Very small calcifications are detected and scored in the coronary arteries from small voxel MDCT images using a new automated/calibrated scoring method with statistical and patient specific plaque definitions

Fully Automated Agatston Score Calculation From Electrocardiography-Gated Cardiac Computed Tomography Using Deep Learning and Multi-Organ Segmentation: A Validation Study

To evaluate deep learning-based calcium segmentation and quantification on ECG-gated cardiac CT scans compared with manual evaluation. Automated calcium quantification was performed using a neural network based on mask regions with convolutional neural networks (R-CNNs) for multi-organ segmentation. Manual evaluation of calcium was carried out using proprietary software. This is a retrospective study of archived data. This study used 40 patients to train the segmentation model and 110 patients were used for the validation of the algorithm. The Pearson correlation coefficient between the reference actual and the computed predictive scores shows high level of correlation (0.84; P < .001) and high limits of agreement (±1.96 SD; -2000, 2000) in Bland-Altman plot analysis. The proposed method correctly classifies the risk group in 75.2% and classifies the subjects in the same group. In total, 81% of the predictive scores lie in the same categories and only seven patients out of 110 were more than one category off. For the presence/absence of coronary artery calcifications, the deep learning model achieved a sensitivity of 90% and a specificity of 94%. Fully automated model shows good correlation compared with reference standards. Automating process reduces evaluation time and optimizes clinical calcium scoring without additional resources.

Fully automatic framework for comprehensive coronary artery calcium scores analysis on non-contrast cardiac-gated CT scan: Total and vessel-specific quantifications

OBJECTIVES

To develop a fully automatic multiview shape constraint framework for comprehensive coronary artery calcium scores (CACS) quantification via deep learning on nonenhanced cardiac CT images.

METHODS

In this retrospective single-centre study, a multi-task deep learning framework was proposed to detect and quantify coronary artery calcification from CT images collected between October 2018 and March 2019. A total of 232 non-contrast cardiac-gated CT scans were retrieved and studied (80 % for model training and 20 % for testing). CACS results of testing datasets (n = 46), including Agatston score, calcium volume score, calcium mass score, were calculated fully automatically and manually at total and vessel-specific levels, respectively.

RESULTS

No significant differences were found in CACS quantification obtained using automatic or manual methods at total and vessel-specific levels (Agatston score: automatic 535.3 vs. manual 542.0, P = 0.993; calcium volume score: automatic 454.2 vs. manual 460.6, P = 0.990; calcium mass score: automatic 128.9 vs. manual 129.5, P = 0.992). Compared to the ground truth, the number of calcified vessels can be accurate recognized automatically (total: automatic 107 vs. manual 102, P = 0.125; left main artery: automatic 15 vs. manual 14, P = 1.000 ; left ascending artery: automatic 37 vs. manual 37, P = 1.000; left circumflex artery: automatic 22 vs. manual 20, P = 0.625; right coronary artery: automatic 33 vs. manual 31, P = 0.500). At the patient's level, there was no statistic difference existed in the classification of Agatston scoring (P = 0.317) and the number of calcified vessels (P = 0.102) between the automatic and manual results.

CONCLUSIONS

The proposed framework can achieve reliable and comprehensive quantification for the CACS, including the calcified extent and distribution indicators at both total and vessel-specific levels.

The relationship between volumetric thoracic bone mineral density and coronary calcification in men and women - results from the Copenhagen General Population Study

BACKGROUND

The association between low bone mineral density (BMD) and the presence of coronary artery calcium (CAC) as a marker of atherosclerosis is unclear. The aim of this study was to assess the potential relationship between volumetric thoracic bone mineral density and coronary calcification in a large population of men and women.

METHODS

Participants from the Copenhagen General Population Study underwent multidetector computed tomography. Volumetric thoracic BMD and CAC were assessed in the same scan. CAC was measured using calibrated mass score (cMS). cMS was dichotomized as cMS = 0 or cMS > 0. The association between BMD and cMS was analyzed using multiple logistic regression in men, premenopausal and postmenopausal women. The model was adjusted for age, BMI, hypertension, hypercholesterolemia, diabetes, known cardiovascular disease and smoking.

RESULTS

Of 2548 eligible participants, 1163 men and 1385 women, mean age 61 ± 10 were included in the study. Mean BMD was 138 ± 46 mg/cm³ for men and 151 ± 49 mg/cm³ women. In 696 men (67%) and 537 women (41%) cMS was found to be above zero. For men, a decrease in BMD of 100 mg/cm³ was associated to an odds ratio of 1.49 for cMS > 0 (95% confidence interval: 1.04-2.13, P = 0.03). In postmenopausal women, a decrease in BMD of 100 mg/cm³ was associated to an odds ratio of 1.47 for MS > 0 (95% confidence interval: 1.04-2.08, P = 0.03). For premenopausal women, no significant association was found between BMD and cMS (odds ratio = 0.74, 95% confidence interval: 0.36-1.52, P = 0.4).

CONCLUSION

Bone mineral density and coronary calcification are inversely related in both men and postmenopausal women, supporting the hypothesis that a direct relation between bone loss and development of atherosclerosis exists irrespective of gender.

Fluorescent angioscopic imaging of calcium phosphate tribasic: precursor of hydroxyapatite, the major calcium deposit in human coronary plaques

Coronary calcification is a risk factor for ischemic heart disease. Hydroxyapatite that is formed by polymerization from calcium phosphate tribasic (CPT) is the major constituent of coronary calcium deposits. If CPT could be visualized, coronary calcification could be predicted and prevented. We discovered that when CPT and collagen I, the main constituent of collagen fibers, are mixed with lac dye (LD) and then exposed to fluorescent light excited at 345 ± 15 nm and emitted at 420 nm, a purple fluorescence that is characteristic of CPT only is elicited. So, we examined localization of CPT and its relation to plaque morphology by color fluorescent angioscopy (CFA) or microscopy (CFM) in 24 coronary arteries obtained from 12 autopsy subjects. By CFA, the incidence (%) of CPT as confirmed by purple fluorescence in 15 normal segments, 25 white plaques, 14 yellow plaques without necrotic core (NC) and 8 yellow plaques with NC was 20, 36, 64 and 100 (p < 0.05 vs. normal segments), respectively. By CFM, the CPT was either deposited alone amorphously or surrounded hydroxyapatite that was identified by Oil Red O, methylene blue and von Kossa’s stain. The results suggested that CFA using LD is feasible for imaging CPT, that is a precursor of hydroxyapatite, in human coronary plaques, and this technique would help prediction and discovery of a preventive method of coronary calcification.

An evaluation of automatic coronary artery calcium scoring methods with cardiac CT using the orCaScore framework

PURPOSE

The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular disease (CVD) events. In clinical practice, CAC is manually identified and automatically quantified in cardiac CT using commercially available software. This is a tedious and time-consuming process in large-scale studies. Therefore, a number of automatic methods that require no interaction and semiautomatic methods that require very limited interaction for the identification of CAC in cardiac CT have been proposed. Thus far, a comparison of their performance has been lacking. The objective of this study was to perform an independent evaluation of (semi)automatic methods for CAC scoring in cardiac CT using a publicly available standardized framework.

METHODS

Cardiac CT exams of 72 patients distributed over four CVD risk categories were provided for (semi)automatic CAC scoring. Each exam consisted of a noncontrast-enhanced calcium scoring CT (CSCT) and a corresponding coronary CT angiography (CCTA) scan. The exams were acquired in four different hospitals using state-of-the-art equipment from four major CT scanner vendors. The data were divided into 32 training exams and 40 test exams. A reference standard for CAC in CSCT was defined by consensus of two experts following a clinical protocol. The framework organizers evaluated the performance of (semi)automatic methods on test CSCT scans, per lesion, artery, and patient.

RESULTS

Five (semi)automatic methods were evaluated. Four methods used both CSCT and CCTA to identify CAC, and one method used only CSCT. The evaluated methods correctly detected between 52% and 94% of CAC lesions with positive predictive values between 65% and 96%. Lesions in distal coronary arteries were most commonly missed and aortic calcifications close to the coronary ostia were the most common false positive errors. The majority (between 88% and 98%) of correctly identified CAC lesions were assigned to the correct artery. Linearly weighted Cohen's kappa for patient CVD risk categorization by the evaluated methods ranged from 0.80 to 1.00.

CONCLUSIONS

A publicly available standardized framework for the evaluation of (semi)automatic methods for CAC identification in cardiac CT is described. An evaluation of five (semi)automatic methods within this framework shows that automatic per patient CVD risk categorization is feasible. CAC lesions at ambiguous locations such as the coronary ostia remain challenging, but their detection had limited impact on CVD risk determination.

Identifying Small Coronary Calcification in Non-Contrast 0.5-mm Slice Reconstruction to Diagnose Coronary Artery Disease in Patients with a Conventional Zero Coronary Artery Calcium Score

Aims: In a new-generation computed tomography (CT) scanner, coronary artery calcium (CAC) scores were measured using 3.0-mm slice reconstruction images originally acquired with 0.5 mm thickness scans in a single beat. This study investigated the usefulness of thin-slice (0.5 mm) reconstruction for identifying small calcifications in coronary arteries and evaluated the association with coronary plaques and stenosis compared to conventional 3.0-mm reconstruction images.

Methods: We evaluated 132 patients with zero CAC scores in conventional 3.0-mm Agatston method using a 320-slice CT. Then, 0.5-mm slice reconstruction was performed to identify small calcifications. The presence of stenosis and coronary plaques was assessed using coronary CT angiography.

Results: In total, 22 small calcifications were identified in 18 patients. There were 28 (21%) patients with any (≥ 25%) stenosis (34 lesions). Forty-seven coronary plaques were found in 33 patients (25%), including 7 calcified plaques in 7 patients (5%), 34 noncalcified plaques in 27 patients (20%), and 6 partially calcified plaques in 5 patients (4%). Patients with small calcifications had a significantly higher prevalence of noncalcified or partially calcified plaques (83% vs 14%; p < 0.001) and obstructive stenosis (33% vs 5.2%; p < 0.001) compared to those without small calcifications. The addition of small calcifications to the coronary risk factors when diagnosing stenosis significantly improved the diagnostic value.

Conclusion: Small calcifications detected by thin-slice 0.5-mm reconstruction are useful for distinguishing coronary atherosclerotic lesions in patients with zero CAC scores from conventional CT reconstruction.

High dose and long-term statin therapy accelerate coronary artery calcification

BACKGROUND

In randomized clinical trials statins and placebo treated patients showed the same degree of coronary artery calcium (CAC) progression. We reanalyzed data from two clinical trials to further investigate the time and dose dependent effects of statins on CAC. Additionally, we investigated whether CAC progression was associated with incident cardiovascular events.

METHODS AND RESULTS

Data were pooled from two clinical trials: St. Francis Heart Study (SFHS) (419 and 432 patients treated with placebo and 20 mg atorvastatin daily, respectively) and EBEAT Study (164 and 179 patients respectively treated with 10 mg and 80 mg atorvastatin daily). CAC scores were assessed at baseline, 2 years and 4-6 years in SFHS; in EBEAT they were measured at baseline and 12 months. After a short-term follow-up (12 to 24 months) placebo and low dose atorvastatin showed a similar CAC increase, although 80 mg/daily atorvastatin increased CAC an additional 12-14% over placebo (p<0.001). In the long-term, atorvastatin caused a greater progression of CAC compared to placebo (additional 1.1%, p=0.04). In SFHS 42 cardiovascular events occurred after the second CT scan. The baseline and progression of CAC were greater in patients with events. However, only baseline CAC and family history of premature cardiovascular disease but not CAC progression were independent predictors of events.

CONCLUSIONS

Despite a greater CAC increase with high dose and long-term statin therapy, events did not occur more frequently in statin treated patients. This suggests that CAC growth under treatment with statins represents plaque repair rather than continuing plaque expansion.