Advances in spatial resolution and radiation dose reduction using super-resolution deep learning-based reconstruction for abdominal computed tomography: A phantom study.

RATIONALE AND OBJECTIVES: This study evaluated the performance of super-resolution deep learning-based reconstruction (SR-DLR) and compared with it that of hybrid iterative reconstruction (HIR) and normal-resolution DLR (NR-DLR) for enhancing image quality in computed tomography (CT) images across various field of view (FOV) sizes, radiation doses, and noise reduction strengths. MATERIALS AND METHODS: A Catphan phantom equipped with an external body ring was used. CT images were reconstructed using filtered back-projection (FBP), HIR, NR-DLR, and SR-DLR across three noise reduction strengths: mild, standard, and strong. The noise power spectrum (NPS) was obtained from the FBP, HIR, NR-DLR, and SR-DLR images at various FOVs, radiation doses, and noise reduction strengths. The noise magnitude ratio (NMR) and central frequency ratio (CFR) were calculated from the HIR, NR-DLR, and SR-DLR images relative to the FBP images using NPS. The high-contrast value was obtained from the amplitude values of the peaks and valleys of profile curve and the task-based transfer function were also analyzed. RESULTS: SR-DLR consistently demonstrated superior noise reduction capabilities, with NMR of 0.29-0.36 at reduced dose and 0.35-0.45 at standard dose, outperforming HIR and showing comparable efficiency to NR-DLR. The high-contrast values for SR-DLR were highest at mild and standard levels for both low and standard doses (0.610 and 0.726 at mild and 0.725 and 0.603 at standard levels). At the standard dose, the spatial resolution of SR-DLR was significantly improved, regardless of the noise reduction strength and FOV. CONCLUSION: SR-DLR images achieved more substantial noise reduction than HIR and similar noise reduction as NR-DLR reconstructions while also improving spatial resolution.

Improving Visualization of In-stent Lumen Using Prototype Photon-counting Detector Computed Tomography with High-resolution Plaque Kernel.

The study aimed to compare the performance of photon-counting detector computed tomography (PCD CT) with high-resolution (HR)-plaque kernel with that of the energy-integrating detector CT (EID CT) in terms of the visualization of the lumen size and the in-stent stenotic portion at different coronary vessel angles. The lumen sizes in PCD CT and EID CT images were 2.13 and 1.80 mm at 0°, 2.20 and 1.77 mm at 45°, and 2.27 mm and 1.67 mm at 90°, respectively. The lumen sizes in PCD CT with HR-plaque kernel were wider than those in EID CT. The mean degree of the in-stent stenotic portion at 50% was 69.7% for PCD CT and 90.4% for EID CT. PCD CT images with HR-plaque kernel enable improved visualization of lumen size and accurate measurements of the in-stent stenotic portion compared to conventional EID CT images regardless of the stent direction.

Low tube voltage and deep-learning reconstruction for reducing radiation and contrast medium doses in thin-slice abdominal CT: a prospective clinical trial.

OBJECTIVES: To investigate the feasibility of low-radiation dose and low iodinated contrast medium (ICM) dose protocol combining low-tube voltage and deep-learning reconstruction (DLR) algorithm in thin-slice abdominal CT. METHODS: This prospective study included 148 patients who underwent contrast-enhanced abdominal CT with either 120-kVp (600 mgL/kg, n = 74) or 80-kVp protocol (360 mgL/kg, n = 74). The 120-kVp images were reconstructed using hybrid iterative reconstruction (HIR) (120-kVp-HIR), while 80-kVp images were reconstructed using HIR (80-kVp-HIR) and DLR (80-kVp-DLR) with 0.5 mm thickness. Size-specific dose estimate (SSDE) and iodine dose were compared between protocols. Image noise, CT attenuation, and contrast-to-noise ratio (CNR) were quantified. Noise power spectrum (NPS) and edge rise slope (ERS) were used to evaluate noise texture and edge sharpness, respectively. The subjective image quality was rated on a 4-point scale. RESULTS: SSDE and iodine doses of 80-kVp were 40.4% (8.1 ± 0.9 vs. 13.6 ± 2.7 mGy) and 36.3% (21.2 ± 3.9 vs. 33.3 ± 4.3 gL) lower, respectively, than those of 120-kVp (both, p < 0.001). CT attenuation of vessels and solid organs was higher in 80-kVp than in 120-kVp images (all, p < 0.001). Image noise of 80-kVp-HIR and 80-kVp-DLR was higher and lower, respectively than that of 120-kVp-HIR (both p < 0.001). The highest CNR and subjective scores were attained in 80-kVp-DLR (all, p < 0.001). There were no significant differences in average NPS frequency and ERS between 120-kVp-HIR and 80-kVp-DLR (p ≥ 0.38). CONCLUSION: Compared with the 120-kVp-HIR protocol, the combined use of 80-kVp and DLR techniques yielded superior subjective and objective image quality with reduced radiation and ICM doses at thin-section abdominal CT. CLINICAL RELEVANCE STATEMENT: Scanning at low-tube voltage (80-kVp) combined with the deep-learning reconstruction algorithm may enhance diagnostic efficiency and patient safety by improving image quality and reducing radiation and contrast doses of thin-slice abdominal CT. KEY POINTS: Reducing radiation and iodine doses is desirable; however, contrast and noise degradation can be detrimental. The 80-kVp scan with the deep-learning reconstruction technique provided better images with lower radiation and contrast doses. This technique may be efficient for improving diagnostic confidence and patient safety in thin-slice abdominal CT.

Prediction of endovascular leaks after thoracic endovascular aneurysm repair though machine learning applied to pre-procedural computed tomography angiographs.

To predict endoleaks after thoracic endovascular aneurysm repair (TEVAR) we submitted patient characteristics and vessel features observed on pre- operative computed tomography angiography (CTA) to machine-learning. We evaluated 1-year follow-up CT scans (arterial and delayed phases) in patients who underwent TEVAR for the presence or absence of an endoleak. We evaluated the effect of machine learning of the patient age, sex, weight, and height, plus 22 vascular features on the ability to predict post-TEVAR endoleaks. The extreme Gradient Boosting (XGBoost) for ML system was trained on 14 patients with- and 131 without endoleaks. We calculated their importance by applying XGBoost to machine learning and compared our findings between with those of conventional vessel measurement-based methods such as the 22 vascular features by using the Pearson correlation coefficients. Pearson correlation coefficient and 95% confidence interval (CI) were r = 0.86 and 0.75 to 0.92 for the machine learning, r = - 0.44 and - 0.56 to - 0.29 for the vascular angle, and r = - 0.19 and - 0.34 to - 0.02 for the diameter between the subclavian artery and the aneurysm (Fig. 3a-c, all: p < 0.05). With machine-learning, the univariate analysis was significant higher compared with the vascular angle and in the diameter between the subclavian artery and the aneurysm such as the conventional methods (p < 0.05). To predict the risk for post-TEVAR endoleaks, machine learning was superior to the conventional vessel measurement method when factors such as patient characteristics, and vascular features (vessel length, diameter, and angle) were evaluated on pre-TEVAR thoracic CTA images.

Diagnostic performance of unenhanced electrocardiogram-gated cardiac CT for detecting myocardial edema.

To assess the diagnostic performance of unenhanced electrocardiogram (ECG)-gated cardiac computed tomography (CT) for detecting myocardial edema, using MRI T2 mapping as the reference standard. This retrospective study protocol was approved by our institutional review board, which waived the requirement for written informed consent. Between December 2017 to February 2019, consecutive patients who had undergone T2 mapping for myocardial tissue characterization were identified. We excluded patients who did not undergo unenhanced ECG-gated cardiac CT within 3 months from MRI T2 mapping or who had poor CT image quality. All patients underwent unenhanced ECG-gated cardiac CT with an axial scan using a third-generation, 320 × 0.5 mm detector-row CT unit. Two radiologists together drew regions of interest (ROIs) in the interventricular septum on the unenhanced ECG-gated cardiac CT images. Using T2 mapping as the reference standard, the diagnostic performance of unenhanced cardiac CT for detecting myocardial edema was evaluated by using the area under the receiver operating characteristic curve with sensitivity and specificity. Youden index was used to find an optimal sensitivity-specificity cutoff point. A cardiovascular radiologist independently performed the measurements, and interobserver reliability was assessed using intraclass correlation coefficients for CT value measurements. A P value of <.05 was considered statistically significant. We included 257 patients who had undergone MRI T2 mapping. Of the 257 patients, 35 patients underwent unenhanced ECG-gated cardiac CT. One patient was excluded from the study because of poor CT image quality. Finally, 34 patients (23 men; age 64.7 ±â€…14.6 years) comprised our study group. Using T2 mapping, we identified myocardial edema in 19 patients. Mean CT and T2 values for 34 patients were 46.3 ±â€…2.7 Hounsfield unit and 49.0 ±â€…4.9 ms, respectively. Mean CT values moderately correlated with mean T2 values (Rho = -0.41; P < .05). Mean CT values provided a sensitivity of 63.2% and a specificity of 93.3% for detecting myocardial edema, with a cutoff value of ≤45.0 Hounsfield unit (area under the receiver operating characteristic curve = 0.77; P < .01). Inter-observer reproducibility in measuring mean CT values was excellent (intraclass correlation coefficient = 0.93; [95% confidence interval: 0.86, 0.96]). Myocardial edema could be detected by CT value of myocardium in unenhanced ECG-gated cardiac CT.

A Novel Approach to Detecting Contrast Extravasation in Computed Tomography: Evaluating the Injection Pressure-to-Injection Rate Ratio.

OBJECTIVE: The purpose of this study was to evaluate the usefulness of the injection pressure-to-injection rate (IPIR) ratio for the early detection of contrast extravasation at the venipuncture site during contrast-enhanced computed tomography. METHODS: We retrospectively enrolled 57,528 patients who underwent contrast-enhanced computed tomography examinations in a single hospital. The power injector recorded the contrast injection pressure at 0.25-second intervals. We constructed logistic regression models using the IPIR ratio as the independent variable and extravasation occurrence as the dependent variable (IPIR ratio models) at 1, 2, 3, 4, 5, and 6 seconds after the start of contrast administration. Univariate logistic regression models in which injection pressure is used as an independent variable (injection pressure models) were also constructed as a reference baseline. The performance of the models was evaluated with the area under the receiver operating characteristic curves. RESULTS: Of the 57,528 cases, 46,022 were assigned to the training group and 11,506 were assigned to the test group, which included 112 extravasation cases (0.24%) in the training group and 28 (0.24%) in the test group. The area under the receiver operating characteristic curves for the IPIR ratio models and injection pressure models were 0.555 versus 0.563 at t = 1 (P = 0.270), 0.712 versus 0.678 at t = 2 (P = 0.305), 0.758 versus 0.693 at t = 3 (P = 0.032), 0.776 versus 0.688 at t = 4 (P = 0.005), 0.810 versus 0.699 at t = 5 (P = 0.002), and 0.811 versus 0.706 at t = 6 (P = 0.002). CONCLUSIONS: The IPIR ratio models perform better in detecting contrast extravasation at 3 to 6 seconds after the start of contrast administration than injection pressure models.

Using Patient-Specific Contrast Enhancement Optimizer Simulation Software During the Transcatheter Aortic Valve Implantation-Computed Tomography Angiography in Patients With Aortic Stenosis.

OBJECTIVES: This study assessed whether patient-specific contrast enhancement optimizer simulation software (p-COP) can reduce the contrast material (CM) dose compared with the conventional body weight (BW)-tailored scan protocol during transcatheter aortic valve implantation-computed tomography angiography (TAVI-CTA) in patients with aortic stenosis. METHODS: We used the CM injection protocol selected by the p-COP in group A (n = 30). p-COP uses an algorithm that concerns data on an individual patient's cardiac output. Group B (n = 30) was assigned to the conventional BW-tailored CM injection protocol group. We compared the CM dose, CM amount, injection rate, and computed tomography (CT) values in the abdominal aorta between the 2 groups and classified them as acceptable (>280 Hounsfield units (HU)) or unacceptable (<279 HU) based on the optimal CT value and visualization scores for TAVI-CTA. We used the Mann-Whitney U test to compare patient characteristics and assess the interpatient variability of subjects in both groups. RESULTS: Group A received 56.2 mL CM and 2.6 mL/s of injection, whereas group B received 76.9 mL CM and 3.4 mL/s of injection ( P < 0.01). The CT value for the abdominal aorta at the celiac level was 287.0 HU in group A and 301.7HU in group B ( P = 0.46). The acceptable (>280 HU) and unacceptable (<280 HU) CT value rates were 22 and 8 patients in group A and 24 and 6 patients in group B, respectively ( P = 0.76). We observed no significant differences in the visualization scores between groups A and B (visualization score = 3, P = 0.71). CONCLUSION: The utilization of p-COP may decrease the CM dosage and injection rate by approximately 30% in individuals with aortic stenosis compared with the body-weight-tailored scan protocol during TAVI-CTA.

Evaluation of four computed tomography reconstruction algorithms using a coronary artery phantom.

Background: Despite advancements in coronary computed tomography angiography (CTA), challenges in positive predictive value and specificity remain due to limited spatial resolution. The purpose of this experimental study was to investigate the effect of 2nd generation deep learning-based reconstruction (DLR) on the quantitative and qualitative image quality in coronary CTA. Methods: A vessel model with stepwise non-calcified plaque was scanned using 320-detector CT. Image reconstruction was performed using four techniques: hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), DLR, and 2nd generation DLR. The luminal peak CT number, contrast-to-noise ratio (CNR), and edge rise slope (ERS) were quantitatively evaluated via profile curve analysis. Two observers qualitatively graded the graininess, lumen sharpness, and overall lumen visibility on the basis of the degree of confidence for the stenosis severity using a five-point scale. Results: The image noise with HIR, MBIR, DLR, and 2nd generation DLR was 23.0, 21.0, 16.9, and 9.5 HU, respectively. The corresponding CNR (25% stenosis) was 15.5, 15.9, 22.1, and 38.3, respectively. The corresponding ERS (25% stenosis) was 203.2, 198.6, 228.9, and 262.4 HU/mm, respectively. Among the four reconstruction methods, the 2nd generation DLR achieved the significantly highest CNR and ERS values. The score of 2nd generation DLR in all evaluation points (graininess, sharpness, and overall lumen visibility) was higher than those of the other methods (overall vessel visibility score, 2.6±0.5, 3.8±0.6, 3.7±0.5, and 4.6±0.5 with HIR, MBIR, DLR, and 2nd generation DLR, respectively). Conclusions: 2nd generation DLR provided better CNR and ERS in coronary CTA than HIR, MBIR, and previous-generation DLR, leading to the highest subjective image quality in the assessment of vessel stenosis.

The Feasibility of Using a Deep Learning-Based Model to Determine Cardiac Computed Tomographic Contrast Dose.

PURPOSE: This study aimed to predict contrast effects in cardiac computed tomography (CT) from CT localizer radiographs using a deep learning (DL) model and to compare the prediction performance of the DL model with that of conventional models based on patients' physical size. METHODS: This retrospective study included 473 (256 men and 217 women) cardiac CT scans between May 2014 and August 2017. We developed and evaluated DL models that predict milligrams of iodine per enhancement of the aorta from CT localizer radiographs. To assess the model performance, we calculated and compared Pearson correlation coefficient ( r ) between the actual iodine dose that was necessary to obtain a contrast effect of 1 HU (iodine dose per contrast effect [IDCE]) and IDCE predicted by DL, body weight, lean body weight, and body surface area of patients. RESULTS: The model was tested on 52 cases for the male group (mean [SD] age, 63.7 ± 11.4) and 44 cases for the female group (mean [SD] age, 69.8 ± 11.6). Correlation coefficients between the actual and predicted IDCE were 0.607 for the male group and 0.412 for the female group, which were higher than the correlation coefficients between the actual IDCE and body weight (0.539 for male, 0.290 for female), lean body weight (0.563 for male, 0.352 for female), and body surface area (0.587 for male, 0.349 for female). CONCLUSIONS: The performance for predicting contrast effects by analyzing CT localizer radiographs with the DL model was at least comparable with conventional methods using the patient's body size, notwithstanding that no additional measurements other than CT localizer radiographs were required.

Cardiac computed tomography angiography with and without bolus tracking methods in infants with congenital heart disease.

The study investigated radiation dose, vascular computed tomography (CT) enhancement and image quality of cardiac computed tomography angiography (CCTA) with and without bolus tracking (BT) methods in infants with congenital heart disease (CHD). The volume CT dose index (CTDIvol) and dose length product (DLP) were recorded for all CT scans, and the effective dose was obtained using a conversion factors. The CT number for the ascending aorta (AO) and pulmonary artery (PA), image noise of muscle tissue and contrast-to-noise ratio (CNR) were measured and calculated. The median values in the groups with and without BT were 2.20 mGy versus 0.44 mGy for CTDIvol, 8.10 mGy·cm versus 6.20 mGy·cm for DLP, and 0.66 mSv versus 0.51 mSv for effective dose (p < 0.001). There were no statistical differences in vascular CT enhancement, image noise, and CNR. CCTA without BT methods can reduce the radiation dose while maintaining vascular CT enhancement and image quality compared to CCTA with BT methods.

Preliminary assessment of automated radiology report generation with generative pre-trained transformers: comparing results to radiologist-generated reports.

PURPOSE: In this preliminary study, we aimed to evaluate the potential of the generative pre-trained transformer (GPT) series for generating radiology reports from concise imaging findings and compare its performance with radiologist-generated reports. METHODS: This retrospective study involved 28 patients who underwent computed tomography (CT) scans and had a diagnosed disease with typical imaging findings. Radiology reports were generated using GPT-2, GPT-3.5, and GPT-4 based on the patient's age, gender, disease site, and imaging findings. We calculated the top-1, top-5 accuracy, and mean average precision (MAP) of differential diagnoses for GPT-2, GPT-3.5, GPT-4, and radiologists. Two board-certified radiologists evaluated the grammar and readability, image findings, impression, differential diagnosis, and overall quality of all reports using a 4-point scale. RESULTS: Top-1 and Top-5 accuracies for the different diagnoses were highest for radiologists, followed by GPT-4, GPT-3.5, and GPT-2, in that order (Top-1: 1.00, 0.54, 0.54, and 0.21, respectively; Top-5: 1.00, 0.96, 0.89, and 0.54, respectively). There were no significant differences in qualitative scores about grammar and readability, image findings, and overall quality between radiologists and GPT-3.5 or GPT-4 (p > 0.05). However, qualitative scores of the GPT series in impression and differential diagnosis scores were significantly lower than those of radiologists (p < 0.05). CONCLUSIONS: Our preliminary study suggests that GPT-3.5 and GPT-4 have the possibility to generate radiology reports with high readability and reasonable image findings from very short keywords; however, concerns persist regarding the accuracy of impressions and differential diagnoses, thereby requiring verification by radiologists.

Improving image quality with super-resolution deep-learning-based reconstruction in coronary CT angiography.

OBJECTIVES: To evaluate the effect of super-resolution deep-learning-based reconstruction (SR-DLR) on the image quality of coronary CT angiography (CCTA). METHODS: Forty-one patients who underwent CCTA using a 320-row scanner were retrospectively included. Images were reconstructed with hybrid (HIR), model-based iterative reconstruction (MBIR), normal-resolution deep-learning-based reconstruction (NR-DLR), and SR-DLR algorithms. For each image series, image noise, and contrast-to-noise ratio (CNR) at the left main trunk, right coronary artery, left anterior descending artery, and left circumflex artery were quantified. Blooming artifacts from calcified plaques were measured. Image sharpness, noise magnitude, noise texture, edge smoothness, overall quality, and delineation of the coronary wall, calcified and noncalcified plaques, cardiac muscle, and valves were subjectively ranked on a 4-point scale (1, worst; 4, best). The quantitative parameters and subjective scores were compared among the four reconstructions. Task-based image quality was assessed with a physical evaluation phantom. The detectability index for the objects simulating the coronary lumen, calcified plaques, and noncalcified plaques was calculated from the noise power spectrum (NPS) and task-based transfer function (TTF). RESULTS: SR-DLR yielded significantly lower image noise and blooming artifacts with higher CNR than HIR, MBIR, and NR-DLR (all p < 0.001). The best subjective scores for all the evaluation criteria were attained with SR-DLR, with significant differences from all other reconstructions (p < 0.001). In the phantom study, SR-DLR provided the highest NPS average frequency, TTF50%, and detectability for all task objects. CONCLUSION: SR-DLR considerably improved the subjective and objective image qualities and object detectability of CCTA relative to HIR, MBIR, and NR-DLR algorithms. CLINICAL RELEVANCE STATEMENT: The novel SR-DLR algorithm has the potential to facilitate accurate assessment of coronary artery disease on CCTA by providing excellent image quality in terms of spatial resolution, noise characteristics, and object detectability. KEY POINTS: • SR-DLR designed for CCTA improved image sharpness, noise property, and delineation of cardiac structures with reduced blooming artifacts from calcified plaques relative to HIR, MBIR, and NR-DLR. • In the task-based image-quality assessments, SR-DLR yielded better spatial resolution, noise property, and detectability for objects simulating the coronary lumen, coronary calcifications, and noncalcified plaques than other reconstruction techniques. • The image reconstruction times of SR-DLR were shorter than those of MBIR, potentially serving as a novel standard-of-care reconstruction technique for CCTA performed on a 320-row CT scanner.

Coronary Stent Evaluation by CTA: Image Quality Comparison Between Super-Resolution Deep Learning Reconstruction and Other Reconstruction Algorithms.

BACKGROUND. A super-resolution deep learning reconstruction (SR-DLR) algorithm may provide better image sharpness than earlier reconstruction algorithms and thereby improve coronary stent assessment on coronary CTA. OBJECTIVE. The purpose of our study was to compare SR-DLR and other reconstruction algorithms in terms of image quality measures related to coronary stent evaluation in patients undergoing coronary CTA. METHODS. This retrospective study included patients with at least one coronary artery stent who underwent coronary CTA between January 2020 and December 2020. Examinations were performed using a 320-row normal-resolution scanner and were reconstructed with hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), normal-resolution deep learning reconstruction (NR-DLR), and SR-DLR algorithms. Quantitative image quality measures were determined. Two radiologists independently reviewed images to rank the four reconstructions (4-point scale: 1 = worst reconstruction, 4 = best reconstruction) for qualitative measures and to score diagnostic confidence (5-point scale: score ≥ 3 indicating an assessable stent). The assessability rate was calculated for stents with a diameter of 3.0 mm or less. RESULTS. The sample included 24 patients (18 men, six women; mean age, 72.5 ± 9.8 [SD] years), with 51 stents. SR-DLR, in comparison with the other reconstructions, yielded lower stent-related blooming artifacts (median, 40.3 vs 53.4-58.2), stent-induced attenuation increase ratio (0.17 vs 0.27-0.31), and quantitative image noise (18.1 vs 20.9-30.4 HU) and higher in-stent lumen diameter (2.4 vs 1.7-1.9 mm), stent strut sharpness (327 vs 147-210 ΔHU/mm), and CNR (30.0 vs 16.0-25.6) (all p < .001). For both observers, all ranked measures (image sharpness; image noise; noise texture; delineation of stent strut, in-stent lumen, coronary artery wall, and calcified plaque surrounding the stent) and diagnostic confidence showed a higher score for SR-DLR (median, 4.0 for all features) than for the other reconstructions (range, 1.0-3.0) (all p < .001). The assessability rate for stents with a diameter of 3.0 mm or less (n = 37) was higher for SR-DLR (86.5% for observer 1 and 89.2% for observer 2) than for HIR (35.1% and 43.2%), MBIR (59.5% and 62.2%), and NR-DLR (62.2% and 64.9%) (all p < .05). CONCLUSION. SR-DLR yielded improved delineation of the stent strut and in-stent lumen, with better image sharpness and less image noise and blooming artifacts, in comparison with HIR, MBIR, and NR-DLR. CLINICAL IMPACT. SR-DLR may facilitate coronary stent assessment on a 320-row normal-resolution scanner, particularly for small-diameter stents.

Can Machine Learning Identify the Intravenous Contrast Dose and Injection Rate Needed for Optimal Enhancement on Dynamic Liver Computed Tomography?

OBJECTIVES: This study aimed to investigate whether machine learning (ML) is useful for predicting the contrast material (CM) dose required to obtain a clinically optimal contrast enhancement in hepatic dynamic computed tomography (CT). METHODS: We trained and evaluated ensemble ML regressors to predict the CM doses needed for optimal enhancement in hepatic dynamic CT using 236 patients for a training data set and 94 patients for a test data set. After the ML training, we randomly divided using the ML-based (n = 100) and the body weight (BW)-based protocols (n = 100) by the prospective trial. The BW protocol was performed using routine protocol (600 mg/kg of iodine) by the prospective trial. The CT numbers of the abdominal aorta and hepatic parenchyma, CM dose, and injection rate were compared between each protocol using the paired t test. Equivalence tests were performed with equivalent margins of 100 and 20 Hounsfield units for the aorta and liver, respectively. RESULTS: The CM dose and injection rate for the ML and BW protocols were 112.3 mL and 3.7 mL/s, and 118.0 mL and 3.9 mL/s ( P < 0.05). There were no significant differences in the CT numbers of the abdominal aorta and hepatic parenchyma between the 2 protocols ( P = 0.20 and 0.45). The 95% confidence interval for the difference in the CT number of the abdominal aorta and hepatic parenchyma between 2 protocols was within the range of predetermined equivalence margins. CONCLUSIONS: Machine learning is useful for predicting the CM dose and injection rate required to obtain the optimal clinical contrast enhancement for hepatic dynamic CT without reducing the CT number of the abdominal aorta and hepatic parenchyma.

Usefulness of electrocardiogram mA modulation during the electrocardiogram-gated CT scan in paediatrics with high heart rate for different helical pitch: a phantom-based assessment study.

We investigated the effect of electrocardiographic (ECG) mA-modulation of ECG-gated scans of computed tomography (CTA) on radiation dose and image noise at high heart rates (HR) above 100 bpm between helical pitches (HP) 0.16 and 0.24. ECG mA-modulation range during ECG-gated CTA is 50-100 mA, the phase setting is 40-60% and the scan range is 90 mm for clinical data during HR for 90, 120 and 150 bpm. Radiation dose and image noise in Housfield units are measured for CT equipment during HR for 90, 120 and 150 bpm between HP 0.16 and 0.24. ECG mA-modulation, dose reduction ratio for HR 90, 120 and 150 bpm are 19.1, 13.4 and 8.7% at HP 0.16 and 17.1, 13.3 and 7.7% at HP 0.24, respectively. No significant differences were observed in image noise between both HP. Dose reductions of 8-24% are achieved with ECG mA-modulation during ECG-gated CCTA scan, which is beneficial even in high HR more than 100 bpm.

Noise power spectrum properties of deep learning-based reconstruction and iterative reconstruction algorithms: Phantom and clinical study.

PURPOSE: To compare the noise power spectrum (NPS) properties and perform a qualitative analysis of hybrid iterative reconstruction (IR), model-based IR (MBIR), and deep learning-based reconstruction (DLR) at a similar noise level in clinical study and compare these outcomes with those in phantom study. METHODS: A Catphan phantom with an external body ring was used in the phantom study. In the clinical study, computed tomography (CT) examination data of 34 patients were reviewed. NPS was calculated from DLR, hybrid IR, and MBIR images. The noise magnitude ratio (NMR) and the central frequency ratio (CFR) were calculated from DLR, hybrid IR, and MBIR images relative to filtered back-projection images using NPS. Clinical images were independently reviewed by two radiologists. RESULTS: In the phantom study, DLR with a mild level had a similar noise level as hybrid IR and MBIR with strong levels. In the clinical study, DLR with a mild level had a similar noise level as hybrid IR with standard and MBIR with strong levels. The NMR and CFR were 0.40 and 0.76 for DLR, 0.42 and 0.55 for hybrid IR, and 0.48 and 0.62 for MBIR. The visual inspection of the clinical DLR image was superior to that of the hybrid IR and MBIR images. CONCLUSION: Deep learning-based reconstruction improves overall image quality with substantial noise reduction while maintaining image noise texture compared with the CT reconstruction techniques.

Image-quality characteristics in the longitudinal direction from different image-reconstruction algorithms during single-rotation volume acquisition on head computed tomography: A phantom study.

Background: A multi detector computed tomography (CT) scanner with wide-area coverage enables whole-brain volumetric scanning in a single rotation. Purpose: To investigate variations in image-quality characteristics in the longitudinal direction for different image-reconstruction algorithms and strengths with phantoms. Material and methods: Single-rotation volume scans were performed on a 320-row multidetector CT volume scanner using three types of phantoms. Tube current was set to 200 mA (standard dose) and 50 mA (low dose). All images were reconstructed with filtered back projection (FBP), mild and strong levels with hybrid iterative reconstruction (HIR), and model-based IR (MBIR). Computed tomography numbers, image noise, noise power spectrum (NPS), task-based transfer function (TTF), and visual spatial resolution were used to evaluate uniformity of image quality in the longitudinal direction (Z-axis). Results: The MBIR images showed smaller variation in CT numbers in the Z-axis. The difference in the highest and lowest CT numbers was smaller (5.0 Hounsfield units [HU]) for MBIR than for FBP (6.6 HU) and HIR (6.8 HU). The variations in image noise were the smallest for strong MBIR and the largest for FBP. The low-frequency component at NPS0.2 was lower for strong MBIR than for other algorithms. The high-frequency component at NPS0.8 was low in all reconstructions. For MBIR, the image resolution and TTFs were higher in the outer portion than in the center. Conclusion: Model-based IR is the optimal image-reconstruction algorithm for single-volume scan of spherical subjects owing to its high in-plane resolution and uniformity of CT numbers, image noise, and NPS in the Z-axis.

Effect of patient characteristics on vessel enhancement on arterio-venous fistula CT angiography in a retrospective cohort study.

To evaluate the effects of various patient characteristics on vessel enhancement on arterio-venous fistula (AVF) computed tomography (CT) angiography (AVF-CT angiography). A total of 127 patients with suspected or confirmed shunt stenosis and internal AVF complications were considered for inclusion in a retrospective cohort study. The tube voltage was 120 kVp, and the tube current was changed from 300 to 770 mA to maintain the image quality (noise index: 14) using automatic tube current modulation. To evaluate the effects of age, sex, body size, and scan delay on the CT number of the brachial artery or vein, we used correlation coefficients and multivariate regression analyses. There was a significant positive correlation between the CT number of the brachial artery or vein and age (R = 0.21 or 0.23, P < .01). The correlations were inverse with the height (r = -0.45 or -0.42), total body weight (r = -0.52 or -0.50), body mass index (r = -0.21 or -0.23), body surface area (body surface area [BSA]; r = -0.56 or -0.54), and lean body weight (r = -0.55 or -0.53) in linear regression analysis (P < .01 for all). There was a significant correlation between the CT number of the brachial artery or vein and scan delay (R = 0.19 or 01.9, P < .01). Only the BSA had significant effects on the CT number in multivariate regression analysis (P < .01). The BSA was significantly correlated with the CT number of the brachial artery or vein on AVF-CT angiography.

[Comparison of Lower Extremity Computed Tomography Angiography by Using Different Subtraction Techniques].

PURPOSE: To compare the diagnostic capabilities of orbital synchronized helical scanning at lower extremity computed tomography angiography between the Add/Sub software and the deformable image registration. METHODS: From March 2015 to December 2016, 100 dialysis patients underwent orbital synchronized lower limb CT subtraction angiography and lower limb endovascular treatment within 4 months. For the visual evaluation of blood vessels in the lower extremities, a stenosis rate of 50% or more was considered to be stenosis. It was classified into two areas: above-knee (AK) region (superficial femoral artery and popliteal artery) and below-knee (BK) region (anterior tibial artery, posterior tibial artery, and fibula artery). Considering angiography for the lower limb endovascular treatment as the golden standard, we calculated the sensitivity, specificity, positive-predictive value, negative-predictive value, and diagnostic capabilities. Receiver operating characteristic curve (ROC) analysis was performed to calculate the area under curve (AUC). RESULTS: Calcification subtraction failure was observed to be 11% in the AK region and 2% in the BK region using the Add/Sub software. The specificity, positive-predictive value, diagnostic capabilities, and AUC of the deformable image registration were lower than those of the Add/Sub software. CONCLUSIONS: Add/Sub software and deformable image registration have high diagnostic capability to remove calcification. On the other hand, the specificity and AUC of the deformable image registration were lower than those of the Add/Sub software. Also, even if the same deformable image registration is used, caution is required because the diagnostic performance varies depending on the site.