radiologists and one hematologist, respectively. Intraclass correlation coefficients of spleen size were 0.90 (95% confidence interval [CI], 0.87–0.93), 0.91 (95% CI, 0.88–0.93), and 0.91 (95% CI, 0.88–0.93) on ultralow-dose, low-dose, and standard-dose CT, respectively. Mean effective radiation doses of standard-dose, low-dose, and ultralow-dose CT were 5.7 ±1.8 mSv, 3.8 ± 1.2 mSv, and 1.9 ± 0.6 mSv, respectively. Our findings suggest that ultralow-dose and low-dose CT, even with radiation doses reduced by 66.7% and 33.3%, respectively, maintained adequate image quality. These imaging modalities may be employed for follow-up lymphoma evaluation in consideration of the long surveillance periods.

Quantitative and qualitative assessments of deep learning image reconstruction in low-keV virtual monoenergetic dual-energy CT

OBJECTIVES

To evaluate a novel deep learning image reconstruction (DLIR) technique for dual-energy CT (DECT) derived virtual monoenergetic (VM) images compared to adaptive statistical iterative reconstruction (ASIR-V) in low kiloelectron volt (keV) images.

METHODS

We analyzed 30 venous phase acute abdominal DECT (80/140 kVp) scans. Data were reconstructed to ASIR-V and DLIR-High at four different keV levels (40, 50, 74, and 100) with 1- and 3-mm slice thickness. Quantitative Hounsfield unit (HU) and noise assessment were measured within the liver, aorta, fat, and muscle. Subjective assessment of image noise, sharpness, texture, and overall quality was performed by two board-certified radiologists.

RESULTS

DLIR reduced image noise by 19.9-35.5% (p < 0.001) compared to ASIR-V in all reconstructions at identical keV levels. Contrast-to-noise ratio (CNR) increased by 49.2-53.2% (p < 0.001) in DLIR 40-keV images compared to ASIR-V 50 keV, while no significant difference in noise was identified except for 1 and 3 mm in aorta and for 1-mm liver measurements, where ASIR-V 50 keV showed 5.5-6.8% (p < 0.002) lower noise levels. Qualitative assessment demonstrated significant improvement particularly in 1-mm reconstructions (p < 0.001). Lastly, DLIR 40 keV demonstrated comparable or improved image quality ratings when compared to ASIR-V 50 keV (p < 0.001 to 0.22).

CONCLUSION

DLIR significantly reduced image noise compared to ASIR-V. Qualitative assessment showed that DLIR significantly improved image quality particularly in thin sliced images. DLIR may facilitate 40 keV as a new standard for routine low-keV VM reconstruction in contrast-enhanced abdominal DECT.

KEY POINTS

• DLIR enables 40 keV as the routine low-keV VM reconstruction. • DLIR significantly reduced image noise compared to ASIR-V, across a wide range of keV levels in VM DECT images. • In low-keV VM reconstructions, improvements in image quality using DLIR were most evident and consistent in 1-mm sliced images.

Deep learning versus iterative reconstruction on image quality and dose reduction in abdominal CT: a live animal study

Objective. While simulated low-dose CT images and phantom studies cannot fully approximate subjective and objective effects of deep learning (DL) denoising on image quality, live animal models may afford this assessment. This study is to investigate the potential of DL in CT dose reduction on image quality compared to iterative reconstruction (IR). Approach. The upper abdomen of a live 4 year old sheep was scanned on a CT scanner at different exposure levels. Images were reconstructed using FBP and ADMIRE with 5 strengths. A modularized DL network with 5 modules was used for image reconstruction via progressive denoising. Radiomic features were extracted from a region over the liver. Concordance correlation coefficient (CCC) was applied to quantify agreement between any two sets of radiomic features. Coefficient of variation was calculated to measure variation in a radiomic feature series. Structural similarity index (SSIM) was used to measure the similarity between any two images. Diagnostic quality, low-contrast detectability, and image texture were qualitatively evaluated by two radiologists. Pearson correlation coefficient was computed across all dose-reconstruction/denoising combinations. Results. A total of 66 image sets, with 405 radiomic features extracted from each, are analyzed. IR and DL can improve diagnostic quality and low-contrast detectability and similarly modulate image texture features. In terms of SSIM, DL has higher potential in preserving image structure. There is strong correlation between SSIM and radiologists’ evaluations for diagnostic quality (0.559) and low-contrast detectability (0.635) but moderate correlation for texture (0.313). There is moderate correlation between CCC of radiomic features and radiologists’ evaluation for diagnostic quality (0.397), low-contrast detectability (0.417), and texture (0.326), implying that improvement of image features may not relate to improvement of diagnostic quality. Conclusion. DL shows potential to further reduce radiation dose while preserving structural similarity, while IR is favored by radiologists and more predictably alters radiomic features.

The influence of a deep learning image reconstruction algorithm on the image quality and auto-analysis of pulmonary nodules at ultra-low dose chest CT: a phantom study

BACKGROUND

To investigate the effect of a new deep learning image reconstruction (DLIR) algorithm on the detection, characterization and image quality of pulmonary nodules (PNs) in ultra-low dose chest computed tomography (CT) in comparison with the adaptive statistical iterative reconstruction (ASIR-V) algorithm.

METHODS

Nine artificial pulmonary nodules [six ground glass nodules (GGNs) and three solid nodules (SNs); density: -800 HU, -630 HU, 100 HU; diameter: 12 mm, 10 mm, 8 mm] were randomly placed in a thorax anthropomorphic phantom (Lungman, Kyoto Kagaku Inc.) and scanned on a 256-row CT (Revolution CT, GE Healthcare). Eight scans were performed at 70 kVp with different tube currents (20, 30, 50, 70, 90, 100, 120, 150 mA). Raw data were reconstructed using the filtered back projection (FBP), ASIR-V (30%, 50%, 80%) and DLIR (Low, Medium, High; TrueFidelity™) at 0.625 mm thickness. The effective radiation dose was recorded. All images were automatically analyzed using a commercially available artificial intelligence software (Intelligent 4D Imaging System for Chest CT 5.5, YITU Healthcare) and CT value, standard deviation (SD), long and short diameters of each nodule and SD of air (background) were measured. The detection rate, deformation degree (long diameter/short diameter), signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of pulmonary nodules were calculated.

RESULTS

Nodule CT values were the same in all mA settings for all three types of reconstruction algorithms (all P>0.05). DLIR groups had significantly lower SD and higher SNR and CNR values, with better overall image quality than ASIR-V and FBP groups at each mA, ranging from 65-85% reduction in SD, 67-83% increase in SNR with DLIR-H over 50%ASIR-V and 75-91% reduction in SD and 77-89% increase in SNR with DLIR-H over FBP (all P<0.05). At ultra-low dose conditions (30 mA), the DLIR-H images had the highest detection rate of PNs (100%). In addition, the DLIR-M had a minimal negative effect on the characterization of PNs.

CONCLUSIONS

DLIR algorithm can be a potential reconstruction technique to optimize image quality and improve detection rate of PNs in ultra-low dose lung screening.

Ultralow-dose CT of the petrous bone using iterative reconstruction technique, tin filter and high resolution detectors allows an adequate assessment of the petrous bone structures

OBJECTIVES

To assess image quality and radiation dose in computed tomography (CT) studies of the petrous bone done with a scanner using a tin filter, high-resolution detectors, and iterative reconstruction, and to compare versus in studies done with another scanner without a tin filter using filtered back projection reconstruction.

MATERIAL AND METHODS

Thirty two patients (group 1) were acquired with an ultra-low dose CT (32-MDCT, 130kV, tin filter and iterative reconstruction). Images and radiation doses were compared to 36 patients (group 2) acquired in a 16-MDCT (120kV and filtered back-projection). Muscle density, bone density, and background noise were measured. Signal-to-noise ratio (SNR) was calculated. To assess image quality, two independent radiologists subjectively evaluated the visualization of the different structures of the middle and inner ear (0=not visualized, 3=perfectly identified and delimited). Interobserver agreement was calculated. Effective dose at different anatomical levels with the dose-length product was recorded.

RESULTS

In the quantitative analysis, there were no significant differences in image noise between the two groups. In the qualitative analysis, a similar or slightly lower subjective score was obtained in the delimitation of different structures of the ossicular chain and cochlea in the 32-MDCT, compared to 16-MDCT, with statistically significant differences. Mean effective dose (±standard deviation) was 0.16±0.04mSv for the 32-MDCT and 1.25±0.30mSv for the 16-MDCT.

CONCLUSIONS

The use of scanners with tin filters, high-resolution detectors, and iterative reconstruction allows to obtain images with adequate quality for the evaluation of the petrous bone structures with ultralow doses of radiation (0.16±0.04mSv).

Evaluation of Abdominal CT Obtained Using a Deep Learning-Based Image Reconstruction Engine Compared with CT Using Adaptive Statistical Iterative Reconstruction

Purpose:

Materials and Methods:

Results:

Conclusions:

Dose-Tracking Software: A Retrospective Analysis of Dosimetric Data in CT Procedures

ABSTRACT

The increasing use of ionizing radiation in healthcare is causing growing alarm about radiation protection of patients and the doses they receive during procedures. Radiation dose assessment for patients in radiodiagnostic procedures is the subject of interest in view of the recent Italian D.Lgs 31 July 2020, n. 101 (Decreto Legislativo 31 luglio 2020, n. 101) and one of its most important focuses is the prescription to provide patient exposure information as an integral part of the examination report. Dose monitoring systems are therefore essential for the collection of the dosimetric data. In order to analyse potential and critical issues of these software, different systems, adopted at the Antonio Cardarelli Hospital in Naples, were employed. Data extracted from the DoseWatch software (GE Healthcare) and Gray Detector (EL.CO. S.r.l. Healthcare Solutions, Italy) and relating to several protocols adopted for computed tomography (CT), were retrospectively analysed for the purpose of identifying critical issues in the data acquisition and recording phase, comparing with Italian nationwide diagnostic reference levels (DRLs), as provided for in regulatory provisions for radiation safety. Multiphase examinations were also included in this study. Once the distributions of volumetric CT Dose Index (CTDIvol) and dose-length product (DLP) were determined for each acquisition phase and total DLP (DLPtot) for each examination, the 25th, 50th and 75th percentiles were calculated for each distribution and then compared with the relevant Italian nationwide DRLs. In addition, to improve protocol optimization and dose reduction the magnitude of the CT acquisition settings chosen in each procedure was evaluated. In conclusion, these systems allow accurate analysis of radiation dose according to equipment and protocol over time. For the application of optimization measures, a constant use of the dose tracking software is required, which can be translated into actions on scan parameters and prospective data analysis.

Establishment of national diagnostic reference levels for percutaneous coronary interventions (PCIs) in Thailand

PURPOSE

To establish national diagnostic reference levels (DRLs) for percutaneous coronary intervention (PCI) in Thailand for lesions of different complexity.

METHODS

Radiation dose quantity as kerma-area-product (KAP) and cumulative air-kerma at reference point (CAK) from 76 catheterization labs in 38 hospitals in PCI registry of Thailand was transferred online to central data management. Sixteen months data (May 2018 to August 2019) was analyzed. We also investigated role of different factors that influence radiation dose the most.

RESULTS

Analysis of 22,737 PCIs resulted in national DRLs for PCI of 91.3 Gy.cm² (KAP) and 1360 mGy (CAK). The NDRLs for KAP for type C, B2, B1 and A lesions were 106.8, 82.6, 67.9, and 45.3 Gy.cm² respectively and for CAK, 1705, 1247, 962, and 790 mGy respectively. Thus, as compared to lesion A, lesion C had more than double the dose and B2 had nearly 1.6 times and B1 had 1.2 times CAK. Our DRL values are lower than other Asian countries like Japan and Korea and are in the middle range of Western countries. University hospital had significantly higher dose than private or public hospital possibly because of higher load of complex procedures in university hospitals and trainees performing the procedures. Transradial approach showed lower doses than transfemoral approach.

CONCLUSIONS

This large multi-centric study established DRLs for PCIs which can act as reference for future studies. A hallmark of our study is establishment of reference levels for coronary lesions classified as per ACC/AHA and thus for different complexities.

Ultra-low-dose computed tomography and its utility in wrist trauma in the emergency department

BACKGROUND

The use and frequency of computed tomography (CT) are increasing day by day in emergency departments (ED). This increases the amount of radiation exposed.

PURPOSE

To evaluate the image quality obtained by ultra-low-dose CT (ULDCT) in patients with suspected wrist fractures in the ED and to investigate whether it is an alternative to standard-dose CT (SDCT).

MATERIAL AND METHODS

This is a study prospectively examining 336 patients who consulted the ED for wrist trauma. After exclusion criteria were applied, the patients were divided into the study and control groups. Then, SDCT (120 kVp and 100 mAs) and ULDCT (80 kVp and 5 mAs) wrist protocols were applied simultaneously. The images obtained were evaluated for image quality and fracture independently by a radiologist and an emergency medical specialist using a 5-point scale.

RESULTS

The effective radiation dose calculated for the control group scans was 41.1 ± 2.1 µSv, whereas the effective radiation dose calculated for the study group scans was 0.5 ± 0.0 µSv. The effective radiation dose of the study group was significantly lower than that of the control group (P < 0.01). The CT images in the study group showed no significant differences in the mean image quality score between observer 1 and observer 2 (3.4 and 4.3, respectively; P = 0.58). Both observers could detect all fractures using the ULDCT images.

CONCLUSION

ULDCT provides high-quality images in wrist traumas while reducing the radiation dose by approximately 98% compared to SDCT without any changes in diagnostic accuracy.

Effect of Body Mass Index in Coronary CT Angiography Performed on a 256-Slice Multi-Detector CT Scanner

We aimed to investigate the effect of a patient’s body mass index (BMI) on radiation dose and image quality in prospectively ECG-triggered coronary CT angiography (CCTA) performed on a 256-slice multi-detector CT scanner. In total, 87 consecutive patients receiving CCTA examinations acquired with tube current modulation (TCM) and iterative reconstruction (IR) were enrolled in this study. The dose report recorded from the CT scanner console was used to derive the effective dose for patients. Subjective image quality scoring and objective noise measurements were conducted to quantify the impact of BMI on the image quality of CCTA. Because of the TCM technique, we expected tube current and radiation dose to increase as BMI increased. However, using TCM did not always guarantee sufficient radiation exposure to achieve consistent image quality for overweight or obese patients since the maximum X-ray tube output in milliamperes and kilovoltage peak was reached. The impact of photon starvation noise on image quality was not significant until BMI ≥ 27 kg/m2; this result could be due to IR’s noise reduction capability. Our results also suggest that using TCM with a noise index of 25 HU can reduce radiation dose without compromising image quality compared to images obtained based on the manufacturer’s default settings.

National Trends in Pediatric CT Scans in South Korea: A Nationwide Cohort Study

Purpose

This study evaluated the rates and annual trends of pediatric CT scans in South Korea using a nationwide population-based database.

Materials and Methods

Data regarding pediatric CT scan usage between 2012 and 2017 were retrieved from the health insurance review and assessment service. Data on the age, sex, diagnosis, and the anatomical area of involved patients were also extracted.

Results

A total of 576376 CT examinations were performed among 58527528 children aged below 18 years (9.8 scans/1000 children), and the number of CT examinations per 1000 children was noted to have increased by 23.2% from 9.0 in 2012 to 11.0 in 2017. Specifically, the number of CT examinations increased by 32.9% for the 6–12 years of age group (7.4/1000 to 9.8/1000) and by 34.0% for the 13–18 years of age group (11.4/1000 to 15.3/1000). Moreover, majority of the CT scans were limited to the head (39.1%), followed by the extremities (32.5%) and the abdomen (13.7%). Notably, the number of extremity CT scans increased by 83.6% (2.3/1000 to 4.2/1000), and its proportion as compared to other scans increased from 25.3% to 37.7%.

Conclusion

CT scans in the pediatric population increased continuously from 2012 to 2017 at an annual rate of 4.4%. Therefore, physicians should balance the benefits of CT with its potential harms from associated radiation exposure in pediatric patients.

Radiation dose levels of thoracic-lumbar spine CT in pediatric trauma patients and assessment of scan parameters for dose optimization

BACKGROUND

CT is frequently used for assessing spinal trauma in children.

OBJECTIVE

To establish the local diagnostic reference levels of spine CT examinations in pediatric spinal trauma patients and analyze scan parameters to enable dose optimization.

MATERIALS AND METHODS

In this retrospective study, we included 192 pediatric spinal trauma patients who underwent spine CT. Children were divided into two age groups: 0-10 years (group 1) and 11-17 years (group 2). Each group was subdivided into thoracic, thoracolumbar and lumbar CT groups. CT acquisition parameters (tube potential, in kilovoltage [kV]; mean tube current-time product, in milliamperes [mAs]; reference mAs; collimated slice width; tube rotation time; pitch; scan length) and radiation dose descriptors (volume CT dose index [CTDI_vol] and dose-length product [DLP]) were recorded. The CTDI_vol and DLP values of spine CTs obtained with different tube potential and collimated slice width values were compared for each group.

RESULTS

CTDI_vol and DLP values of thoracolumbar spine CTs in group 1 and lumbar spine CTs in group 2 were significantly lower in CTs acquired with low tube potential levels (P<0.05). CTDI_vol and DLP values of thoracolumbar spine CTs in both groups and lumbar spine CTs in group 2 acquired with high collimated slice width values were significantly lower than in corresponding CTs acquired with low collimated slice width values (P<0.05).

CONCLUSION

Pediatric spine CT radiation doses can be notably reduced from the manufacturers' default protocols while preserving image quality.

Effect of decreased contrast injection flow rate on aortic enhancement in 80-KV peak CT with contrast dose reduction

BACKGROUND

Effect of decreased injection flow rate of contrast agent at the same iodine dose and delivery rate on aortic enhancement has not been clearly elucidated.

PURPOSE

To evaluate the effect of decreased injection flow rate of contrast agent on aortic peak enhancement in a dynamic flow phantom and on aortic enhancement in clinical dynamic 80-kVp computed tomography (CT) with contrast dose reduction.

MATERIAL AND METHODS

In the dynamic flow phantom experiment, the effect of a decreased injection flow rate at the same total iodine dose and delivery rate on simulated aortic peak enhancement was evaluated. In the clinical retrospective study, we searched 312 patients with renal dysfunction who underwent an 80-kVp abdominal dynamic CT with 40% reduction of contrast agent from a standard 120-kVp protocol and measured the aortic enhancement at the level of the hepatic hilum. Independent predictors for aortic enhancement were determined by multiple linear regression analysis, and after adjustment of significant predictors, independent variables for acquiring optimal aortic enhancement, ≥300 HU, were determined by multiple logistic regression analysis.

RESULTS

In the phantom experiment, decreased flow rate showed a significant but small descent effect (6%-9%) on simulated aortic peak enhancement. In the multiple linear regression analysis, only age was an independent predictor of aortic enhancement; there was no independent predictor for optimal age-adjusted aortic enhancement of ≥300 HU.

CONCLUSIONS

Decreased injection flow rate had a small influence on aortic enhancement in vitro but had no significant effect on the aortic enhancement in clinical dynamic 80-kVp CT.

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.

Fluorine-18-fluorodeoxyglucose (FDG) positron emission tomography (PET) computed tomography (CT) for the detection of bone, lung, and lymph node metastases in rhabdomyosarcoma

BACKGROUND

Rhabdomyosarcoma (RMS) is the most common paediatric soft-tissue sarcoma and can emerge throughout the whole body. For patients with newly diagnosed RMS, prognosis for survival depends on multiple factors such as histology, tumour site, and extent of the disease. Patients with metastatic disease at diagnosis have impaired prognosis compared to those with localised disease. Appropriate staging at diagnosis therefore plays an important role in choosing the right treatment regimen for an individual patient. Fluorine-18-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) is a functional molecular imaging technique that uses the increased glycolysis of cancer cells to visualise both structural information and metabolic activity. 18F-FDG-PET combined with computed tomography (CT) could help to accurately stage the extent of disease in patients with newly diagnosed RMS. In this review we aimed to evaluate whether 18F-FDG-PET could replace other imaging modalities for the staging of distant metastases in RMS.

OBJECTIVES

To determine the diagnostic accuracy of 18F-FDG-PET/CT imaging for the detection of bone, lung, and lymph node metastases in RMS patients at first diagnosis.

SEARCH METHODS

We searched MEDLINE in PubMed (from 1966 to 23 December 2020) and Embase in Ovid (from 1980 to 23 December 2020) for potentially relevant studies. We also checked the reference lists of relevant studies and review articles; scanned conference proceedings; and contacted the authors of included studies and other experts in the field of RMS for information about any ongoing or unpublished studies. We did not impose any language restrictions.

SELECTION CRITERIA

We included cross-sectional studies involving patients with newly diagnosed proven RMS, either prospective or retrospective, if they reported the diagnostic accuracy of 18F-FDG-PET/CT in diagnosing lymph node involvement or bone metastases or lung metastases or a combination of these metastases. We included studies that compared the results of the 18F-FDG-PET/CT imaging with those of histology or with evaluation by a multidisciplinary tumour board as reference standard.

DATA COLLECTION AND ANALYSIS

Two review authors independently performed study selection, data extraction, and methodological quality assessement according to Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). We analysed data for the three outcomes (nodal involvement and lung and bone metastases) separately. We used data from the 2 × 2 tables (consisting of true positives, false positives, true negatives, and false negatives) to calculate sensitivity and specificity in each study and corresponding 95% confidence intervals. We did not consider a formal meta-analysis to be relevant because of the small number of studies and substantial heterogeneity between studies.

MAIN RESULTS

Two studies met our inclusion criteria. The diagnostic accuracy of 18F-FDG-PET/CT was reported in both studies, which included a total of 36 participants. We considered both studies to be at high risk of bias for the domain reference standard. We considered one study to be at high risk of bias for the domain index test and flow and timing. Sensitivity and specificity of 18F-FDG-PET/CT for the detection of bone metastases was 100% in both studies (95% confidence interval (CI) for sensitivity was 29% to 100% in study one and 40% to 100% in study two; 95% CI for specificity was 83% to 100% in study one and 66% to 100% in study two). The reported sensitivity of 18F-FDG-PET/CT for the detection of lung metastases was not calculated since only two participants in study two showed lung metastases, of which one was detected by 18F-FDG-PET/CT. Reported specificity was 96% in study one (95% CI 78% to 100%) and 100% (95% CI 72% to 100%) in study two. The reported sensitivity for the detection of nodal involvement was 100% (95% CI 63% to 100% in study one and 40% to 100% in study two); the reported specificity was 100% (95% CI 78% to 100%) in study one and 89% (95% CI 52% to 100%) in study two.

AUTHORS' CONCLUSIONS

The diagnostic accuracy of 18F-FDG-PET/CT for the detection of bone, lung, and lymph node metastases was reported in only two studies including a total of only 36 participants with newly diagnosed RMS. Because of the small number of studies (and participants), there is currently insufficient evidence to reliably determine the diagnostic accuracy of 18F-FDG-PET/CT in the detection of distant metastases. Larger series evaluating the diagnostic accuracy of 18F-FDG-PET/CT for the detection of metastases in patients with RMS are necessary.

Uncertainty in organ delineation using low-dose computed tomography images with high-strength iterative reconstruction technique in radiotherapy for prostate cancer

Introduction

This study aimed to investigate the uncertainty in organ delineation of low-dose computed tomography (CT) images using a high-strength iterative reconstruction (IR) during radiotherapy planning for the treatment of prostate cancer.

Methods

Two CT datasets were prepared with different dose levels by adjusting the reconstruction slice thickness. Two observers independently delineated the prostate, seminal vesicles, bladder and rectum on both images without referring to other modality images. The delineated organ volumes were compared between both images. Observer delineation variability was assessed using Dice similarity coefficient (DSC) and mean distance to agreement.

Results

No significant differences regarding the delineated organ volumes were observed between the low- and standard-dose images for all organs. Regarding inter-observer variability, the DSC was relatively high for both images, whereas mean distance to agreement was not significantly different between images (p > 0·05 for all). Intra-observer variability for each observer showed high DSC (>0·8 and >0·9 for seminal vesicles and other organs, respectively) but no significant differences in the mean distance to agreement (p > 0·05 for all).

Conclusions

Our results indicate that low-dose CT images with high-strength IR would be available for organ delineation in the radiotherapy treatment planning for prostate cancer.

Image quality assessment of pediatric chest and abdomen CT by deep learning reconstruction

BACKGROUND

Efforts to reduce the radiation dose have continued steadily, with new reconstruction techniques. Recently, image denoising algorithms using artificial neural networks, termed deep learning reconstruction (DLR), have been applied to CT image reconstruction to overcome the drawbacks of iterative reconstruction (IR). The purpose of our study was to compare the objective and subjective image quality of DLR and IR on pediatric abdomen and chest CT images.

METHODS

This retrospective study included pediatric body CT images from February 2020 to October 2020, performed on 51 patients (34 boys and 17 girls; age 1-18 years). Non-contrast chest CT (n = 16), contrast-enhanced chest CT (n = 12), and contrast-enhanced abdomen CT (n = 23) images were included. Standard 50% adaptive statistical iterative reconstruction V (ASIR-V) images were compared to images with 100% ASIR-V and DLR at medium and high strengths. Attenuation, noise, contrast to noise ratio (CNR), and signal to noise (SNR) measurements were performed. Overall image quality, artifacts, and noise were subjectively assessed by two radiologists using a four-point scale (superior, average, suboptimal, and unacceptable). A phantom scan was performed including the dose range of the clinical images used in our study, and the noise power spectrum (NPS) was calculated. Quantitative and qualitative parameters were compared using repeated-measures analysis of variance (ANOVA) with Bonferroni correction and Wilcoxon signed-rank tests.

RESULTS

DLR had better CNR and SNR than 50% ASIR-V in both pediatric chest and abdomen CT images. When compared with 50% ASIR-V, high strength DLR was associated with noise reduction in non-contrast chest CT (33.0%), contrast-enhanced chest CT (39.6%), and contrast-enhanced abdomen CT (38.7%) with increases in CNR at 149.1%, 105.8%, and 53.1% respectively. The subjective assessment of overall image quality and the noise was also better on DLR images (p < 0.001). However, there was no significant difference in artifacts between reconstruction methods. From NPS analysis, DLR methods showed a pattern of reducing the magnitude of noise while maintaining the texture.

CONCLUSION

Compared with 50% ASIR-V, DLR improved pediatric body CT images with significant noise reduction. However, artifacts were not improved by DLR, regardless of strength.

Advances in deep learning for computed tomography denoising

Computed tomography (CT) has seen a rapid increase in use in recent years. Radiation from CT accounts for a significant proportion of total medical radiation. However, given the known harmful impact of radiation exposure to the human body, the excessive use of CT in medical environments raises concerns. Concerns over increasing CT use and its associated radiation burden have prompted efforts to reduce radiation dose during the procedure. Therefore, low-dose CT has attracted major attention in the radiology, since CT-associated x-ray radiation carries health risks for patients. The reduction of the CT radiation dose, however, compromises the signal-to-noise ratio, which affects image quality and diagnostic performance. Therefore, several denoising methods have been developed and applied to image processing technologies with the goal of reducing image noise. Recently, deep learning applications that improve image quality by reducing the noise and artifacts have become commercially available for diagnostic imaging. Deep learning image reconstruction shows great potential as an advanced reconstruction method to improve the quality of clinical CT images. These improvements can provide significant benefit to patients regardless of their disease, and further advances are expected in the near future.

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.

Diagnostic performance and image quality of deep learning image reconstruction (DLIR) on unenhanced low-dose abdominal CT for urolithiasis

BACKGROUND

Patients with urolithiasis undergo radiation overexposure from computed tomography (CT) scans. Improvement of image reconstruction is necessary for radiation dose reduction.

PURPOSE

To evaluate a deep learning-based reconstruction algorithm for CT (DLIR) in the detection of urolithiasis at low-dose non-enhanced abdominopelvic CT.

MATERIAL AND METHODS

A total of 75 patients who underwent low-dose abdominopelvic CT for urolithiasis were retrospectively included. Each examination included three reconstructions: DLIR; filtered back projection (FBP); and hybrid iterative reconstruction (IR; ASiR-V 70%). Image quality was subjectively and objectively assessed using attenuation and noise measurements in order to calculate the signal-to-noise ratio (SNR), absolute contrast, and contrast-to-noise ratio (CNR). Attenuation of the largest stones were also compared. Detectability of urinary stones was assessed by two observers.

RESULTS

Image noise was significantly reduced with DLIR: 7.2 versus 17 and 22 for ASiR-V 70% and FBP, respectively. Similarly, SNR and CNR were also higher compared to the standard reconstructions. When the structures had close attenuation values, contrast was lower with DLIR compared to ASiR-V. Attenuation of stones was also lowered in the DLIR series. Subjective image quality was significantly higher with DLIR. The detectability of all stones and stones >3 mm was excellent with DLIR for the two observers (intraclass correlation [ICC] = 0.93 vs. 0.96 and 0.95 vs. 0.99). For smaller stones (<3 mm), results were different (ICC = 0.77 vs. 0.86).

CONCLUSION

For low-dose abdominopelvic CT, DLIR reconstruction exhibited image quality superior to ASiR-V and FBP as well as an excellent detection of urinary stones.

The use of deep learning towards dose optimization in low-dose computed tomography: A scoping review

INTRODUCTION

Low-dose computed tomography tends to produce lower image quality than normal dose computed tomography (CT) although it can help to reduce radiation hazards of CT scanning. Research has shown that Artificial Intelligence (AI) technologies, especially deep learning can help enhance the image quality of low-dose CT by denoising images. This scoping review aims to create an overview on how AI technologies, especially deep learning, can be used in dose optimisation for low-dose CT.

METHODS

Literature searches of ProQuest, PubMed, Cinahl, ScienceDirect, EbscoHost Ebook Collection and Ovid were carried out to find research articles published between the years 2015 and 2020. In addition, manual search was conducted in SweMed+, SwePub, NORA, Taylor & Francis Online and Medic.

RESULTS

Following a systematic search process, the review comprised of 16 articles. Articles were organised according to the effects of the deep learning networks, e.g. image noise reduction, image restoration. Deep learning can be used in multiple ways to facilitate dose optimisation in low-dose CT. Most articles discuss image noise reduction in low-dose CT.

CONCLUSION

Deep learning can be used in the optimisation of patients' radiation dose. Nevertheless, the image quality is normally lower in low-dose CT (LDCT) than in regular-dose CT scans because of smaller radiation doses. With the help of deep learning, the image quality can be improved to equate the regular-dose computed tomography image quality.

IMPLICATIONS TO PRACTICE

Lower dose may decrease patients' radiation risk but may affect the image quality of CT scans. Artificial intelligence technologies can be used to improve image quality in low-dose CT scans. Radiologists and radiographers should have proper education and knowledge about the techniques used.

Scanner dependence of adaptive statistical iterative reconstruction with 3D noise power spectrum central frequency and noise magnitude ratios

PURPOSE

In this study, the noise reduction properties of the adaptive statistical iterative reconstruction (IR) on two different CT scanners of 64 and 256-slice were compared and their differences were assessed.

METHODS AND MATERIALS

The homogeneous module of the ACR CT phantom was scanned on the 64 and 256 slices CT scanners from the same vendor in the range of 15-40 mA. On each scanner, the data were reconstructed using filtered back projection (FBP) and at all strengths of IR with the STANDARD kernel. For each reconstruction, a 3D noise power spectrum (NPS) was calculated and the central frequency ratio in the xy plane (CFR_xy ), CFR in the z-direction (CFR_z ), and noise magnitude ratio (NMR) were derived. CFR is the central frequency ratio of NPS between the denoised image and the FBP image, and NMR is the ratio of the areas under the NPS curves. Ideally, both CFR_xy and CFR_z should be near 1, indicating minimal texture changes in both xy and z directions, while NMR should be as close to 0 as possible, indicating more noise reduction.

RESULTS

When comparing strengths with equivalent impact on noise texture, IR on the 64-slice reduced the noise magnitude in the xy plane more than that on the 256-slice. In the z-direction, the IR on the 256-slice produced a central frequency shift on the 256-slice but not on the 64-slice. In addition, the noise reduction effects of the IR on the 256-slice were affected when radiation exposure was below 2.0 mGy, but there was no observable dose-dependence on the 64-slice.

CONCLUSIONS

Our noise property analysis revealed that iterative reconstructions on different scanner platforms from the same vendor can be distinct, with unique effects on the noise texture and magnitude in CT images. The IR on a 64-slice scanner provides slightly enhanced noise reduction and maintains a noise reduction rate independent of dose, unlike the one on a 256-slice scanner. Notably, the IR on the 64-slice scanner was a 2D noise reduction technique (NRT), while the one on the 256-slice was a 3D NRT. These observations showcase the impact of different NRTs on clinical CT images, even when comparing the same NRT on different scanners.

Bosniak classification of cystic renal masses, version 2019: interpretation pitfalls and recommendations to avoid misclassification

The purpose of this review is to describe the potential sources of variability or discrepancy in interpretation of cystic renal masses under the Bosniak v2019 classification system. Strategies to avoid these pitfalls and clinical examples of diagnostic approaches are also presented. Potential pitfalls in the application of Bosniak v2019 are divided into three categories: interpretative, technical, and mass related. An organized, comprehensive review of possible discrepancies in interpreting Bosniak v2019 cystic masses is presented with pictorial examples of difficult clinical cases and proposed solutions. The scheme provided can guide readers to consistent, precise application of the classification system. Radiologists should be aware of the possible sources of misinterpretation of cystic renal masses when applying Bosniak v2019. Knowing which features and types of cystic masses are prone to interpretive errors, in addition to the inherent trade-offs between the CT and MR techniques used to characterize them, can help radiologists avoid these pitfalls.