The effect of coronary calcification on diagnostic performance of machine learning-based CT-FFR: a Chinese multicenter study

Agreement of Fractional Flow Reserve Estimated by Computed Tomography With Invasively Measured Fractional Flow Reserve: A Systematic Review and Meta-Analysis

BACKGROUND

Fractional flow reserve (FFR) is the ratio of blood pressure measured distal to a stenosis and pressure proximal to a stenosis. FFR can be estimated noninvasively using computed tomography (CT) although the usefulness of this technique remains controversial. This meta-analysis evaluated the agreement of FFR estimated by CT (FFR-CT) with invasively measured FFR. The study also evaluated the diagnostic accuracy of FFR-CT, defined as the ability of FFR-CT to classify lesions as hemodynamically significant (invasive FFR ≤0.8) or insignificant (invasive FFR >0.8).

METHODS AND RESULTS

Forty-three studies reporting on 7291 blood vessels from 5236 patients were included. A moderate positive linear relationship between FFR-CT and invasively measured FFR was observed (Spearman correlation coefficient: 0.67). Agreement between the 2 measures increased as invasively measured FFR values approached 1. The overall diagnostic accuracy, sensitivity and specificity of FFR-CT were 82.2%, 80.9%, and 83.1%, respectively. Diagnostic accuracy of 90% could be demonstrated for FFR-CT values >0.90 and <0.49. The diagnostic accuracy of off-site tools was 79.4% and the diagnostic accuracy of on-site tools was 84.1%.

CONCLUSIONS

The agreement between FFR-CT and invasive FFR is moderate although agreement is highest in vessels with FFR-CT >0.9. Diagnostic accuracy varies widely with FFR-CT value but is above 90% for FFR-CT values >0.90 and <0.49. Furthermore, on-site and off-site tools have similar performance. Ultimately, FFR-CT may be a useful adjunct to CT coronary angiography as a gatekeeper for invasive coronary angiogram.

Feasibility and Diagnostic Performance of Functional SYNTAX Score Derived From Dynamic CT Myocardial Perfusion Imaging

BACKGROUND

Computed tomography (CT) fractional flow reserve (FFR)-derived functional SYNTAX score (FSSCT-FFR) is a valuable method for guiding treatment strategy in patients with multivessel coronary artery disease. Dynamic CT myocardial perfusion imaging (CT-MPI) demonstrates higher diagnostic accuracy than CT-FFR in identifying hemodynamically significant coronary artery disease. We aimed to evaluate the feasibility of CT-MPI-derived FSS (FSSCT-MPI) with reference to invasive FSS.

METHODS

In this retrospective study, patients with multivessel coronary artery disease who underwent dynamic CT-MPI+ coronary CT angiography and invasive coronary angiography or FFR within 4 weeks were consecutively included. Invasive (FSSinvasive) and noninvasive FSS (FSSCT-MPI and FSSCT-FFR) were calculated by an online calculator, which assigned points to lesions with hemodynamic significance (defined as FFRinvasive ≤0.80, invasive coronary angiography diameter stenosis ≥90%, CT-FFR ≤0.80, and myocardial ischemia on CT-MPI). Weighted κ value and net reclassification index were calculated to determine the consistency and incremental discriminatory power of FSSCT-MPI. Receiver operating characteristic curve analysis was used for the comparison of FSSCT-MPI and FSSCT-FFR in detecting intermediate- to high-risk patients.

RESULTS

A total of 119 patients (96 men; 64.6±10.6 years) with 305 obstructive lesions were included. The average FSSCT-MPI, FSSCT-FFR, and FSSinvasive were 15.58±13.03, 16.18±13.30, and 13.11±12.22, respectively. The agreement on risk classification based on the FSSCT-MPI tertiles was good (weighted κ, 0.808). With reference to FSSinvasive, FSSCT-MPI correctly reclassified 27 (22.7%) patients from the intermediate- to high SYNTAX score group to the low-score group (net reclassification index, 0.30; P<0.001). In patients with severe calcification, FSSCT-MPI had better diagnostic value than FSSCT-FFR in detecting intermediate- to high-risk patients when compared with FSSinvasive (area under the curve, 0.976 versus 0.884; P<0.001).

CONCLUSIONS

Noninvasive FSS derived from CT-MPI is feasible and has strong concordance with FSSinvasive. It allows accurate categorization of FSS in patients with multivessel coronary artery disease, in particular with severe calcification.

Diagnostic performance of angiography-derived fractional flow reserve and CT-derived fractional flow reserve: A systematic review and Bayesian network meta-analysis

OBJECTIVE

Accumulating evidence has demonstrated that fractional flow reserves (FFRs) derived from invasive coronary angiograms (CA-FFRs) and coronary computed tomography angiography-derived FFRs (CT-FFRs) are promising alternatives to wire-based FFRs. However, it remains unclear which method has better diagnostic performance. This systematic review and meta-analysis aimed to compare the diagnostic performances of the two approaches.

METHODS

The Cochrane Library, PubMed, Embase, Medline (Ovid), the Chinese China National Knowledge Infrastructure Database (CNKI), VIP, and WanFang Data databases were searched for relevant studies that included comparisons between CA-FFR and CT-FFR, from their respective database inceptions until January 1, 2023. Studies where both noninvasive FFR (including CA-FFR and CT-FFR) and invasive FFR (as a reference standard) were performed for the diagnosis of ischemic coronary artery disease and were designed as prospective, paired diagnostic studies, were pulled. The diagnostic test accuracy method and Bayesian hierarchical summary receiver operating characteristic (ROC) model for network meta-analysis (NMA) of diagnostic tests (HSROC-NMADT) were both used to perform a meta-analysis on the data.

RESULTS

Twenty-six studies were included in this NMA. The results from both the diagnostic test accuracy and HSROC-NMADT methods revealed that the diagnostic accuracy of CA-FFR was higher than that of CT-FFR, in terms of sensitivity (Se; 0.86 vs. 0.84), specificity (Sp; 0.90 vs. 0.78), positive predictive value (PPV; 0.83 vs. 0.70), and negative predictive value (NPV; 0.91 vs. 0.89) for the detection of myocardial ischemia. A cumulative ranking curve analysis indicated that CA-FFR had a higher diagnostic accuracy than CT-FFR in the context of this study, with a higher area under the ROC curve (AUC; 0.94 vs. 0.87).

CONCLUSIONS

Although both of these two commonly used virtual FFR methods showed high levels of diagnostic accuracy, we demonstrated that CA-FFR had a better Se, Sp, PPV, NPV, and AUC than CT-FFR. However, this study provided only indirect comparisions; therefore, larger studies are warranted to directly compare the diagnostic performances of these two approaches.

A meta-analysis comparing the diagnostic performance of computed tomography-derived fractional flow reserve and coronary computed tomography angiography at different levels of coronary artery calcium score

OBJECTIVES

The impact of coronary calcification on the diagnostic accuracy of computed tomography-derived fractional flow reserve (CT-FFR) and coronary computed tomography angiography (CCTA) remains a crucial consideration. This meta-analysis aims to compare the diagnostic performance of CT-FFR and CCTA at different levels of coronary artery calcium score (CACS).

METHODS AND RESULTS

We searched PubMed, Embase, and the Cochrane Library for relevant articles on CCTA, CT-FFR, and invasive fractional flow reserve (FFR). Ten studies were included to evaluate the diagnostic performance of CT-FFR and CCTA at the per-patient and per-vessel levels in four CACS groups. Invasive FFR was used as the reference standard. Except for the CACS ≥ 400 group, the AUC of CT-FFR was higher than those of CCTA in other subgroups of CACS (in CACS < 100 (per-patient, 0.9 (95% CI 0.87-0.92) vs. 0.32 (95% CI 0.28-0.36); per-vessel, 0.92 (95% CI 0.89-0.94) vs. 0.66 (95% CI 0.62-0.7); both p < 0.001), CACS ≥ 100 (per-patient, 0.86 (95% CI 0.82-0.88) vs. 0.44 (95% CI 0.4-0.48); per-vessel, 0.88 (95% CI 0.85-0.9) vs. 0.51 (95% CI 0.46-0.55); both p < 0.001), and CACS < 400 (per-patient, 0.9 (95% CI 0.87-0.93) vs. 0.74 (95% CI 0.7-0.78), p < 0.001; per-vessel, 0.8 (95% CI 0.76-0.83) vs. 0.74 (95% CI 0.7-0.78); p = 0.02)).

CONCLUSIONS

CT-FFR demonstrates superior diagnostic performance in low CACS groups (CACS < 400) than CCTA in detecting hemodynamic stenoses in patients with coronary artery disease (CAD).

CLINICAL RELEVANCE STATEMENT

Computed tomography-derived fractional flow reserve might be utilized to determine the necessity of invasive coronary angiography in coronary artery disease patients with coronary artery calcium score < 400.

KEY POINTS

• There is a lack of meta-analysis comparing the diagnostic performance of computed tomography-derived fractional flow reserve and coronary computed tomography angiography at different levels of calcification. • Computed tomography-derived fractional flow reserve only has a better diagnostic performance than coronary computed tomography angiography with low amounts of coronary calcium. • For the low coronary artery calcium score group, computed tomography-derived fractional flow reserve might be a good non-invasive method to detect hemodynamic stenoses in coronary artery disease patients.

The differences between patients with nonalcoholic fatty liver disease (NAFLD) and those without NAFLD, as well as predictors of functional coronary artery ischemia in patients with NAFLD

BACKGROUND

Nonalcoholic fatty liver disease (NAFLD) is a chronic liver disease associated with metabolic syndrome. It is the most common cause of cryptogenic cirrhosis. The disease is also involved in the occurrence and development of type 2 diabetes and atherosclerosis and can directly affect the outcome of patients with coronary heart disease. Therefore, the focus of treatment of nonalcoholic fatty liver disease has also begun to focus on the treatment of risk factors for atherosclerotic heart disease. In this study, we investigated the difference between patients with coronary artery stenosis combined with NAFLD and those without NAFLD and evaluated the predictive factors and value of functional coronary artery ischemia in patients with NAFLD.

HYPOTHESIS

Many clinical factors (such as age, BMI, hyperglycemia) and imaging parameters (such as CACS grade) in the NAFLD group were different from those in the non-NAFLD group. The predictive model combined with multiple influencing factors has a good value in predicting coronary artery ischemia in patients with NAFLD.

METHODS

We collected the clinical and imaging data of patients who underwent coronary computed tomography angiography and coronary artery calcification score (CACS) scans between January and June 2023. A total of 392 patients were included and divided into the NAFLD group and the non-NAFLD group. Based on CT fractional flow reserve (CT-FFR), patients with NAFLD were divided into CT-FFR ≤ 0.08 group and CT-FFR > 0.08 group.

RESULTS

Significant differences were observed between the non-NAFLD and NAFLD groups in terms of age, body mass index, hyperglycemia, hyperlipidemia, triglyceride, high-density lipoprotein, coronary artery disease-reporting and data system (CAD-RADS) classification, CACS classification, number of diseased coronary arteries, and CT-FFR ≤ 0.80 ratio (p < .05). The CAD-RADS and CACS classifications can independently predict functional coronary artery ischemia in NAFLD patients. The combined use of CAD-RADS and CACS classifications resulted in an area under the curve of 0.819 (95% confidence interval: 0.761-0.876) for predicting coronary artery ischemia in NAFLD patients, which was higher than the individual classification methods (CAD-RADS: 0.762, CACS: 0.742) (p = .000).

CONCLUSIONS

There are differences between patients with coronary artery stenosis and NAFLD and those without NAFLD. The CAD-RADS classification and CACS classification can economically and efficiently predict functional coronary artery ischemia in patients with NAFLD, which has crucial value in clinical diagnosis and treatment.

Machine learning based ischemia-specific stenosis prediction: A Chinese multicenter coronary CT angiography study

OBJECTIVES

To evaluate the performance of coronary computed tomography angiography (CCTA) derived characteristics including CT derived fractional flow reserve (CT-FFR) with FFR as a reference standard in identifying the lesion-specific ischemia by machine learning (ML) algorithms.

METHODS

The retrospective analysis enrolled 596 vessels in 462 patients (mean age, 61 years ± 11 [SD]; 71.4 % men) with suspected coronary artery disease who underwent CCTA and invasive FFR. The data were divided into training cohort, internal validation cohort, external validation cohorts 1 and 2 according to participating centers. All CCTA-derived parameters, which contained 10 qualitative and 33 quantitative plaque parameters, were collected to establish ML model. The Boruta and unsupervised clustering algorithm were implemented to select important and non-redundant parameters. Finally, the eight features with the highest mean importance were included for further ML model establishment and decision tree building. Five models were built to predict lesion-specific ischemia: stenosis degree from CCTA, CT-FFR, ΔCT-FFR, ML model and nested model.

RESULTS

Low-attenuation plaque, bend and lesion length were the main predictors of ischemia-specific lesions. Of 5 models, the ML model showed favorable discrimination for ischemia-specific lesions in the training and three validation sets (area under the curve [95 % confidence interval], 0.93 [0.90-0.96], 0.86 [0.79-0.94], 0.88 [0.83-0.94], and 0.90 [0.84-0.96], respectively). The nested model which combined the ML model and CT-FFR showed better diagnostic efficacy (AUC [95 %CI], 0.96 [0.94-0.99], 0.92 [0.86-0.99], 0.92 [0.86-0.99] and 0.94 [0.91-0.98], respectively; all P < 0.05), and net reclassification improvement (NRI) and integrated discrimination improvement (IDI) were significantly higher than CT-FFR alone.

CONCLUSIONS

Comprehensive CCTA-derived multiparameter model could better predict the ischemia-specific lesions by ML algorithms compared to stenosis degree from CTA, CT-FFR and ΔCT-FFR. Decision tree can be used to predict myocardial ischemia effectively.

Optimal Measurement Sites of Coronary-Computed Tomography Angiography-derived Fractional Flow Reserve: The Insight From China CT-FFR Study

OBJECTIVES

To investigate the optimal measurement site of coronary-computed tomography angiography-derived fractional flow reserve (FFR CT ) for the assessment of coronary artery disease (CAD) in the whole clinical routine practice.

MATERIALS AND METHODS

This retrospective multicenter study included 396 CAD patients who underwent coronary-computed tomography angiography, FFR CT , and invasive FFR. FFR CT was measured at 1 cm (FFR CT -1 cm), 2 cm (FFR CT -2 cm), 3 cm (FFR CT -3 cm), and 4 cm (FFR CT -4 cm) distal to coronary stenosis, respectively. FFR CT and invasive FFR ≤0.80 were defined as lesion-specific ischemia. The diagnostic performance of FFR CT to detect ischemia was obtained using invasive FFR as the reference standard. Reduced invasive coronary angiography rate and revascularization efficiency were calculated. After a median follow-up of 35 months in 267 patients for major adverse cardiovascular events (MACE), Cox hazard proportional models were performed with FFR CT values at each measurement site.

RESULTS

For discriminating lesion-specific ischemia, the areas under the curve of FFR CT -1 cm (0.91) as well as FFR CT -2 cm (0.91) were higher than those of FFR CT -3 cm (0.89) and FFR CT -4 cm (0.88), respectively (all P <0.05). The higher reduced invasive coronary angiography rate (81.6%) was found at FFR CT -1 cm than FFR CT -2 cm (81.6% vs. 62.6%, P <0.05). Revascularization efficiency did not differ between FFR CT -1 cm and FFR CT -2 cm (80.8% vs. 65.5%, P =0.019). In 12.4% (33/267) MACE occurred and only values of FFR CT -2 cm were independently predictive of MACE (hazard ratio: 0.957 [95% CI: 0.925-0.989]; P =0.010).

CONCLUSIONS

This study indicates FFR CT -2 cm is the optimal measurement site with superior diagnostic performance and independent prognostic role.

Coronary Computed Tomography Angiography-derived Fractional Flow Reserve: An Expert Consensus Document of Chinese Society of Radiology

Invasive fractional flow reserve (FFR) measured by a pressure wire is a reference standard for evaluating functional stenosis in coronary artery disease. Coronary computed tomography angiography-derived fractional flow reserve (CT-FFR) uses advanced computational analysis methods to noninvasively obtain FFR results from a single conventional coronary computed tomography angiography data to evaluate the hemodynamic significance of coronary artery disease. More and more evidence has found good correlation between the results of noninvasive CT-FFR and invasive FFR. CT-FFR has proven its potential in optimizing patient management, improving risk stratification and prognosis, and reducing total health care costs. However, there is still a lack of standardized interpretation of CT-FFR technology in real-world clinical settings. This expert consensus introduces the principle, workflow, and interpretation of CT-FFR; summarizes the state-of-the-art application of CT-FFR; and provides suggestions and recommendations for the application of CT-FFR with the aim of promoting the standardized application of CT-FFR in clinical practice.

Cardiovascular Imaging in China: Yesterday, Today, and Tomorrow

The high prevalence and mortality of cardiovascular diseases in China's large population has increased the use of cardiovascular imaging for the assessment of conditions in recent years. In this study, we review the past 20 years of cardiovascular imaging in China, the increasingly important role played by cardiovascular computed tomography in coronary artery disease and pulmonary embolism assessment, magnetic resonance imaging's use for cardiomyopathy assessment, the development and application of artificial intelligence in cardiovascular imaging, and the future of Chinese cardiovascular imaging.

Effect of 320-row CT reconstruction technology on fractional flow reserve derived from coronary CT angiography based on machine learning: single- versus multiple-cardiac periodic images

BACKGROUND

Fractional flow reserve derived from computed tomography (CT-FFR) can be used to noninvasively evaluate the functions of coronary arteries and has been widely welcomed in the field of cardiovascular research. However, whether different image reconstruction schemes have an effect on CT-FFR analysis through single- and multiple-cardiac periodic images in the same patient has not been investigated.

METHODS

This study retrospectively enrolled 122 patients who underwent 320-row computed tomography (CT) examination with both single- and multiple-cardiac periodic reconstruction schemes; a total of 366 coronary arteries were analyzed. The lowest CT-FFR values of each vessel and the poststenosis CT-FFR values of the lesion-specific coronary artery were measured using the two reconstruction techniques. The Wilcoxon signed-rank test was used to compare differences in CT-FFR values between the two reconstruction techniques. Spearman correlation analysis was performed to determine the relationship between CT-FFR values derived using the two methods. Bland-Altman and intraclass correlation coefficient (ICC) analyses were performed to evaluate the consistency of CT-FFR values.

RESULTS

In all blood vessels, the lowest CT-FFR values showed no significant differences between the two reconstruction techniques in the left anterior descending artery (LAD; P=0.65), left circumflex artery (LCx; P=0.46), or right coronary artery (RCA; P=0.22). In blood vessels with atherosclerotic plaques, the poststenosis CT-FFR values (2 cm distal to the maximum stenosis) exhibited no significant differences between the two reconstruction techniques in the LAD (P=0.78), LCx (P=1.00), or RCA (P=1.00). The mean CT-FFR values of single- and multiple-cardiac periodic images showed excellent correlation and minimal bias in all groups.

CONCLUSIONS

CT-FFR analysis based on an artificial intelligence deep learning neural network is stable and not affected by the type of 320-row CT reconstruction technology.

Functional CAD-RADS using FFRCT on therapeutic management and prognosis in patients with coronary artery disease

OBJECTIVES

To propose a novel functional Coronary Artery Disease-Reporting and Data System (CAD-RADS) category system integrated with coronary CT angiography (CCTA)-derived fractional flow reserve (FFR_CT) and to validate its effect on therapeutic decision and prognosis in patients with coronary artery disease (CAD).

METHODS

Firstly, we proposed a novel functional CAD-RADS and evaluated the performance of functional CAD-RADS for guiding treatment strategies with actual clinical treatment as a reference standard in a retrospective multicenter cohort with CCTA and invasive FFR performed in all patients (n = 466). Net reclassification improvement (NRI) of functional CAD-RADS over anatomical CAD-RADS was calculated. Secondly, the prognostic value of functional CAD-RADS in a prospective two-arm cohort (566 [FFR_CT arm] vs. 567 [CCTA arm]) was calculated, after a 1-year follow-up, functional CAD-RADS in FFR_CT arm (n = 513) and anatomical CAD-RADS in CCTA arm (n = 511) to determine patients at risk of adverse outcomes were compared with a Cox hazard proportional model.

RESULTS

Functional CAD-RADS demonstrated superior value over anatomical CAD-RADS (AUC: 0.828 vs. 0.681, p < 0.001) and comparable performance to FFR (AUC: 0.828 vs. 0.848, p = 0.253) in guiding therapeutic decisions. Functional CAD-RADS resulted in the revision of management plan as determined by anatomical CAD-RADS in 30.0% of patients (n = 140) (NRI = 0.369, p < 0.001). Functional CAD-RADS was an independent predictor for 1-year outcomes with indexes of concordance of 0.795 and the corresponding value was 0.751 in anatomical CAD-RADS.

CONCLUSION

The novel functional CAD-RADS gained incremental value in guiding therapeutic decision-making compared with anatomical CAD-RADS and comparable power in 1-year prognosis with anatomical CAD-RADS in a real-world scenario.

KEY POINTS

• The novel functional CAD-RADS category system with FFR_CT integrated into the anatomical CAD-RADS categories was originally proposed. • The novel functional CAD-RADS category system was validated superior value over anatomical CAD-RADS (AUC: 0.828 vs. 0.681, p < 0.001) in guiding therapeutic decisions and revised management plan in 30.0% of patients as determined by anatomical CAD-RADS (net reclassification improvement index = 0.369, p < 0.001). • Functional CAD-RADS was an independent predictor with an index of concordance of 0.795 and 0.751 in anatomical CAD-RADS for 1-year prognosis of adverse outcomes.

Current and Future Applications of Artificial Intelligence in Coronary Artery Disease

Cardiovascular diseases (CVDs) carry significant morbidity and mortality and are associated with substantial economic burden on healthcare systems around the world. Coronary artery disease, as one disease entity under the CVDs umbrella, had a prevalence of 7.2% among adults in the United States and incurred a financial burden of 360 billion US dollars in the years 2016–2017. The introduction of artificial intelligence (AI) and machine learning over the last two decades has unlocked new dimensions in the field of cardiovascular medicine. From automatic interpretations of heart rhythm disorders via smartwatches, to assisting in complex decision-making, AI has quickly expanded its realms in medicine and has demonstrated itself as a promising tool in helping clinicians guide treatment decisions. Understanding complex genetic interactions and developing clinical risk prediction models, advanced cardiac imaging, and improving mortality outcomes are just a few areas where AI has been applied in the domain of coronary artery disease. Through this review, we sought to summarize the advances in AI relating to coronary artery disease, current limitations, and future perspectives.

Artificial Intelligence Advances in the World of Cardiovascular Imaging

The tremendous advances in digital information and communication technology have entered everything from our daily lives to the most intricate aspects of medical and surgical care. These advances are seen in electronic and mobile health and allow many new applications to further improve and make the diagnoses of patient diseases and conditions more precise. In the area of digital radiology with respect to diagnostics, the use of advanced imaging tools and techniques is now at the center of evaluation and treatment. Digital acquisition and analysis are central to diagnostic capabilities, especially in the field of cardiovascular imaging. Furthermore, the introduction of artificial intelligence (AI) into the world of digital cardiovascular imaging greatly broadens the capabilities of the field both with respect to advancement as well as with respect to complete and accurate diagnosis of cardiovascular conditions. The application of AI in recognition, diagnostics, protocol automation, and quality control for the analysis of cardiovascular imaging modalities such as echocardiography, nuclear cardiac imaging, cardiovascular computed tomography, cardiovascular magnetic resonance imaging, and other imaging, is a major advance that is improving rapidly and continuously. We document the innovations in the field of cardiovascular imaging that have been brought about by the acceptance and implementation of AI in relation to healthcare professionals and patients in the cardiovascular field.

Influence of diabetes mellitus on the diagnostic performance of machine learning-based coronary CT angiography-derived fractional flow reserve: a multicenter study

OBJECTIVES

To examine the diagnostic accuracy of machine learning-based coronary CT angiography-derived fractional flow reserve (FFR_CT) in diabetes mellitus (DM) patients.

METHODS

In total, 484 patients with suspected or known coronary artery disease from 11 Chinese medical centers were retrospectively analyzed. All patients underwent CCTA, FFR_CT, and invasive FFR. The patients were further grouped into mild (25~49 %), moderate (50~69 %), and severe (≥ 70 %) according to CCTA stenosis degree and Agatston score < 400 and Agatston score ≥ 400 groups according to coronary artery calcium severity. Propensity score matching (PSM) was used to match DM (n  = 112) and non-DM (n  = 214) groups. Sensitivity, specificity, accuracy, and area under the curve (AUC) with 95 % confidence interval (CI) were calculated and compared.

RESULTS

Sensitivity, specificity, accuracy, and AUC of FFR_CT were 0.79, 0.96, 0.87, and 0.91 in DM patients and 0.82, 0.93, 0.89, and 0.89 in non-DM patients without significant difference (all p > 0.05) on a per-patient level. The accuracies of FFR_CT had no significant difference among different coronary stenosis subgroups and between two coronary calcium subgroups (all p > 0.05) in the DM and non-DM groups. After PSM grouping, the accuracies of FFR_CT were 0.88 in the DM group and 0.87 in the non-DM group without a statistical difference (p > 0.05).

CONCLUSIONS

DM has no negative impact on the diagnostic accuracy of machine learning-based FFR_CT.

KEY POINTS

• ML-based FFR_CT has a high discriminative accuracy of hemodynamic ischemia, which is not affected by DM. • FFR_CT was superior to the CCTA alone for the detection of ischemia relevance of coronary artery stenosis in both DM and non-DM patients. • Coronary calcification had no significant effect on the diagnostic accuracy of FFR_CT to detect ischemia in DM patients.

Effect of Coronary Calcification Severity on Measurements and Diagnostic Performance of CT-FFR With Computational Fluid Dynamics: Results From CT-FFR CHINA Trial

Aims: To explore the effect of coronary calcification severity on the measurements and diagnostic performance of computed tomography-derived fractional flow reserve (FFR; CT-FFR).

Methods: This study included 305 patients (348 target vessels) with evaluable coronary calcification (CAC) scores from CT-FFR CHINA clinical trial. The enrolled patients all received coronary CT angiography (CCTA), CT-FFR, and invasive FFR examinations within 7 days. On both per-patient and per-vessel levels, the measured values, accuracy, and diagnostic performance of CT-FFR in identifying hemodynamically significant lesions were analyzed in all CAC score groups (CAC = 0, > 0 to <100, ≥ 100 to <400, and ≥ 400), with FFR as reference standard.

Results: In total, the sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and area under receiver operating characteristics curve (AUC) of CT-FFR were 85.8, 88.7, 86.9, 87.8, 87.1%, 0.90 on a per-patient level and 88.3, 89.3, 89.5, 88.2, 88.9%, 0.88 on a per-vessel level, respectively. Absolute difference of CT-FFR and FFR values tended to elevate with increased CAC scores (CAC = 0: 0.09 ± 0.10; CAC > 0 to <100: 0.06 ± 0.06; CAC ≥ 100 to <400: 0.09 ± 0.10; CAC ≥ 400: 0.11 ± 0.13; p = 0.246). However, no statistically significant difference was found in patient-based and vessel-based diagnostic performance of CT-FFR among all CAC score groups.

Conclusion: This prospective multicenter trial supported CT-FFR as a viable tool in assessing coronary calcified lesions. Although large deviation of CT-FFR has a tendency to correlate with severe calcification, coronary calcification has no significant influence on CT-FFR diagnostic performance using the widely-recognized cut-off value of 0.8.

CT Assessment of Myocardial Perfusion and Fractional Flow Reserve in Coronary Artery Disease: A Review of Current Clinical Evidence and Recent Developments

Coronary computed tomography angiography (CCTA) is routinely used for anatomical assessment of coronary artery disease (CAD). However, invasive measurement of fractional flow reserve (FFR) is the current gold standard for the diagnosis of hemodynamically significant CAD. CT-derived FFRCT and CT perfusion are two emerging techniques that can provide a functional assessment of CAD for risk stratification and clinical decision making. Several clinical studies have shown that the diagnostic performance of concomitant CCTA and functional CT assessment for detecting hemodynamically significant CAD is at least non-inferior to that of other routinely used imaging modalities. This article aims to review the current clinical evidence and recent developments in functional CT techniques.

Artificial intelligence in coronary computed tomography angiography

Coronary computed tomography angiography (CCTA) is recommended as a frontline diagnostic tool in the non-invasive assessment of patients with suspected coronary artery disease (CAD) and cardiovascular risk stratification. To date, artificial intelligence (AI) techniques have brought major changes in the way that we make individualized decisions for patients with CAD. Applications of AI in CCTA have produced improvements in many aspects, including assessment of stenosis degree, determination of plaque type, identification of high-risk plaque, quantification of coronary artery calcium score, diagnosis of myocardial infarction, estimation of computed tomography-derived fractional flow reserve, left ventricular myocardium analysis, perivascular adipose tissue analysis, prognosis of CAD, and so on. The purpose of this review is to provide a comprehensive overview of current status of AI in CCTA.

Deep learning powered coronary CT angiography for detecting obstructive coronary artery disease: The effect of reader experience, calcification and image quality

OBJECTIVES

To investigate the effect of reader experience, calcification and image quality on the performance of deep learning (DL) powered coronary CT angiography (CCTA) in automatically detecting obstructive coronary artery disease (CAD) with invasive coronary angiography (ICA) as reference standard.

METHODS

A total of 165 patients (680 vessels and 1505 segments) were included in this study. Three sessions were performed in order: (1) The artificial intelligence (AI) software automatically processed CCTA images, stenosis degree and processing time were recorded for each case; (2) Six cardiovascular radiologists with different experiences (low/ intermediate/ high experience) independently performed image post-processing and interpretation of CCTA, (3) AI + human reading was performed. Luminal stenosis ≥50% was defined as obstructive CAD in ICA and CCTA. Diagnostic performances of AI, human reading and AI + human reading were evaluated and compared on a per-patient, per-vessel and per-segment basis with ICA as reference standard. The effects of calcification and image quality on the diagnostic performance were also studied.

RESULTS

The average post-processing and interpretation times of AI was 2.3 ± 0.6 min per case, reduced by 76%, 72%, 69% compared with low/ intermediate/ high experience readers (all P < 0.001), respectively. On a per-patient, per-vessel and per-segment basis, with ICA as reference method, the AI overall diagnostic sensitivity for detecting obstructive CAD were 90.5%, 81.4%, 72.9%, the specificity was 82.3%, 93.9%, 95.0%, with the corresponding areas under the curve (AUCs) of 0.90, 0.90, 0.87, respectively. Compared to human readers, the diagnostic performance of AI was higher than that of low experience readers (all P < 0.001). The diagnostic performance of AI + human reading was higher than human reading alone, and AI + human readers' ability to correctly reclassify obstructive CAD was also improved, especially for low experience readers (Per-patient, the net reclassification improvement (NRI) = 0.085; per-vessel, NRI = 0.070; and per-segment, NRI = 0.068, all P < 0.001). The diagnostic performance of AI was not significantly affected by calcification and image quality (all P > 0.05).

CONCLUSIONS

AI can substantially shorten the post-processing time, while AI + human reading model can significantly improve the diagnostic performance compared with human readers, especially for inexperienced readers, regardless of calcification severity and image quality.

Impact of coronary calcium score and lesion characteristics on the diagnostic performance of machine-learning-based computed tomography-derived fractional flow reserve

AIMS

To evaluate the impact of coronary artery calcium (CAC) score, minimal lumen area (MLA), and length of coronary artery stenosis on the diagnostic performance of the machine-learning-based computed tomography-derived fractional flow reserve (ML-FFR).

METHODS AND RESULTS

In 471 patients with coronary artery disease, computed tomography angiography (CTA) and invasive coronary angiography were performed with fractional flow reserve (FFR) in 557 lesions at a single centre. Diagnostic performances of ML-FFR, computational fluid dynamics-based CT-FFR (CFD-FFR), MLA, quantitative coronary angiography (QCA), and visual stenosis grading were evaluated using invasive FFR as a reference standard. Diagnostic performances were analysed according to lesion characteristics including the MLA, length of stenosis, CAC score, and stenosis degree. ML-FFR was obtained by automated feature selection and model building from quantitative CTA. A total of 272 lesions showed significant ischaemia, defined by invasive FFR ≤0.80. There was a significant correlation between CFD-FFR and ML-FFR (r = 0.99, P < 0.001). ML-FFR showed moderate sensitivity and specificity in the per-patient analysis. Diagnostic performances of CFD-FFR and ML-FFR did not decline in patients with high CAC scores (CAC > 400). Sensitivities of CFD-FFR and ML-FFR showed a downward trend along with the increase in lesion length and decrease in MLA. The area under the curve (AUC) of ML-FFR (0.73) was higher than those of QCA and visual grading (AUC = 0.65 for both, P < 0.001) and comparable to those of MLA (AUC = 0.71, P = 0.21) and CFD-FFR (AUC = 0.73, P = 0.86).

CONCLUSION

ML-FFR showed comparable results to MLA and CFD-FFR for the prediction of lesion-specific ischaemia. Specificities and accuracies of CFD-FFR and ML-FFR decreased with smaller MLA and long lesion length.