CT Imaging of the Vulnerable Plaque

Cardiac CT: Competition, complimentary or confounder

Coronary CT angiography (CCTA) has been gradually adopted into clinical practice over the last two decades. CCTA has high diagnostic accuracy, prognostic value, and unique features such as assessment of plaque composition. CCTA-derived functional assessment techniques such as fractional flow reserve and CT perfusion are also available and can increase the diagnostic specificity of the modality. These properties propound CCTA as a competitor of functional testing in diagnosis of obstructive CAD, however, utilizing CCTA in a concomitant fashion to potentiate the performance of the latter can lead to better patient care and may provide more accurate prognostic information. Although multiple diagnostic challenges such as evaluation of calcified segments, stents, and small distal vessels still exist, the technologic developments in hardware as well as growing incorporation of artificial intelligence to daily practice are all set to augment the diagnostic and prognostic role of CCTA in cardiovascular disorders.

Predicting coronary artery calcified plaques using perivascular fat CT radiomics features and clinical risk factors

OBJECTIVE

The purpose of this study was to develop a combined radiomics model to predict coronary plaque texture using perivascular fat CT radiomics features combined with clinical risk factors.

METHODS

The data of 200 patients with coronary plaques were retrospectively analyzed and randomly divided into a training group and a validation group at a ratio of 7:3. In the training group, The best feature set was selected by using the maximum correlation minimum redundancy method and the least absolute shrinkage and selection operator. Radiomics models were built based on different machine learning algorithms. The clinical risk factors were then screened using univariate logistic regression analysis. and finally a combined radiomics model was developed using multivariate logistic regression analysis to combine the best performing radiomics model with clinical risk factors and validated in the validation group. The efficacy of the model was assessed by a receiver operating characteristic curve, the consistency of the nomogram was assessed using calibration curves, and the clinical usefulness of the nomogram was assessed using decision curve analysis.

RESULTS

Twelve radiomics features were used by different machine learning algorithms to construct the radiomics model. Finally, the random forest algorithm built the best radiomics model in terms of efficacy, and this was combined with age to construct a combined radiomics model. The area under curve for the training and validation group were 0.98 (95% confidence interval, 0.95-1.00) and 0.97 (95% confidence interval, 0.92-1.00) with sensitivities of 0.92 and 0.86 and specificities of 0.99 and 1, respectively. The calibration curve demonstrated that the nomogram had good consistency, and the decision curve analysis demonstrated that the nomogram had high clinical utility.

CONCLUSIONS

The combined radiomics model established based on CT radiomics features and clinical risk factors has high value in predicting coronary artery calcified plaque and can provide a reference for clinical decision-making.

Integrating Coronary Plaque Information from CCTA by ML Predicts MACE in Patients with Suspected CAD

Conventional prognostic risk analysis in patients undergoing noninvasive imaging is based upon a limited selection of clinical and imaging findings, whereas machine learning (ML) algorithms include a greater number and complexity of variables. Therefore, this paper aimed to explore the predictive value of integrating coronary plaque information from coronary computed tomographic angiography (CCTA) with ML to predict major adverse cardiovascular events (MACEs) in patients with suspected coronary artery disease (CAD). Patients who underwent CCTA due to suspected coronary artery disease with a 30-month follow-up for MACEs were included. We collected demographic characteristics, cardiovascular risk factors, and information on coronary plaques by analyzing CCTA information (plaque length, plaque composition and coronary artery stenosis of 18 coronary artery segments, coronary dominance, myocardial bridge (MB), and patients with vulnerable plaque) and follow-up information (cardiac death, nonfatal myocardial infarction and unstable angina requiring hospitalization). An ML algorithm was used for survival analysis (CoxBoost). This analysis showed that chest symptoms, the stenosis severity of the proximal anterior descending branch, and the stenosis severity of the middle right coronary artery were among the top three variables in the ML model. After the 22nd month of follow-up, in the testing dataset, ML showed the largest C-index and AUC compared with Cox regression, SIS, SIS score + clinical factors, and clinical factors. The DCA of all the models showed that the net benefit of the ML model was the highest when the treatment threshold probability was between 1% and 9%. Integrating coronary plaque information from CCTA based on ML technology provides a feasible and superior method to assess prognosis in patients with suspected coronary artery disease over an approximately three-year period.

Cardiac-CT with the newest CT scanners: An incoming screening tool for competitive athletes?

Competitive athletes of all skill levels are at risk of sudden cardiac death (SCD) due to certain heart conditions. Prior to engagement in high-intensity athletics, it is necessary to screen for these conditions in order to prevent sudden cardiac death. Cardiac-CT angiography (CCTA) is a reliable tool to rule out the leading causes of SCD by providing an exceptional overview of vascular and cardiac morphology. This allows CCTA to be a powerful resource in identifying cardiac anomalies in selected patients (i.e. unclear symptoms or findings at ECG or echocardiography) as well as to exclude significant coronary artery disease (CAD). With the advancement of technology over the last few years, the latest generations of computed tomography (CT) scanners provide better image quality at lower radiation exposures. With the amount of radiation exposure per scan now reaching the sub-millisievert range, the number of CT examinations it is supposed to increase greatly, also in the athlete's population. It is thus necessary for radiologists to have a clear understanding of how to make and interpret a CCTA examination so that these studies may be performed in a responsible and radiation conscious manner especially when used in the younger populations. Our work aims to illustrate the main radiological findings of CCTAs and highlight their clinical impact with some case studies. We also briefly describe critical features of state-of-the-art CT scanners that optimize different acquisitions to obtain the best quality at the lowest possible dose.

Characteristics of culprit lesion in patients with non-ST-elevation myocardial infarction and improvement of diagnostic utility using dual energy cardiac CT

AIMS

The aim of the study was to identify the characteristics of the culprit lesions compared to non-culprit lesions in patients with non-ST-elevation-myocardial infarction using dual energy computed tomography (DECT).

METHODS AND RESULTS

In 29 patients, we identified 29 culprit lesions and 227 non-culprit lesions. Quantitative values such as the effective atomic number (effective-Z) and Hounsfield Units (HU) values were measured. Furthermore, all the lesions were characterised using characteristics such as composition (non-calcified, predominantly-non-calcified, predominantly-calcified, or calcified), presence of spotty calcification, remodelling index, and napkin ring sign. The mean effective-Z and HU values were significantly lower in culprit lesions than in non-culprit lesions (8.99 ± 1.21 vs 9.79 ± 1.52; p = 0.0066 and 87.41 ± 84.97 vs. 154.45 ± 176.13; p = 0.0447). The culprit lesions had a higher frequency of non-calcified plaques and predominantly non-calcified plaques, and were with a greater presence of napkin ring signs in comparison with non-culprit lesions. There were no differences in the presence of spotty calcification or remodelling index. By adding effective-Z to plaque characteristics such as non-calcified, positive remodelling, spotty calcification, and napkin rings we observed a significant increased sensitivity of detecting culprit lesions (65.5% vs.44.8%), but no significant changes in area under curve (AUC).

CONCLUSION

The use of DECT adds new information of the plaque composition expressed by the effective-Z, which differs significantly in culprit lesions in comparison with non-culprit lesions. The use of the effective-Z improves the diagnostic sensitivity in detection of culprit lesions.