Enhanced visualization in endoleak detection through iterative and AI-noise optimized spectral reconstructions.

To assess the image quality parameters of dual-energy computed tomography angiography (DECTA) 40-, and 60 keV virtual monoenergetic images (VMIs) combined with deep learning-based image reconstruction model (DLM) and iterative reconstructions (IR). CT scans of 28 post EVAR patients were enrolled. The 60 s delayed phase of DECTA was evaluated. Objective [noise, contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR)] and subjective (overall image quality and endoleak conspicuity - 3 blinded readers assessment) image quality analyses were performed. The following reconstructions were evaluated: VMI 40, 60 keV VMI; IR VMI 40, 60 keV; DLM VMI 40, 60 keV. The noise level of the DLM VMI images was approximately 50% lower than that of VMI reconstruction. The highest CNR and SNR values were measured in VMI DLM images. The mean CNR in endoleak in 40 keV was accounted for as 1.83 ± 1.2; 2.07 ± 2.02; 3.6 ± 3.26 in VMI, VMI IR, and VMI DLM, respectively. The DLM algorithm significantly reduced noise and increased lesion conspicuity, resulting in higher objective and subjective image quality compared to other reconstruction techniques. The application of DLM algorithms to low-energy VMIs significantly enhances the diagnostic value of DECTA in evaluating endoleaks. DLM reconstructions surpass traditional VMIs and IR in terms of image quality.

A Deep Learning Image Reconstruction Algorithm for Improving Image Quality and Hepatic Lesion Detectability in Abdominal Dual-Energy Computed Tomography: Preliminary Results.

This study aimed to compare the performance of deep learning image reconstruction (DLIR) and adaptive statistical iterative reconstruction-Veo (ASIR-V) in improving image quality and diagnostic performance using virtual monochromatic spectral images in abdominal dual-energy computed tomography (DECT). Sixty-two patients [mean age ± standard deviation (SD): 56 years ± 13; 30 men] who underwent abdominal DECT were prospectively included in this study. The 70-keV DECT images in the portal phase were reconstructed at 5-mm and 1.25-mm slice thicknesses with 40% ASIR-V (ASIR-V40%) and at 1.25-mm slice with deep learning image reconstruction at medium (DLIR-M) and high (DLIR-H) levels and then compared. Computed tomography (CT) attenuation, SD values, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured in the liver, spleen, erector spinae, and intramuscular fat. The lesions in each reconstruction group at 1.25-mm slice thickness were counted. The image quality and diagnostic confidence were subjectively evaluated by two radiologists using a 5-point scale. For the 1.25-mm images, DLIR-M and DLIR-H had lower SD, higher SNR and CNR, and better subjective image quality compared with ASIR-V40%; DLIR-H performed the best (all P values < 0.001). Furthermore, the 1.25-mm DLIR-H images had similar SD, SNR, and CNR values as the 5-mm ASIR-V40% images (all P > 0.05). Three image groups had similar lesion detection rates, but DLIR groups exhibited higher confidence in diagnosing lesions. Compared with ASIR-V40% at 70 keV, 70-keV DECT with DLIR-H further reduced image noise and improved image quality. Additionally, it improved diagnostic confidence while ensuring a consistent lesion detection rate of liver lesions.

Impact of deep learning-based image reconstruction on image quality and lesion visibility in renal computed tomography at different doses.

Background: Numerous computed tomography (CT) image reconstruction algorithms have been developed to improve image quality, and high-quality renal CT images are crucial to clinical diagnosis. This study evaluated the image quality and lesion visibility of deep learning-based image reconstruction (DLIR) compared with adaptive statistical iterative reconstruction-Veo (ASiR-V) in contrast-enhanced renal CT at different reconstruction strengths and doses. Methods: From January 2020 to May 2021, we prospectively included 101 patients who underwent renal contrast-enhanced CT scanning (69 at 120 kV; 32 at 80 kV). All image data were reconstructed with ASiR-V (30% and 70%) and DLIR at low, medium, and high reconstruction strengths (DLIR-L, DLIR-M, and DLIR-H, respectively). The CT number, noise, noise reduction rate (NRR), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), overall image quality, and the proportion of acceptable images were compared. Lesions of DLIR groups were evaluated, and the conspicuity-to-noise ratio (C/N) was calculated. Results: Quantitative values (noise, SNR, CNR, and NRR) significantly differed between all reconstructions at 120 and 80 kV (P<0.001) and between each reconstruction, except ASiR-V 70% vs. DLIR-M. At 120 kV, the overall image quality and the proportion of acceptable images significantly differed between all reconstructions (P<0.001) and between each reconstruction, except ASiR-V 30% vs. DLIR-L and ASiR-V 70% vs. DLIR-M. At 80 kV, the overall image quality significantly differed between all reconstructions (P<0.001) and between each reconstruction, except between ASiR-V 30%, ASiR-V 70%, and DLIR-L. Quantitative and qualitative values were highest in DLIR-H, while the values were close in DLIR-H (80 kV) vs. ASiR-V 70% (120 kV) and DLIR-M (80 kV) vs. ASiR-V 30% (120 kV). The lesion conspicuity and noise significantly differed in DLIR at 120 kV and 80 kV (P<0.001). C/N significantly differed in DLIR at 120 kV (P<0.001) but not at 80 kV. DLIR-L and DLIR-M exhibited much-improved lesion display (C/N >1), and DLIR-H exhibited much-improved noise (C/N <1) at 120 kV. Conclusions: DLIR significantly improved the image quality and lesion visibility of renal CT compared with ASiR-V, even at a low dose.

Associations between paraspinal muscles fatty infiltration and lumbar vertebral bone mineral density - An investigation by fast kVp switching dual-energy CT and QCT.

Purpose: To investigate the relationship between paraspinal muscles fat content and lumbar bone mineral density (BMD). Methods: A total of 119 participants were enrolled in our study (60 males, age: 50.88 ± 17.79 years, BMI: 22.80 ± 3.80 kg·m-2; 59 females, age: 49.41 ± 17.69 years, BMI: 22.22 ± 3.12 kg·m-2). Fat content of paraspinal muscles (erector spinae (ES), multifidus (MS), and psoas (PS)) were measured at (ES L1/2-L4/5; MS L2/3-L5/S1; PS L2/3-L5/S1) levels using dual-energy computed tomography (DECT). Quantitative computed tomography (QCT) was used to assess BMD of L1 and L2. Linear regression analysis was used to assess the relationship between BMD of the lumbar spine and paraspinal muscles fat content with age, sex, and BMI. The variance inflation factor (VIF) was used to detect the degree of multicollinearity among the variables. P < .05 was considered to indicate a statistically significant difference. Results: The paraspinal muscles fat content had a fairly significant inverse association with lumbar BMD after controlling for age, sex, and BMI (adjusted R 2 = 0.584-0.630, all P < .05). Conclusion: Paraspinal muscles fat content was negatively associated with BMD.Paraspinal muscles fatty infiltration may be considered as a potential marker to identify BMD loss.

Image quality improvement in low-dose chest CT with deep learning image reconstruction.

OBJECTIVES: To investigate the clinical utility of deep learning image reconstruction (DLIR) for improving image quality in low-dose chest CT in comparison with 40% adaptive statistical iterative reconstruction-Veo (ASiR-V40%) algorithm. METHODS: This retrospective study included 86 patients who underwent low-dose CT for lung cancer screening. Images were reconstructed with ASiR-V40% and DLIR at low (DLIR-L), medium (DLIR-M), and high (DLIR-H) levels. CT value and standard deviation of lung tissue, erector spinae muscles, aorta, and fat were measured and compared across the four reconstructions. Subjective image quality was evaluated by two blind readers from three aspects: image noise, artifact, and visualization of small structures. RESULTS: The effective dose was 1.03 ± 0.36 mSv. There was no significant difference in CT values of erector spinae muscles and aorta, whereas the maximum difference for lung tissue and fat was less than 5 HU among the four reconstructions. Compared with ASiR-V40%, the DLIR-L, DLIR-M, and DLIR-H reconstructions reduced the noise in aorta by 11.44%, 33.03%, and 56.1%, respectively, and had significantly higher subjective quality scores in image artifacts (all p < 0.001). ASiR-V40%, DLIR-L, and DLIR-M had equivalent score in visualizing small structures (all p > 0.05), whereas DLIR-H had slightly lower score. CONCLUSIONS: Compared with ASiR-V40%, DLIR significantly reduces image noise in low-dose chest CT. DLIR strength is important and should be adjusted for different diagnostic needs in clinical application.

Application of computer-aided detection (CAD) software to automatically detect nodules under SDCT and LDCT scans with different parameters.

PURPOSE: To explore the application of computer-aided detection (CAD) software on automatically detecting nodules under standard-dose CT (SDCT) and low-dose CT (LDCT) scans with different parameters including definition modes and blending levels of adaptive statistical iterative reconstruction (ASIR), whose influence was important to optimize radiology workflow serving for clinical work. MATERIALS AND METHODS: 117 patients underwent SDCT and LDCT scans. The comprehensive performance of CAD in detect pulmonary nodules including under different ASIR blending levels (0%, 60%, and 80%) and high-definition (HD) or non-HD modes were assessed. The true positive (TP) rate, false positive (FP) rate and the sensitivity were recorded. RESULTS: The stand-alone sensitivity of CAD system was 78.03% (515/660) in SDCT images and 70.15% (456/650) on LDCT images (p < 0.05). The sensitivity of CAD system to pulmonary nodules under non-HD mode was higher than that under HD mode. The detectability of nodules in images reconstructed with 60% and 80% ASIR was found significantly superior to that with 0% ASIR (p < 0.001). The overall sensitivity of CAD system on LDCT images reconstructed with 60% ASIR under HD mode was greater than that with 0% ASIR (p < 0.05), but lower than that with 80% ASIR. However, under non-HD mode, CAD demonstrated a comparable performance on LDCT images reconstructed with 60% ASIR to those reconstructed with 80% ASIR. CONCLUSION: Using the CAD system to detect pulmonary nodules on LDCT images with appropriate levels of ASIR could maintain high diagnostic sensitivity while reducing the radiation dose, which is useful to optimize the radiology workflow.

Impact of deep learning-based image reconstruction on image quality compared with adaptive statistical iterative reconstruction-Veo in renal and adrenal computed tomography.

OBJECTIVE: To evaluate image quality of deep learning-based image reconstruction (DLIR) in contrast-enhanced renal and adrenal computed tomography (CT) compared with adaptive statistical iterative reconstruction-Veo (ASiR-V). METHODS: We prospectively recruited 52 patients. All images were reconstructed with ASiR-V 30%, ASiR-V 70%, and DLIR at low, medium, and high reconstruction strengths. CT number, noise, noise reduction rate, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured and calculated within the region of interest (ROI) on subcutaneous fat, bilateral renal cortices, renal medulla, renal arteries, and adrenal glands. For qualitative analyses, the differentiation of the renal cortex and medulla, conspicuity of the adrenal gland boundary, sharpness, artifacts, and subjective noise were assessed. The overall image quality was calculated on a scale from 0 (worst) to 15 (best) based on the five values above and the score≥9 was acceptable. RESULTS: CT number does not significantly differ between the reconstruction datasets. Noise does not significantly differ between ASiR-V 30% and DLIR-L, but it is significantly lower using ASiR-V 70%, DLIR-M, and DLIR-H. The noise reduction rate relative to ASiR-V 30% is significantly different between the DLIR groups and ASiR-V 70%, and DLIR-H yields the highest noise reduction rate (61.6%). SNR and CNR are higher for DLIR-M, DLIR-H, and ASiR-V 70% than for ASiR-V 30% and DLIR-L. DLIR-H shows the best SNR and CNR. The overall image quality yields the same pattern for DLIR-H, with the highest score. Percentages of cases with overall image quality score≥9 are 100% (DLIR-H), 94.23% (DLIR-M), 90.38% (ASiR-V70%), 67.31% (DLIR-L), and 63.46% (ASiR-V30%), respectively. CONCLUSIONS: DLIR significantly improved the objective and subjective image quality of renal and adrenal CTs, yielding superior noise reduction compared with ASiR-V.

Deep learning versus iterative image reconstruction algorithm for head CT in trauma.

PURPOSE: To compare the image quality between a deep learning-based image reconstruction algorithm (DLIR) and an adaptive statistical iterative reconstruction algorithm (ASiR-V) in noncontrast trauma head CT. METHODS: Head CT scans from 94 consecutive trauma patients were included. Images were reconstructed with ASiR-V 50% and the DLIR strengths: low (DLIR-L), medium (DLIR-M), and high (DLIR-H). The image quality was assessed quantitatively and qualitatively and compared between the different reconstruction algorithms. Inter-reader agreement was assessed by weighted kappa. RESULTS: DLIR-M and DLIR-H demonstrated lower image noise (p < 0.001 for all pairwise comparisons), higher SNR of up to 82.9% (p < 0.001), and higher CNR of up to 53.3% (p < 0.001) compared to ASiR-V. DLIR-H outperformed other DLIR strengths (p ranging from < 0.001 to 0.016). DLIR-M outperformed DLIR-L (p < 0.001) and ASiR-V (p < 0.001). The distribution of reader scores for DLIR-M and DLIR-H shifted towards higher scores compared to DLIR-L and ASiR-V. There was a tendency towards higher scores with increasing DLIR strengths. There were fewer non-diagnostic CT series for DLIR-M and DLIR-H compared to ASiR-V and DLIR-L. No images were graded as non-diagnostic for DLIR-H regarding intracranial hemorrhage. The inter-reader agreement was fair-good between the second most and the less experienced reader, poor-moderate between the most and the less experienced reader, and poor-fair between the most and the second most experienced reader. CONCLUSION: The image quality of trauma head CT series reconstructed with DLIR outperformed those reconstructed with ASiR-V. In particular, DLIR-M and DLIR-H demonstrated significantly improved image quality and fewer non-diagnostic images. The improvement in qualitative image quality was greater for the second most and the less experienced readers compared to the most experienced reader.

Impact of Adaptive Statistical Iterative Reconstruction-V on Coronary Artery Calcium Scores Obtained From Low-Tube-Voltage Computed Tomography - A Patient Study.

OBJECTIVE: To evaluate the impact of adaptive statistical iterative reconstruction-V (ASIR-V) on the accuracy of ultra-low-dose coronary artery calcium (CAC) scoring. MATERIALS AND METHOD: One-hundred-and-three patients who underwent computed tomography (CT) for CAC scoring were prospectively included. All underwent standard scanning with 120-kilovolt-peak (kVp) and with 80- and 70-kVp tube voltage. ASiR-V was applied to the 80- and 70-kVp scans at different levels. The 120-kVp scans reconstructed with filtered back projection served as the standard of reference. Recently published novel kVp-adapted thresholds were used for calculation of CAC scores from 80- and 70-kVp scans and the resulting CAC scores were compared against the standard of reference. Patients were stratified into six CAC score risk categories: 0, 1-10, 11-100, 101-400, 401-1000, and >1000. RESULTS: Increasing levels of ASIR-V led to an increasing underestimation of CAC scores with bias ranging from -128 to -118 and from -205 to -198 for the 80- and 70-kVp scans, respectively, when compared with the standard of reference. Reconstruction with 20% and 40% ASIR-V for the 80- and 70-kVp scans, respectively, yielded noise levels comparable to the standard of reference. Nevertheless, a change in risk-class was observed in 29 (28.6%) and 46 (44.7%) patients, exclusively to a lower risk-class, when CAC scores were derived from these reconstructions. CONCLUSION: ASIR-V leads to noise reduction in CT scans acquired with low tube-voltages. However, ASIR-V introduces substantial inaccuracies and marked underestimation of ultra-low-dose CAC scoring as compared with standard-dose CAC scoring despite normalization of noise.

Deep learning reconstruction algorithm in improving portal vein CT image quality / 西安交通大学学报(医学版)

【Objective】 To explore the value of deep learning reconstruction algorithm (DLIR) in improving image quality of portal vein. 【Methods】 We retrospectively enrolled 32 patients who underwent double-phasic enhanced abdominal CT scanning. Images at the portal venous phase were reconstructed using the 50% adaptive statistical iterative reconstruction (ASIR-V), DLIR at medium (DLIR-M) and high strength (DLIR-H). The CT value and image noise (standard deviation) of the main portal vein, the right portal vein branch, the left portal vein branch, and the paravertebral muscle were measured, and the contrast-noise-ratio (CNR) for vessels were calculated. Moreover, the edge-rising-slope (ERS) of the main portal vein edge was measured to evaluate image spatial resolution. The overall image noise, image contrast, and portal vein branch display were evaluated using a 5-point grading scale and image artifacts using a 4-point grading scare by two experienced radiologists. In addition, we calculated the display rate of small branches of the portal vein in the three reconstruction algorithms. 【Results】 Image noise of the DLIR images in the main portal vein, right branch and left branch was significantly lower than that of ASIR-V 50% images, of which the DLIR-H images had the lowest noise and highest CNR. The ERS of the DLIR images in the main portal vein was significantly higher than that of the ASIR-V 50% images. For qualitative analyses, the DLIR images were significantly better than the ASIR-V 50% ones (P<0.01). In addition, the display rates of small branches of the portal vein in DLIR images were (DLIR-M: 93.75%; DLIR-H: 100%), significantly higher than that of ASIR-V 50% (68.75%). 【Conclusion】 Compared with ASIR-V 50% images, DLIR images can significantly reduce the image noise and improve the spatial resolution of the portal vein and the display rate of small branches of the portal vein.

Impact of novel deep learning image reconstruction algorithm on diagnosis of contrast-enhanced liver computed tomography imaging: Comparing to adaptive statistical iterative reconstruction algorithm.

OBJECTIVE: To assess clinical application of applying deep learning image reconstruction (DLIR) algorithm to contrast-enhanced portal venous phase liver computed tomography (CT) for improving image quality and lesions detection rate compared with using adaptive statistical iterative reconstruction (ASIR-V) algorithm under routine dose. METHODS: The raw data from 42 consecutive patients who underwent contrast-enhanced portal venous phase liver CT were reconstructed using three strength levels of DLIRs (low [DL-L]; medium [DL-M]; high [DL-H]) and two levels of ASIR-V (30%[AV-30]; 70%[AV-70]). Objective image parameters, including noise, signal-to-noise (SNR), and the contrast-to-noise ratio (CNR) relative to muscle, as well as subjective parameters, including noise, artifact, hepatic vein-clarity, index lesion-clarity, and overall scores were compared pairwise. For the lesions detection rate, the five reconstructions in patients who underwent subsequent contrast-enhanced magnetic resonance imaging (MRI) examinations were compared. RESULTS: For objective parameters, DL-H exhibited superior image quality of lower noise and higher SNR than AV-30 and AV-70 (all P < 0.05). CNR was not statistically different between AV-70, DL-M, and DL-H (all P > 0.05). In both objective and subjective parameters, only image noise was statistically reduced as the strength of DLIR increased compared with ASIR-V (all P < 0.05). Regarding the lesions detection rate, a total of 45 lesions were detected by MRI examination and all five reconstructions exhibited similar lesion-detection rate (25/45, 55.6%). CONCLUSION: Compared with AV-30 and AV 70, DLIR leads to better image quality with equal lesion detection rate for liver CT imaging under routine dose.

Imaging pediatric acute head trauma using 100-kVp low dose CT with adaptive statistical iterative reconstruction (ASIR-V) in single rotation on a 16 cm wide-detector CT.

OBJECTIVE: To demonstrate the ability of achieving low dose and high-quality head CT images for children with acute head trauma using 100 kVp and adaptive statistical iterative reconstruction (ASIR-V) algorithm in single rotation on a 16 cm wide-detector system. MATERIALS AND METHODS: We retrospectively analyzed the CT dose index (CTDI) and image quality of 104 children aged 0-6 years with acute head trauma (1 hour -3 days) in two groups: Group 1(n = 50) on a 256-row CT with single rotation at a reduced-dose of 100 kVp/240 mA and reconstructed using ASIR-V at 70%level; Group 2(n = 54) on a 64-row CT with multiple rotations at a standard dose of 120 kVp/ 180mA and reconstructed using a conventional filtered back-projection (FBP). Both groups used the 0.5 s/r axial scan mode. CT dose index (CTDI) and quantitative image quality measurements were compared using the Student t test; qualitative image quality comparison was carried out using Mann-Whitney rank test and the inter-reviewer agreement was evaluated using Kappa test. RESULTS: The exposure time was 0.5 s for Group 1 and 3.27±0.29 s for Group 2. The CTDI in Group 1 was 9.74±0.86mGy, 36.38%lower than the 15.31mGy in Group 2 (p < 0.001). Group 1 and Group 2 had similar artifact index (2.06±1.06 vs. 2.37±1.18) in the cerebellar hemispheres, and similar contrast-to-noise ratio (2.32±0.83 vs. 1.69±0.68), (1.47±0.72 vs. 1.10±0.43) respectively for cerebellum and thalamus (p > 0.05). Image quality was acceptable for diagnosis, and motion artifacts were reduced in Group 1 (p < 0.001). CONCLUSION: Single rotation CT with 100 kVp and 70%ASIR-V on 16 cm wide-detector CT reduces radiation dose and motion artifacts for children with acute head trauma without compromising diagnostic quality as compared with standard dose protocol. Thus, it provides a novel imaging method in management of pediatric acute head trauma.

Adaptive statistical iterative reconstruction for computed tomography of the spine.

INTRODUCTION: The utility of evaluating a sagittal view of CT of the spine is well-known. In many clinical cases, the sagittal view includes noise generated from surrounding objects and may degrade the image quality. Iterative reconstruction (IR) techniques are useful for noise reduction; however, they can reduce spatial resolution. The aim of this study was to evaluate the effectiveness of the adaptive statistical iterative reconstruction (ASiR) for generating sagittal CT images of the spine when compared to filtered back projection (FBP). METHODS: The image quality of clinical images from 25 patients were subjectively assessed. Three radiologists rated spatial resolution, image noise, and overall image quality using a five-point scale. For objective assessment, z-direction modulation transfer function (z-MTF) was measured using a custom-made phantom. Additionally, z-axis noise power spectrum (z-NPS) was measured using a water phantom. An improved adaptive statistical iterative reconstruction algorithm called ASiR-V was used in this study. Blending levels were 50%, and 100% (ASiR-V50, ASiR-V100, respectively). RESULTS: For subjective assessments, images using ASiR-V100 were determined to have the best overall image quality, despite having received the worst score in the assessment of spatial resolution. For objective assessments, the image using ASiR-V50 and ASiR-V100 curves were slightly degraded in terms of low contrast z-MTF when compared to FBP. CONCLUSION: ASiR-V was effective to improve the image quality when compared with FBP when reviewing sagittal reformats of the spine. IMPLICATIONS FOR PRACTICE: This study suggests that high resolution is not the only thing that is key when reviewing sagittal CT spinal reformats. Such images should be provided as part of routine CT spine protocols, where available.

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

BACKGROUND: Adaptive statistical iterative reconstruction-V technique (ASIR-V) is usually set at different strengths according to the different clinical requirements and scenarios encountered when setting scanning protocols, such as setting a more aggressive tube current reduction (defined as preset ASIR-V). Reconstruction with ASIR-V is useful after scanning using image algorithms to improve image quality (defined as postset ASIR-V). The aim of this study was to investigate the quality of images reconstructed with preset and postset ASIR-V, using the same noncontrast abdominal-pelvic computed tomography (CT) protocols in the same individual on a wide detector CT. METHODS: We prospectively enrolled 141 patients. The scan protocols in Groups A-E were 0%, 20%, 40%, 60%, and 80% preset ASIR-V, respectively, in the 256 wide-detector row Revolution CT (GE Healthcare, Waukesha, WI, USA). Each group was further divided into 5 subgroups with 0%, 20%, 40%, 60%, and 80% postset ASIR-V, respectively. The 64-detector Discovery 750 HDCT (GE, USA) was used for Group F as a control group, using 0%, 20%, 40%, 60%, and 80% ASIR, respectively. Image noise was measured in the spleen, aorta, and muscle. The CT attenuation and image noise were analyzed using the paired t-test; analysis of variance and post hoc multiple comparisons were made using the Student-Newman-Keuls (SNK) method. RESULTS: The CT attenuation in Groups A-F exhibited no significant difference between subgroups in three organs (P>0.05). Only with increasing preset ASIR-V% (Groups A to E), did the image noise decrease, except in Group B in the aorta and muscle (NoiseB > NoiseA, PmuscleA&B=0.233, PaortaA&B=0.796). Only with increasing postset ASIR-V or ASIR% (Groups A and F), did the image noise decrease in the three organs. After preset and postset ASIR-V were combined, with preset ASIR-V% being equal to postset ASIR-V%, the image become similar to the corresponding preset ASIR-V part with the line of postset ASIR-V 0% (baseline of each group). When preset ASIR-V% was greater than the postset ASIR-V%, the image noise was higher than the baseline of each group. When preset ASIR-V% was less than the postset ASIR-V%, the image noise was lower than the baseline of each group. The radiation dose from B to E decreased from 11.2% to 57.1%. The CT dose index volume (CTDIvol) and dose length product (DLP) in Group F were significantly higher than those in Group A. CONCLUSIONS: Using both preset and postset ASIR-V allows dose reduction, with a potential to improve image quality only when postset ASIR-V% is higher than or equal to preset ASIR-V%. The image quality depends on postset ASIR-V%, whereas the decrease of radiation dose depends on preset ASIR-V%.

Influence of deep learning image reconstruction and adaptive statistical iterative reconstruction-V on coronary artery calcium quantification.

BACKGROUND: Deep learning image reconstruction (DLIR) and adaptive statistical iterative reconstruction-V (ASIR-V) has been used for cardiac computed tomography imaging. However, DLIR and ASIR-V may influence the quantification of coronary artery calcification (CAC). METHODS: CT images of 96 patients were reconstructed using filtered back projection (FBP), ASIR-V 50%, and three levels of DLIR [low (L), medium (M), and high (H)]. Image noise and the Agatston, volume, and mass scores were compared between the reconstructions. Patients were stratified into six Agatston score-based risk categories and five CAC percentile risk categories adjusted by Agatston score, age, sex, and race. The number of patients who were switched to another risk stratification group when ASIR-V and DLIR were used was compared. Bland-Altman plots were used to present the agreement of Agatston scores between FBP and the different reconstruction techniques. RESULTS: Compared to that with FBP, image noise was significantly decreased with ASIR-V 50%, and DLIR-L, -M, and -H (all P<0.001). The Agatston, volume, and mass scores with ASIR-V 50% and DLIR-L, -M, and -H showed significant decreases in comparison to those calculated with FBP (all P<0.001). Severity classification showed no significant differences between the five reconstruction techniques in any of the CAC score-based risk categories (all P>0.05). CONCLUSIONS: DLIR and ASIR-V show great potential for improving CT image quality, and appear to have no pronounced impact on CAC quantification or Agatston score-based risk stratification.

A phantom study using dual-energy spectral computed tomography imaging: Comparison of image quality between two adaptive statistical iterative reconstruction (ASiR, ASiR-V) algorithms for evaluating ground-glass nodules of the lung.

Aims: To assess the image quality of the two adaptive statistical iterative reconstruction (ASiR and ASiR-V) algorithms for evaluating ground-glass nodules (GGNs) of the lung. Subjects and Methods: The chest phantom with ground-glass simulated pulmonary nodules was scanned by dual-energy spectral computed tomography (CT) using gemstone spectral imaging mode. The image was reconstructed with ASiR and ASiR-V from 0 (FBP) to 90% blending percentages, respectively. The average noise and signal-to-noise ratio (SNR) of reconstruction images were calculated. The data were statistically analyzed. Results: Compared with FBP, as the percentage of ASiR and ASiR-V increased from 10 to 90%, image noise reduced by 3.7%-45.2% and 14.1%-73.8%, respectively, and the SNR increased accordingly. There was significantly higher SNR value of ASiR-V images as the percentages of IR increased to 50% or greater, compared to those of ASiR. Subjective image quality scores of ASiR and ASiR-V improved significantly as percentage increased from 10 to 80% for ASiR and ASiR-V (peaked at 60% for both of them). Conclusions: Both ASiR and ASiR-V can reduce the image noise and improve the objective image quality for presenting pulmonary nodules on dual-energy spectral CT imaging compared with FBP. ASiR-V provided further image quality improvement than ASiR, and both ASiR and ASiR-V 60% had the highest image quality score.

Deep learning-based image reconstruction for brain CT: improved image quality compared with adaptive statistical iterative reconstruction-Veo (ASIR-V).

PURPOSE: To compare the image quality of brain computed tomography (CT) images reconstructed with deep learning-based image reconstruction (DLIR) and adaptive statistical iterative reconstruction-Veo (ASIR-V). METHODS: Sixty-two patients underwent routine noncontrast brain CT scans and datasets were reconstructed with 30% ASIR-V and DLIR with three selectable reconstruction strength levels (low, medium, high). Objective parameters including CT attenuation, noise, noise reduction rate, artifact index of the posterior cranial fossa, and contrast-to-noise ratio (CNR) were measured at the levels of the centrum semiovale and basal ganglia. Subjective parameters including gray matter-white matter differentiation, sharpness, and overall diagnostic quality were also assessed and compared with the interobserver agreement. RESULTS: There was a gradual reduction in the image noise and artifact index of the posterior cranial fossa as the strength levels of DLIR increased (all P < 0.001) compared with that of ASIR-V. CNR in both the centrum semiovale and basal ganglia levels also improved from the low to high strength levels of DLIR compared with that of ASIR-V (all P < 0.001). DLIR images with medium and high strength levels demonstrated the best subjective image quality scores among the reconstruction datasets. There was moderate to good interobserver agreement for the subjective image quality assessments with ASIR-V and DLIR. CONCLUSION: On routine brain CT scans, optimized protocols with DLIR allowed significant reduction of noise and artifacts with improved subjective image quality compared with ASIR-V.

Validation of deep-learning image reconstruction for coronary computed tomography angiography: Impact on noise, image quality and diagnostic accuracy.

BACKGROUND: Advances in image reconstruction are necessary to decrease radiation exposure from coronary CT angiography (CCTA) further, but iterative reconstruction has been shown to degrade image quality at high levels. Deep-learning image reconstruction (DLIR) offers unique opportunities to overcome these limitations. The present study compared the impact of DLIR and adaptive statistical iterative reconstruction-Veo (ASiR-V) on quantitative and qualitative image parameters and the diagnostic accuracy of CCTA using invasive coronary angiography (ICA) as the standard of reference. METHODS: This retrospective study includes 43 patients who underwent clinically indicated CCTA and ICA. Datasets were reconstructed with ASiR-V 70% (using standard [SD] and high-definition [HD] kernels) and with DLIR at different levels (i.e., medium [M] and high [H]). Image noise, image quality, and coronary luminal narrowing were evaluated by three blinded readers. Diagnostic accuracy was compared against ICA. RESULTS: Noise did not significantly differ between ASiR-V SD and DLIR-M (37 vs. 37 HU, p = 1.000), but was significantly lower in DLIR-H (30 HU, p < 0.001) and higher in ASiR-V HD (53 HU, p < 0.001). Image quality was higher for DLIR-M and DLIR-H (3.4-3.8 and 4.2-4.6) compared to ASiR-V SD and HD (2.1-2.7 and 1.8-2.2; p < 0.001), with DLIR-H yielding the highest image quality. Consistently across readers, no significant differences in sensitivity (88% vs. 92%; p = 0.453), specificity (73% vs. 73%; p = 0.583) and diagnostic accuracy (80% vs. 82%; p = 0.366) were found between ASiR-V HD and DLIR-H. CONCLUSION: DLIR significantly reduces noise in CCTA compared to ASiR-V, while yielding superior image quality at equal diagnostic accuracy.

Dose and blending fraction quantification for adaptive statistical iterative reconstruction based on low-contrast detectability in abdomen CT.

PURPOSE: The utilization of iterative reconstruction makes it difficult to identify the dose-noise relationship, resulting in empirical design of scan protocols and inconsistent conclusions on dose reduction for consistent image quality. This study was to quantitatively determine the dose and the blending fraction of adaptive statistical iterative reconstruction (ASIR) based on the specified low-contrast detectability (LCD). METHODS: A tissue equivalent abdomen phantom and a GE discovery 750 HD computed tomography (CT) were utilized. The normality of the noise distribution was tested at various spatial scales (2.1-9.8 mm) in the presence of ASIR (10-100%) with a wide range of doses (2.24-38 mGy). The statically defined minimum detectable contrast (MDC) was used as the image quality metric. The parametric model decomposed the MDC into two terms: one with and the other without ASIR, each was related to the dose in the form of power law with factors and indices dependent on spatial scales. The parameters were identified by least-square fitting to the experimental data. By considering the constraint of the blending fraction in the range of [0, 1], the dose and ASIR blending fraction were determined for any specified low-contrast detectability (LCD), quantified by the MDC at the concerned lesion size. RESULTS: It was verified that noise distribution is normal in the presence of ASIR. It was also found that the noises obtained from the subtractions of adjacent slices had an underestimate of 20% as compared to the ground truth noises, regardless of the spatial scale, pitch, or ASIR blending fraction. The least-square fitting for the parametric model resulted in correlation coefficients from 0.905 to 0.996. The root-mean-square errors ranged from 1.27% to 7.15%. CONCLUSION: The parametric model can be used to form a look-up-table for dose and ASIR blending fraction. The dose choices may be substantially limited in some cases depending on the required LCD.

[Artificial intelligence evaluation of simulated phantom lung nodules with different pre-adaptive iteration techniques].

Objective: To investigate the detection rate of pulmonary nodules and the accuracy of automated measurement in chest simulation phantom by artificial intelligent computer-aided detection of pulmonary nodules with different pre-adaptive iterative techniques (ASIR-V) in wide-spectrum CT scanning. Methods: Sixteen pulmonary nodules with different diameters, densities and shapes were placed in the chest simulation phantom from December 2017 to March 2018. The weight of ASIR-V was set at 0%, 20%, 30%, 40% and 50% respectively by using Revolution CT broadband energy spectrum scanning protocol. Spearman correlation analysis was used to analyze the dose volume CT dose index (CTDIvol) and dose length product (DLP) of each group. Scanning data were imported into Tuma Shenwei artificial pulmonary nodule analysis software to evaluate the nature of the detected nodules, and ICC was used to detect the differences among groups. Results: With the increase of ASIR-V weight, the effective dose of patients decreased gradually. CTDIvol of five groups of radiation dose volume CT dose index was 7.93, 7.24, 5.85, 5.15, 3.76 mGy,dose-length product DLP was 379, 346, 280, 246, 179 mGy·cm.There was a linear negative correlation between ASIR-V weights and CTDIvol as well as DLP, r value was-0.969, P<0.01.There was no significant difference in the detection rate of pulmonary nodules between AI and physicians (P>0.05). There was high intraclass correlation coefficients for the diameter, volume, CT value and malignant percentage of pulmonary nodules (ICCs:0.981-1.000). Conclusions: Radiation dose of unenhanced chest CT scan using wide detector spectral imaging decreased with the increasing of preset ASIR-V. Lung nodule detection rate and evaluation performance can be maintained well by using ASIR-V reconstructions at lower radiation dosage.