scholarly journals Deep learning for automated exclusion of cardiac CT examinations negative for coronary artery calcium

2020 ◽  
Vol 129 ◽  
pp. 109114
Author(s):  
Leonardus B. van den Oever ◽  
Ludo Cornelissen ◽  
Marleen Vonder ◽  
Congying Xia ◽  
Jurjen N. van Bolhuis ◽  
...  
2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
E Arbas Redondo ◽  
D Tebar Marquez ◽  
I.D Poveda Pinedo ◽  
R Dalmau Gonzalez-Gallarza ◽  
S.C Valbuena Lopez ◽  
...  

Abstract Introduction Cardiac computed tomography (CT) use has progressively increased as the preferred initial test to rule out coronary artery disease (CAD) when clinical likelihood is low. Coronary artery calcium (CAC) detected by CT is a well-established marker for cardiovascular risk. However, it is not recommended for diagnosis of obstructive CAD. Absence of CAC, defined as an Agatston score of zero, has been associated to good prognosis despite underestimation of non-calcified plaques. Purpose To evaluate whether zero CAC score could help ruling out obstructive CAD in a safely manner. Methods Observational study based on a prospective database of patients (pts) referred to cardiac CT between 2017 and 2019. Pts with an Agatston score of zero were selected. Results We included 176 pts with zero CAC score and non-invasive coronary angiography performed. The median duration of follow-up was 23.9 months. Baseline characteristics of the population are shown in Table 1. In 117 pts (66.5%), cardiac CT was indicated as part of their chest pain evaluation. Mean age was 57.2 years old, 68.2% were women and only and 9.4% were active smokers. Normal coronary arteries were found in 173 pts (98.3%). Obstructive CAD, defined as ≥50% luminal diameter stenosis of a major vessel, was present in 1/176 (0.6%); while non-obstructive atherosclerotic plaques were found in 2 pts (1.1%). During follow-up, one patient died of out-of-hospital cardiac arrest. None either suffered from myocardial infarction or needed coronary revascularization. Conclusions In our cohort, a zero CAC score detected by cardiac CT rules out obstructive coronary artery disease in 98.3%, with only 1.7% of non-calcified atherosclerosis plaques and 0.6% of major adverse events. Although further research on this topic is needed, these results support the fact that non-invasive coronary angiography could be avoided in patients with low clinical likelihood of CAD and zero CAC score, facilitating the management of the increasing demand for coronary CT and reduction of radiation dose. Funding Acknowledgement Type of funding source: None


2021 ◽  
Vol 10 (2) ◽  
pp. 356
Author(s):  
Lennard Kroll ◽  
Kai Nassenstein ◽  
Markus Jochims ◽  
Sven Koitka ◽  
Felix Nensa

(1) Background: Epi- and Paracardial Adipose Tissue (EAT, PAT) have been spotlighted as important biomarkers in cardiological assessment in recent years. Since biomarker quantification is an increasingly important method for clinical use, we wanted to examine fully automated EAT and PAT quantification for possible use in cardiovascular risk stratification. (2) Methods: 966 patients with intermediate Framingham risk scores for Coronary Artery Disease referred for coronary calcium scans were included in clinical routine retrospectively. The Coronary Artery Calcium Score (CACS) was extracted and tissue quantification was performed by a deep learning network. (3) Results: The Computed Tomography (CT) segmentations predicted by the network indicated no significant correlation between EAT volume and EAT radiodensity when compared to Agatston score (r = 0.18, r = −0.09). CACS 0 category patients showed significantly lower levels of total EAT and PAT volumes and higher EAT and PAT densities than CACS 1–99 category patients (p < 0.01). Notably, this difference did not reach significance regarding EAT attenuation in male patients. Women older than 50 years, thus more likely to be postmenopausal, were shown to be at higher risk of coronary calcification (p < 0.01, OR = 4.59). CACS 1–99 vs. CACS ≥100 category patients remained below significance level (EAT volume: p = 0.087, EAT attenuation: p = 0.98). (4) Conclusions: Our study proves the feasibility of a fully automated adipose tissue analysis in clinical cardiac CT and confirms in a large clinical cohort that volume and attenuation of EAT and PAT are not correlated with CACS. Broadly available deep learning based rapid and reliable tissue quantification should thus be discussed as a method to assess this biomarker as a supplementary risk predictor in cardiac CT.


Circulation ◽  
2021 ◽  
Vol 143 (Suppl_1) ◽  
Author(s):  
Bhavya Varma ◽  
Oluseye Ogunmoroti ◽  
Chiadi Ndumele ◽  
Di Zhao ◽  
Moyses Szklo ◽  
...  

Background: Adipokines are secreted by adipose tissue, play a role in cardiometabolic pathways, and have differing associations with cardiovascular disease (CVD). Coronary artery calcium (CAC) and its progression indicate subclinical atherosclerosis and prognosticate CVD risk. However the association of adipokines with CAC progression is not well established. We examined the association of adipokines with the odds of a history of CAC progression in the Multi-Ethnic Study of Atherosclerosis (MESA). Methods: We performed an analysis of 1,904 community dwelling adults free of clinical CVD in MESA. Participants underwent measurement of serum adipokines [leptin, resistin and adiponectin] at visits 2 or 3 (randomly assigned) and a contemporaneous cardiac CT scan at same visit. Participants also had a prior cardiac CT at visit 1, at a median of 2.4 years earlier. On both CTs, CAC was quantified by Agatston score. We defined a history of CAC progression between the CT scans at visit 1 and at visit 2 or 3 as those with >0 Agatston units of change per year (and compared to those with ≤0 units of change per year). We used logistic regression to examine the odds of having a history of CAC progression by adipokine tertiles using progressively adjusted models. Results: The mean participant age was 65 (10) years; 50% were women, 40% White, 13% Chinese, 21% Black and 26% Hispanic. The prevalences of CAC at visits 1 and 2/3 were 49% and 58%, respectively. There were 1,001 (53%) who had CAC progression between the 2 CT scans. In demographic-adjusted models (model 1, Table), higher leptin and lower adiponectin were associated with increased odds of prior CAC progression. In models fully adjusted for BMI and other CVD risk factors (model 3), only the highest tertile of leptin remained associated with a greater odds of prior CAC progression [OR 1.55 (95% CI 1.04, 2.30)]. Conclusions: Higher leptin levels were independently associated with a history of CAC progression. Atherosclerosis progression may be one mechanism through which leptin confers increased CVD risk


2020 ◽  
Vol 13 (2) ◽  
pp. 524-526 ◽  
Author(s):  
Simon S. Martin ◽  
Marly van Assen ◽  
Saikiran Rapaka ◽  
H. Todd Hudson ◽  
Andreas M. Fischer ◽  
...  

Author(s):  
Gianmarco Santini ◽  
Daniele Della Latta ◽  
Nicola Martini ◽  
Gabriele Valvano ◽  
Andrea Gori ◽  
...  

Radiology ◽  
2007 ◽  
Vol 243 (2) ◽  
pp. 527-538 ◽  
Author(s):  
Cynthia H. McCollough ◽  
Stefan Ulzheimer ◽  
Sandra S. Halliburton ◽  
Kaiss Shanneik ◽  
Richard D. White ◽  
...  

2020 ◽  
Vol 35 (Supplement_3) ◽  
Author(s):  
Ana Carina Ferreira ◽  
Marco Mendes ◽  
Cecília Silva ◽  
Patrícia Cotovio ◽  
Inês Aires ◽  
...  

Abstract Background and Aims Chronic kidney disease – mineral and bone disorder (CKD-MBD) is a well-known syndrome in end stage renal disease. Vascular calcifications are one of its components. Renal transplantation seemed to halt the progression of vascular calcifications. The aim of this study was to analyse the progression of vascular calcifications in a cohort of renal transplanted patients, and the associations of those with the old and new bone-derived hormones. Method We performed a prospective cohort study of a consecutive sample of de novo single renal transplanted patients in our unit. All patients were submitted to a bone biopsy and laboratorial evaluation at baseline (time 0) including measurements of calcium (Ca), phosphorus (Pi), magnesium (Mg), vitamin D (vitD), calcitonin, parathyroid hormone (PTH), bone alkaline phosphatase (bAP) and total alkaline phosphatase (tAP), alpha-klotho, fibroblast grow-factor 23 (FGF23) and sclerostin. Patients were followed for 12 months, after which performed a second bone biopsy and laboratorial evaluation (time 1). At inclusion, demographic, clinical and transplant-related data were collected, X-ray of the pelvis and hands (Adragão score) and echocardiographic findings were recorded. At the end of the study, echocardiogram, X-ray of pelvis and hands, bone densitometry and non-contrast cardiac CT (Agatston score) were performed. Immunosuppression included induction therapy followed by tacrolimus, mycophenolate mofetil and prednisolone. Continuous variables are presented as medians and categorical variables as frequencies. Associations between variables were performed using Wilcoxon rank sum test and Spearman correlation test. STATA software was used and p &lt; 0.05 was considered statistically significant. Results We recruited 85 patients from 1st October 2015 to 1st March 2018. Mean age 50.1±12.7 years, 59 men (69.4%), 66 caucasian (77.6%), median BMI 25.1±3.4. At the end of 12 months, 6 patients refuse to perform the 2nd evaluation, 5 had primary non-function of the kidney graft, 1 had no sample on bone biopsy in time 0 and 4 patients died. We performed a 2nd evaluation in 69 patients and included those in this study. The median baseline and 12 months Adragão score had no differences [1 (0 – 2)]. The median coronary artery calcium score was 48.5 (0 – 535) and median percentile was 80 (0 – 92.5). Valvular calcifications were present in 15 and 16 patients at baseline and after 1 year respectively, with no statistical difference between the two time points. Coronary artery calcium scores were correlated with age (p&lt;0.001), two time points Adragão score (p&lt;0.001), presence of valvular calcification in time 1 evaluation (p=0.004), baseline calcium (p=0.02), baseline and 1-year sclerostin (p=0.01; p=0.04). Coronary artery calcium scores were higher in patients with highest values of FGF23 at baseline (p=0.04). Using a pairwise correlation, vitamin D levels (r=0.4, p=0.0004), iPTH (r=0.6, p&lt;0.001) and total cholesterol levels (r=-0.3, p=0.01) were correlated with the score. Coronary calcium Percentile (adjusted for age, gender and race) was correlated with Adragão score in the two time points (p=0.0001; p=0.002), with presence of valvular calcifications in time 1 evaluation (p=0.02), baseline and 1-year calcium serum levels (p=0.004; p=0.02) and baseline sclerostin (p=0.01). Conclusion In conclusion, vascular calcifications stabilize after renal transplant. Adragão score, that is a less expensive exam than cardiac CT, can assess vascular calcifications in renal transplanted patients. Only calcium and sclerostin correlated with both Agatston scores and coronary calcium percentiles.


2020 ◽  
Vol 14 (3) ◽  
pp. S23
Author(s):  
E. Udoh ◽  
T. Cohoon ◽  
M. Kolossváry ◽  
S. Newlander ◽  
B. Szilveszter ◽  
...  

Circulation ◽  
2018 ◽  
Vol 137 (suppl_1) ◽  
Author(s):  
Vinita Subramanya ◽  
Di Zhao ◽  
Pamela Ouyang ◽  
Wendy Ying ◽  
Dhananjay Vaidya ◽  
...  

Background: Cardiovascular disease (CVD) is the leading cause of death in women. Sex differences in risk factors, prevalence and mortality suggest the involvement of sex hormones in disease processes. Coronary artery calcium (CAC) is a marker of subclinical atherosclerosis and its progression. CAC is prognostic of CVD risk, independent of traditional risk factors, even among low-risk women. We hypothesized that a more androgenic hormone pattern will predict CAC progression over 10 years in post-menopausal women. Methods: We studied 2759 post-menopausal women, aged 45-84 years, participating in MESA who underwent serum sex hormone measurement and a cardiac CT scan for CAC at baseline (2000-2002). Among these, 2427 women had up to 3 follow-up cardiac CT scans at subsequent visits spanning 10 years. CAC was assessed by Agatson units. CAC and sex hormones were log-transformed for analysis. Using multivariable-adjusted Poisson and linear mixed effects models, we tested the longitudinal associations of testosterone (T), free T, dehydroepiandrosterone (DHEA), estradiol (E2), and sex hormone binding globulin (SHBG) with prevalent CAC and progression of CAC over 10 years. Results: At baseline, average age was 65 years, 46% had prevalent CAC and 32% were using hormone therapy (HT). Cross-sectionally, there were no associations between sex hormones and prevalent CAC. After adjustment for demographics, lifestyle factors and use of HT, higher levels of free T and lower levels of SHBG were associated with an increase in CAC progression over 10 years ( Table, Model 2). These associations remained statistically significant after adjusting for potential mediating cardiovascular risk factors (Model 3) and in sensitivity analyses excluding women on HT. Conclusion: A more androgenic hormone profile of higher free T and lower SHBG is associated with a greater CAC progression over 10 years in post-menopausal women. Sex hormone levels may help identify women at increased CVD risk who may benefit from other risk reduction strategies.


Sign in / Sign up

Export Citation Format

Share Document