Impact of deep learning image reconstructions (DLIR) on coronary artery calcium quantification

We evaluated the influence of sinogram-affirmed iterative reconstruction (SAFIRE) on the coronary artery calcium (CAC) score by computed tomography (CT). Seventy patients underwent CAC imaging by 128-slice dual-source CT. CAC volume, mass and Agatston score were calculated from images reconstructed by filtered back projection (FBP) without and with incremental degrees of the SAFIRE algorithm (10-50 %). We used the repeated measuring test and the Steel-Dwass test for multiple comparisons of values and the difference ratio among different SAFIRE groups using the FBP as reference. The median Agatston score (range) decreased with incremental SAFIRE degrees: 163 (0.1 - 3,393.3), 158.4 (0.3 - 3,079.3), 137.7 (0.1 - 2,978.0), 120.6 (0 - 2,783.6), 102.6 (0 - 2,468.4) and 84.1 (0 - 2,186.9) for 0 % (FBP), 10 %, 20 %, 30 %, 40 % and 50 % SAFIRE, respectively (P < 0.05). In comparison with FBP, CAC volume (from 8.1 % to 47.7 %), CAC mass (from 5.3 % to 44.7 %) and CAC Agatston score (from 7.3 % to 48.4 %) all decreased with increasing SAFIRE from 10 % to 50 %, respectively (P < 0.05). High-grade SAFIRE resulted in the disappearance of detectable calcium in three cases with low calcium burden. SAFIRE noise reduction techniques significantly affected the CAC, which potentially alters perceived cardiovascular risk.

Background and Aims Cardiovascular calcification is highly prevalent among patients with end-stage renal disease (ESRD). Low normal serum magnesium has been linked to a more severe degree of vascular calcification and a decrease in patient survival. An inhibitory effect of extracellular magnesium on osteogenic transformation of vascular smooth muscle cells and the upregulation of anti-calcification protein have been confirmed in vitro. Increased dialysate magnesium concentration has also been shown to lower calcification propensity of the serum of maintenance hemodialysis (HD) patients. Method This study is an investigator initiated, single-blinded, parallel-group, matched case-control clinical trial that investigated the effect of high dialysate magnesium concentration for 24 weeks on the progression of coronary artery calcification (CAC) in maintenance HD patients. The changes in laboratory data and bone mineral density (BMD) were also examined. Seventy-six ESRD patients underwent CAC screening by multi-slice computed tomography and BMD measurement by dual-x-ray absorptiometry. Only patients with Agatston score&amp;gt;300 were included. They were matched according to the initial CAC score that fell within 20% of one another. Twenty patients were assigned to high dialysate magnesium concentration of 1.75 mEq/L and the matched controls were kept on standard dialysate magnesium concentration of 0.7 mEq/L. CAC and BMD measurements were repeated after 24 weeks. Laboratory data were obtained prior to dialysis at study entry, 8-week intervals during the study and 2 weeks after the study ended. Results There were no significant differences in age, sex, BMI, underlying diseases, dialysis vintage, medications, baseline CAC scores and BMD. The median baseline CAC Agatston score (Volume score) were 1923 (720) and 1672 (785) in the standard and high dialysate groups, respectively. At the end of the study, a significant increase in the CAC score was observed in both groups. Because majority of the included patients had severe calcification burden at baseline, patients were categorized into 2 subgroups using the median baseline CAC Agatston (1600) and Volume scores (700) as cut-offs. Among patients with CAC Agatston score &amp;lt;=1600, CAC score increased significantly in the standard dialysate magnesium group (P&amp;lt;0.01) but was stable in the high dialysate magnesium group (P=0.33). Among patients with CAC Agatston score &amp;gt;1600, the severity of CAC worsened in both groups. The progression of CAC was analyzed by the difference between the follow-up and the baseline square root transformed Agatston and Volume scores. In subgroup of patients with less severe calcification, more patients in the standard dialysate magnesium group progressed compared to the high dialysate magnesium group (P=0.03). In subgroup of patients with more severe calcification, the number of progressors were comparable among the 2 groups. Serum and ionized magnesium levels increased substantially during the study and returned to baseline after the return to standard dialysate magnesium concentration. The highest predialysis serum magnesium was 3.8 mg/dL. Most patients who received high dialysate magnesium reported the disappearance of symptoms of muscle cramps (P=0.01) and requested the high dialysate magnesium be continued after the end of the study. There were no significant changes in serum calcium, phosphate or PTH levels. The decline in BMD was observed in both groups but the difference did not reach statistical significance. Conclusion High dialysate magnesium was well tolerated and could ameliorate the progression of CAC in maintenance HD patients with mild to moderate vascular calcification.

The purpose of this study was to examine the individual and joint associations of obesity and cardiorespiratory fitness (CRF) with indices of coronary artery calcification (CAC) in 2090 middle-aged men. Obesity was defined as a body mass index (BMI) ≥25 kg/m2 and a waist circumference (WC) ≥90 cm. Cardiorespiratory fitness was operationally defined as peak oxygen uptake (V˙o2peak) directly measured using gas analysis. Participants were then divided into unfit and fit categories based on age-specific V˙o2peak percentiles. Agatston scores >100 and volume and density scores >75th percentile were defined as indices of CAC, signifying advanced subclinical atherosclerosis. Obese men had increased CAC Agatston, volume, and density scores, while higher CRF was associated with lower Agatston and volume scores after adjusting for potential confounders. In the joint analysis, unfit-obese men had higher CAC Agatston and CAC volume. The fit-obesity category was not associated with CAC Agatston (OR = 0.91: 95% CI, 0.66-1.25, for BMI and OR = 1.21: 95% CI, 0.86-1.70, for WC) and CAC volume (OR = 1.14: 95% CI, 0.85-1.53, for BMI and OR = 1.23: 95% CI, 0.90-1.69, for WC), which were similar to estimates for the fit-normal weight category. These findings demonstrate that while obesity is positively associated with the prevalence of moderate to severe CAC scores, CRF is inversely associated with the prevalence of moderate to severe CAC scores. Additionally, the combination of being fit and obese was not associated with CAC scores, which could potentially reinforce the fat-but-fit paradigm.

Background and Aims In the CaLIPSO study, SNF472 significantly attenuated progression of coronary artery calcium (CAC) volume score compared with placebo. This pre-specified analysis examined the effect of SNF472 on CAC progression in key subgroups of patients in CaLIPSO. Method Patients with a CAC Agatston score of 100 to 3500 at baseline were randomized to SNF472 300 mg (n=92), SNF472 600 mg (n=91), or placebo (n=91), infused during hemodialysis (HD) thrice weekly for 52 weeks. Patients received standard of care therapy, including phosphate binders and calcimimetics as determined by investigator. The primary endpoint (change in log CAC volume score from baseline to week 52 in the combined dose groups vs placebo) was analyzed for patients who received SNF472 or placebo and had an evaluable CT scan post-randomization (modified ITT population). Sensitivity analysis was also performed for the per protocol population of patients that met entry criteria, received 80% of scheduled treatment, completed the study procedures, and had both a baseline and week 52 evaluable CT scan. The analysis plan pre-specified key subgroups: age, sex, diabetes, dialysis vintage, and arteriosclerotic cardiovascular disease (ASCVD), as well as baseline use of non-calcium phosphate binders, calcium-based phosphate binders, calcimimetics, activated vitamin D, warfarin, or statins. Results Demographics and disease characteristics were similar across the treatment groups. Age (mean±SD) at baseline was 63.6±8.9 years and 39% of the patients were female; 62% had diabetes and 41% had prior ASCVD. Median dialysis vintage was 42.4 months; 33% had received hemodialysis for ≥5 years. Concomitant medications at baseline were: non-calcium phosphate binders, 62%; calcium-based phosphate binders, 28%; calcimimetics, 31%; activated vitamin D, 51%; warfarin, 8%; and statins, 64%. CAC volume progression was 11% for the combined dose groups and 20% for placebo (p=0.016). Treatment differences for CAC volume score progression from baseline to week 52 were similar across the subgroups (FIGURE). All interaction p-values were non-significant, and comparisons favored SNF472 vs placebo in each subgroup for both the modified ITT and per protocol population. Conclusion SNF472 treatment for 52 weeks attenuated CAC progression compared with placebo in all subgroups of the CaLIPSO study. These results support the potential benefit of SNF472 across a broad population of patients with cardiovascular calcification. Future studies are needed to determine the effects of SNF472 on cardiovascular events in patients receiving HD.

Aim: To investigate if estimation of the amount of calcium in the coronary system utilizing a visual coronary artery calcium scoring (CACS) system (Kirsch et al. Detection of coronary calcium during standard chest computed tomography correlates with multi-detector computed tomography coronary artery calcium score) in non - electrocardiogram (ECG) gated chest computed tomography (CT) scans maintains its strong correlation with the Agatston CACS on dedicated ECG gated cardiac CT exams across two or more points in time per patient. Methods: A visual scoring system (Weston score, WCS) was previously developed assigning a score (0-3, total score 0-12) for each coronary vessel including the left main trunk. Predetermined score cutoffs in both Agatston and Weston scoring methods were designated for risk stratification. Following institutional review board approval, we retrospectively analyzed 127 total body CT scans on 53 low-risk patients referred by executive health who had received repeat CT scans between 2007 and 2018 and compared the traditional Agatston CACS with the Weston score. Analysis: The data were gathered from a total of 53 executive health patients ages 33 to 71, with an average age of 51. 83.6% were male and 16.4% were female. 118 scans were examined, taken between 307 and 2,792 days apart, with an average of 937 days between scans. The Weston and Agatston scores predicted the same risk classification for 79.7% of the first set of scans, with 10.2% uprisked and 10.2% downrisked by their Weston scores. For the second set of scans, 78.0% had the same classification, with 10.2% uprisked and 11.9% downrisked by their Weston scores. Weston scores predicted 100% of scans within one risk classification of the corresponding Agatston score across all pairs of scans.The average CACS utilizing the Agatston scoring method was 54.3, with a standard deviation of 148.6 due to a large positive skew in the data. The corresponding Weston scores had an average of 1.1, with a standard deviation of 2.14. Conclusion: A visual CACS system (WCS) performed on non-gated CT scans allows risk stratification for cardiac events in a similar manner as the Agatston CACS on ECG-gated CT scans even at separate points in time.

Association of aortic root calcification severity with the extent of coronary artery calcification assessed by calcium-scoring dual-source computed tomography

Coronary artery calcium (CAC) scoring with computed tomography (CT) is an established tool for quantifying calcified atherosclerotic plaque burden. Despite the widespread use of novel image reconstruction techniques in CT, the effect of iterative model reconstruction on CAC score remains unclear. We sought to assess the impact of iterative model based reconstruction (IMR) on coronary artery calcium quantification as compared to the standard filtered back projection (FBP) algorithm and hybrid iterative reconstruction (HIR). In addition, we aimed to simulate the impact of iterative reconstruction techniques on calcium scoring based risk stratification of a larger asymptomatic population. We studied 63 individuals who underwent CAC scoring. Images were reconstructed with FBP, HIR and IMR and CAC scores were measured. We estimated the cardiovascular risk reclassification rate of IMR versus HIR and FBP in a larger asymptomatic population (n = 504). The median CAC scores were 147.7 (IQR 9.6-582.9), 107.0 (IQR 5.9-526.6) and 115.1 (IQR 9.3-508.3) for FBP, HIR and IMR, respectively. The HIR and IMR resulted in lower CAC scores as compared to FBP (both p < 0.001), however there was no difference between HIR and IMR (p = 0.855). The CAC score decreased by 7.2 % in HIR and 7.3 % in IMR as compared to FBP, resulting in a risk reclassification rate of 2.4 % for both HIR and IMR. The utilization of IMR for CAC scoring reduces the measured calcium quantity. However, the CAC score based risk stratification demonstrated modest reclassification in IMR and HIR versus FBP.

Patterns of prescription opioid misuse among young people who inject drugs

Association between HIV status and mental health disorders among newly diagnosed tuberculosis patients in Botswana

Correction Factors for CT Coronary Artery Calcium Scoring Using Advanced Modeled Iterative Reconstruction Instead of Filtered Back Projection

Coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular disease (CVD) that can be quantified in CT scans showing the heart. CAC lesions are defined as lesions in the coronary arteries with image intensity above 130 HU. The use of a threshold may lead to under- or over-estimation of the amount of CAC and, hence, to incorrect cardiovascular categorization of patients. This is especially pronounced in CT scans without ECG-synchronization where lesions are more subject to cardiac motion and partial volume effects. To address this, we propose a method for quantification of CAC without a threshold. A set of 373 cardiac and 1181 chest CT scans was included to develop the method and a set of 21 scan-rescan pairs (42 scans) was included for final evaluation. Assuming that the attenuation of CAC is superimposed on the attenuation of the artery, we aimed to separate the CAC from the coronary arteries by employing a CycleGAN to generate a synthetic image without CAC from an image containing CAC and vice versa. By subtracting the synthetic image without CAC from the image with CAC, a CAC map is created. The CAC-map can subsequently be used to identify and quantify CAC. The ground truth, i.e. the true amount of CAC, can not be established, therefore, in this work the results generated by the method are compared with clinical calcium scoring in terms of reproducibility. The average relative difference between the calcium scores in scan-rescan pairs of scans was 50% with the proposed method and 86% for the conventional method. Moreover, the correlation between CAC pseudo masses in scan-rescan pairs was 0.92 with the proposed method and 0.89 with conventional calcium scoring. Our proposed method is able to identify and quantify CAC lesions in CT scans without using an intensity level thresholding. This might allow for more reproducible quantification of CAC in CT scans made without ECG synchronization, and, therefore, it might allow more accurate CVD risk prediction.

Computed tomography perfusion (CTP) and computed tomography angiography (CTA) are valuable tools for diagnosing acute ischemic stroke (AIS). It is essential to obtain high-quality CTP and CTA images in short time. This study aimed to evaluate the image quality and diagnostic performance of brain CTP and CTA images generated from CTP reconstructed by a deep learning image reconstruction (DLIR) algorithm on patients with AIS. The study prospectively enrolled 54 patients with suspected AIS undergoing non-contrast CT and CTP within 24 hours. CTP datasets were reconstructed with three levels of adaptive statistical iterative reconstruction-Veo algorithm [ASIR-V 0% with filtered back projection (FBP), ASIR-V 40%, and ASIR-V 80%] and three levels of DLIR, including low (DLIR-L), medium (DLIR-M), and high (DLIR-H). CTA images were generated using the CTP datasets at the peak arterial phase. Objective parameters including signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and noise reduction rate. Subjective evaluation was assessed according to Abels scoring system. Perfusion parameters and detection accuracy for infarction core lesions were evaluated. The objective and subjective image quality of CTA images were also evaluated. All reconstructions produced similar CT values (P>0.05). With the increase of ASIR-V and DLIR reconstruction strength, image noise decreased, while SNR and CNR increased for CTP images, especially in white matter. DLIR-H, DLIR-M, and ASIR-V80% yielded higher subjective scores than did ASIR-V40% and FBP. DLIR-H provided the highest noise reduction rate and detection accuracy. No significant difference was found in conventional parameters, the volume of infarct core, or ischemic penumbra among the 6 groups (P>0.05). The objective evaluation of reconstructed CTA images was comparable in DLIR-H, DLIR-M, and ASIR-V80% (P>0.05). The subjective scores of the DLIR-H and DLIR-M images were higher than those of the other groups, especially ASIR-V40% and FBP (P<0.05). Compared with FBP and ASIR-V40%, DLIR-H, DLIR-M, and ASIR-V80% improved the overall image quality of CTP and CTA images to varying degrees. Furthermore, DLIR-H and DLIR-M showed the best performance. DLIR-H is the best choice in diagnosing AIS with improved detection accuracy for cerebral infarction. Reconstructing CTA images using CTP datasets could reduce contrast agent and radiation dose.

Deep learning imaging reconstruction of reduced-dose 40 keV virtual monoenergetic imaging for early detection of colorectal cancer liver metastases

Computed tomography angiography (CTA) provides significant information on image quality in vascular imaging, thus offering high-resolution images despite having the disadvantages of increased radiation doses and contrast agent-related side effects. The deep-learning image reconstruction strategies were used to quantitatively evaluate the enhanced contrast-to-noise ratio (CNR) and the dose reduction effect of subtracted images. This study aimed to elucidate a comprehensive understanding of the quantitative image quality features of the conventional filtered back projection (FBP) and the advanced intelligent clear-IQ engine (AiCE), a deep learning reconstruction technique. The comparison was made in subtracted images with variable concentrations of contrast agents at variable tube currents and voltages, enhancing our knowledge of these two techniques. Data were obtained using a state-of-the-art 320-detector CT scanner. Image reconstruction was performed using FBP and AiCE with various intensities. The image quality evaluation was based on eight iodine concentrations in the phantom setup. The efficiency of AiCE relative to FBP was assessed by computing parameters including the root mean square error (RMSE), dose-dependent CNR, and potential dose reduction. The results showed that elevated concentrations of iodine and increased tube currents improved AiCE performance regarding CNR enhancement compared to FBP. AiCE also demonstrated a potential dose reduction ranging from 13.7 to 81.9% compared to FBP, suggesting a significant reduction in radiation exposure while maintaining image quality. The employment of deep learning image reconstruction with AiCE presented a significant improvement in CNR and potential dose reduction in CT angiography. This study highlights the potential of AiCE to improve vascular image quality and decrease radiation exposure risk, thereby improving diagnostic precision and patient care in vascular imaging practices.

The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular events. Non-contrast enhanced cardiac CT is considered a reference for quantification of CAC. Recently, it has been shown that CAC may be quantified in cardiac CT angiography (CCTA). We present a pattern recognition method that automatically identifies and quantifies CAC in CCTA. The study included CCTA scans of 50 patients equally distributed over five cardiovascular risk categories. CAC in CCTA was identified in two stages. In the first stage, potential CAC voxels were identified using a convolutional neural network (CNN). In the second stage, candidate CAC lesions were extracted based on the CNN output for analyzed voxels and thereafter described with a set of features and classified using a Random Forest. Ten-fold stratified cross-validation experiments were performed. CAC volume was quantified per patient and compared with manual reference annotations in the CCTA scan. Bland-Altman bias and limits of agreement between reference and automatic annotations were -15 (-198–168) after the first stage and -3 (-86 – 79) after the second stage. The results show that CAC can be automatically identified and quantified in CCTA using the proposed method. This might obviate the need for a dedicated non-contrast-enhanced CT scan for CAC scoring, which is regularly acquired prior to a CCTA scan, and thus reduce the CT radiation dose received by patients.