Automated assessment of longitudinal biomarker changes at abdominal CT: correlation with subsequent cardiovascular events in an asymptomatic adult screening cohort.

BACKGROUND: Cardiovascular (CV) disease is a major public health concern, and automated methods can potentially capture relevant longitudinal changes on CT for opportunistic CV screening purposes. METHODS: Fully-automated and validated algorithms that quantify abdominal fat, muscle, bone, liver, and aortic calcium were retrospectively applied to a longitudinal adult screening cohort undergoing serial non-contrast CT examination between 2005 and 2016. Downstream major adverse events (MI/CVA/CHF/death) were identified via algorithmic EHR search. Logistic regression, ROC curve, and Cox survival analyses assessed for associations between changes in CT variables and adverse events. RESULTS: Final cohort included 1949 adults (942 M/1007F; mean age, 56.2 ± 6.2 years at initial CT). Mean interval between CT scans was 5.8 ± 2.0 years. Mean clinical follow-up interval from initial CT was 10.4 ± 2.7 years. Major CV events occurred after follow-up CT in 230 total subjects (11.8%). Mean change in aortic calcium Agatston score was significantly higher in CV(+) cohort (591.6 ± 1095.3 vs. 261.1 ± 764.3), as was annualized Agatston change (120.5 ± 263.6 vs. 46.7 ± 143.9) (p < 0.001 for both). 5-year area under the ROC curve (AUC) for Agatston change was 0.611. Hazard ratio for Agatston score change > 500 was 2.8 (95% CI 1.5-4.0) relative to < 500. Agatston score change was the only significant univariate CT biomarker in the survival analysis. Changes in fat and bone measures added no meaningful prediction. CONCLUSION: Interval change in automated CT-based abdominal aortic calcium load represents a promising predictive longitudinal tool for assessing cardiovascular and mortality risks. Changes in other body composition measures were less predictive of adverse events.

Atherosclerotic Plaque Burden on Abdominal CT: Automated Assessment With Deep Learning on Noncontrast and Contrast-enhanced Scans.

BACKGROUND: Abdominal aortic atherosclerotic plaque burden may have clinical significance but manual measurement is time-consuming and impractical. PURPOSE: To perform external validation on an automated atherosclerotic plaque detector for noncontrast and postcontrast abdominal CT. MATERIALS AND METHODS: The training data consisted of 114 noncontrast CT scans and 23 postcontrast CT urography scans. The testing data set consisted of 922 CT colonography (CTC) scans, and 1207 paired noncontrast and postcontrast CT scans from renal donors from a second institution. Reference standard data included manual plaque segmentations in the 137 training scans and manual plaque burden measurements in the 922 CTC scans. The total Agatston score and group (0-3) was determined using fully-automated deep learning software. Performance was assessed by measures of agreement, linear regression, and paired evaluations. RESULTS: On CTC scans, automated Agatston scoring correlated highly with manual assessment (R2 = 0.94). On paired renal donor CT scans, automated Agatston scoring on postcontrast CT correlated highly with noncontrast CT (R2 = 0.95). When plaque burden was expressed as a group score, there was excellent agreement for both the CTC (weighted kappa 0.80 ± 0.01 [95% confidence interval: 0.78-0.83]) and renal donor (0.83 ± 0.02 [0.79-0.86]) assessments. CONCLUSION: Fully automated detection, segmentation, and scoring of abdominal aortic atherosclerotic plaques on both pre- and post-contrast CT was validated and may have application for population-based studies.

Cardiac cine CT approaching 1 mSv: implementation and assessment of a 58-ms temporal resolution protocol.

Clinical use of cardiac cine CT imaging is limited by high radiation dose and low temporal resolution. To evaluate a low radiation dose, high temporal resolution cardiac cine CT protocol in human cardiac CT and phantom scans. CT scans of a circulating iodine target were reconstructed using the conventional single heartbeat half-scan (HS, approx. 175 ms temporal resolution) and the 3-heartbeat multi-segment (MS, approx. 58 ms) algorithms. Motion artifacts were quantified by the root-mean-square error (RMSE). Low-dose cardiac cine CT scans were performed in 55 subjects at a tube potential of 80 kVp and current of 80 mA. Image quality of HS and MS scans was assessed by blinded reader quality assessment, left ventricular (LV) free wall motion, and LV ejection rate. Motion artifacts in phantom scans were higher in HS than in MS reconstructions (RSME 188 and 117 HU, respectively; p = 0.001). Median radiation dose in human scans was 1.2 mSv. LV late diastolic filling was observed more frequently in MS than in HS images (42 vs. 26 subjects, respectively; p < 0.001). LV free wall systolic motion was more physiologic and had less error in MS than in HS reconstructions (sum-of-squared errors 34 vs. 45 mm2, respectively; p < 0.001), and LV peak ejection rate was higher in MS than in HS reconstructions (166 vs. 152 mL/s, respectively; p < 0.001). Cardiac cine CT imaging is feasible at a low radiation dose of 1.2 mSv. MS reconstruction showed improved imaging of rapid motion in phantom studies and human cardiac CTs.

Automated Liver Fat Quantification at Nonenhanced Abdominal CT for Population-based Steatosis Assessment.

Background Nonalcoholic fatty liver disease and its consequences are a growing public health concern requiring cross-sectional imaging for noninvasive diagnosis and quantification of liver fat. Purpose To investigate a deep learning-based automated liver fat quantification tool at nonenhanced CT for establishing the prevalence of steatosis in a large screening cohort. Materials and Methods In this retrospective study, a fully automated liver segmentation algorithm was applied to noncontrast abdominal CT examinations from consecutive asymptomatic adults by using three-dimensional convolutional neural networks, including a subcohort with follow-up scans. Automated volume-based liver attenuation was analyzed, including conversion to CT fat fraction, and compared with manual measurement in a large subset of scans. Results A total of 11 669 CT scans in 9552 adults (mean age ± standard deviation, 57.2 years ± 7.9; 5314 women and 4238 men; median body mass index [BMI], 27.8 kg/m2) were evaluated, including 2117 follow-up scans in 1862 adults (mean age, 59.2 years; 971 women and 891 men; mean interval, 5.5 years). Algorithm failure occurred in seven scans. Mean CT liver attenuation was 55 HU ± 10, corresponding to CT fat fraction of 6.4% (slightly fattier in men than in women [7.4% ± 6.0 vs 5.8% ± 5.7%; P < .001]). Mean liver Hounsfield unit varied little by age (<4 HU difference among all age groups) and only weak correlation was seen with BMI (r2 = 0.14). By category, 47.9% (5584 of 11 669) had negligible or no liver fat (CT fat fraction <5%), 42.4% (4948 of 11 669) had mild steatosis (CT fat fraction of 5%-14%), 8.8% (1025 of 11 669) had moderate steatosis (CT fat fraction of 14%-28%), and 1% (112 of 11 669) had severe steatosis (CT fat fraction >28%). Excellent agreement was seen between automated and manual measurements, with a mean difference of 2.7 HU (median, 3 HU) and r2 of 0.92. Among the subcohort with longitudinal follow-up, mean change was only -3 HU ± 9, but 43.3% (806 of 1861) of patients changed steatosis category between first and last scans. Conclusion This fully automated CT-based liver fat quantification tool allows for population-based assessment of hepatic steatosis and nonalcoholic fatty liver disease, with objective data that match well with manual measurement. The prevalence of at least mild steatosis was greater than 50% in this asymptomatic screening cohort. © RSNA, 2019.

Associations of cardiovascular disease risk factors with abdominal aortic calcium volume and density: The Multi-Ethnic Study of Atherosclerosis (MESA).

BACKGROUND AND AIMS: Abdominal aortic calcium (AAC) predicts future cardiovascular disease (CVD) events and all-cause mortality independent of CVD risk factors. The standard AAC score, the Agatston, up-weights for greater calcium density, and thus models higher calcium density as associated with increased CVD risk. We determined associations of CVD risk factors with AAC volume and density (separately). METHODS: In a multi-ethnic cohort of community living adults, we used abdominal computed tomography scans to measure AAC volume and density. Multivariable linear regression was used to determine the period cross-sectional independent associations of CVD risk factors with AAC volume and AAC density in participants with prevalent AAC. RESULTS: Among 1413 participants with non-zero AAC scores, the mean age was 65 ± 9 years, 52% were men, 44% were European-, 24% were Hispanic-, 18% were African-, and 14% were Chinese Americans (EA, HA, AA, and CA respectively). Median (interquartile range, IQR) for AAC volume was 628 mm3 (157-1939 mm3), and mean AAC density was 3.0 ± 0.6. Compared to EA, each of HA, AA, and CA had lower natural log (ln) AAC volume, but higher AAC density. After adjustments for AAC density, older age, ever smoking history, higher systolic blood pressure, elevated total cholesterol, reduced HDL cholesterol, statin and anti-hypertensive medication use, family history of myocardial infarction, and alcohol consumption were significantly associated with higher ln(AAC volume). In contrast, after adjustments for ln(AAC volume), older age, ever smoking history, higher BMI, and lower HDL cholesterol were significantly associated with lower AAC density. CONCLUSIONS: Several CVD risk factors were associated with higher AAC volume, but lower AAC density. Future studies should investigate the impact of calcium density of aortic plaques in CVD.

Impact of Replacing the Pooled Cohort Equation With Other Cardiovascular Disease Risk Scores on Atherosclerotic Cardiovascular Disease Risk Assessment (from the Multi-Ethnic Study of Atherosclerosis [MESA]).

The increase in statin eligibility by the new cholesterol guidelines is mostly driven by the Pooled Cohort Equation (PCE) criterion (≥7.5% 10-year PCE). The impact of replacing the PCE with either the modified Framingham Risk Score (FRS) or the Systematic Coronary Risk Evaluation (SCORE) on assessment of atherosclerotic cardiovascular disease (ASCVD) risk assessment and statin eligibility remains unknown. We assessed the comparative benefits of using the PCE, FRS, and SCORE for ASCVD risk assessment in the Multi-Ethnic Study of Atherosclerosis. Of 6,815 participants, 654 (mean age 61.4 ± 10.3; 47.1% men; 37.1% whites; 27.2% blacks; 22.3% Hispanics; 12.0% Chinese-Americans) were included in analysis. Area under the curve (AUC) and decision curve analysis were used to compare the 3 risk scores. Decision curve analysis is the plot of net benefit versus probability thresholds; net benefit = true positive rate - (false positive rate × weighting factor). Weighting factor = Threshold probability/1 - threshold probability. After a median of 8.6 years, 342 (6.0%) ASCVD events (myocardial infarction, coronary heart disease death, fatal or nonfatal stroke) occurred. All 4 risk scores had acceptable discriminative ability for incident ASCVD events; (AUC [95% CI] PCE: 0.737 [0.713 to 0.762]; FRS: 0.717 [0.691 to 0.743], SCORE (high risk) 0.722 [0.696 to 0.747], and SCORE (low risk): 0.721 [0.696 to 0.746]. At the ASCVD risk threshold recommended for statin eligibility for primary prevention (≥7.5%), the PCE provides the best net benefit. Replacing the PCE with the SCORE (high), SCORE (low) and FRS results in a 2.9%, 8.9%, and 17.1% further increase in statin eligibility. The PCE has the best discrimination and net benefit for primary ASCVD risk assessment in a US-based multiethnic cohort compared with the SCORE or the FRS.