AI-based, automated chamber volumetry from gated, non-contrast CT.

BACKGROUND: Accurate chamber volumetry from gated, non-contrast cardiac CT (NCCT) scans can be useful for potential screening of heart failure. OBJECTIVES: To validate a new, fully automated, AI-based method for cardiac volume and myocardial mass quantification from NCCT scans compared to contrasted CT Angiography (CCTA). METHODS: Of a retrospectively collected cohort of 1051 consecutive patients, 420 patients had both NCCT and CCTA scans at mid-diastolic phase, excluding patients with cardiac devices. Ground truth values were obtained from the CCTA scans. RESULTS: The NCCT volume computation shows good agreement with ground truth values. Volume differences [95% CI ] and correlation coefficients were: -9.6 [-45; 26] mL, r â€‹= â€‹0.98 for LV Total, -5.4 [-24; 13] mL, r â€‹= â€‹0.95 for LA, -8.7 [-45; 28] mL, r â€‹= â€‹0.94 for RV, -5.2 [-27; 17] mL, r â€‹= â€‹0.92 for RA, -3.2 [-42; 36] mL, r â€‹= â€‹0.91 for LV blood pool, and -6.7 [-39; 26] g, r â€‹= â€‹0.94 for LV wall mass, respectively. Mean relative volume errors of less than 7% were obtained for all chambers. CONCLUSIONS: Fully automated assessment of chamber volumes from NCCT scans is feasible and correlates well with volumes obtained from contrast study.

Sex differences in machine learning computed tomography-derived fractional flow reserve.

Coronary computed tomography angiography (CCTA) derived machine learning fractional flow reserve (ML-FFRCT) can assess the hemodynamic significance of coronary artery stenoses. We aimed to assess sex differences in the association of ML-FFRCT and incident cardiovascular outcomes. We studied a retrospective cohort of consecutive patients who underwent clinically indicated CCTA and single photon emission computed tomography (SPECT). Obstructive stenosis was defined as ≥ 70% stenosis severity in non-left main vessels or ≥ 50% in the left main coronary. ML-FFRCT was computed using a machine learning algorithm with significant stenosis defined as ML-FFRCT < 0.8. The primary outcome was a composite of death or non-fatal myocardial infarction (D/MI). Our study population consisted of 471 patients with mean (SD) age 65 (13) years, 53% men, and multiple comorbidities (78% hypertension, 66% diabetes, 81% dyslipidemia). Compared to men, women were less likely to have obstructive stenosis by CCTA (9% vs. 18%; p = 0.006), less multivessel CAD (4% vs. 6%; p = 0.25), lower prevalence of ML-FFRCT < 0.8 (39% vs. 44%; p = 0.23) and higher median (IQR) ML-FFRCT (0.76 (0.53-0.86) vs. 0.71 (0.47-0.84); p = 0.047). In multivariable adjusted models, there was no significant association between ML-FFRCT < 0.8 and D/MI [Hazard Ratio 0.82, 95% confidence interval (0.30, 2.20); p = 0.25 for interaction with sex.]. In a high-risk cohort of symptomatic patients who underwent CCTA and SPECT testing, ML-FFRCT was higher in women than men. There was no significant association between ML-FFRCT and incident mortality or MI and no evidence that the prognostic value of ML-FFRCT differs by sex.

Interoperator reliability of an on-site machine learning-based prototype to estimate CT angiography-derived fractional flow reserve.

BACKGROUND: Advances in CT and machine learning have enabled on-site non-invasive assessment of fractional flow reserve (FFRCT). PURPOSE: To assess the interoperator and intraoperator variability of coronary CT angiography-derived FFRCT using a machine learning-based postprocessing prototype. MATERIALS AND METHODS: We included 60 symptomatic patients who underwent coronary CT angiography. FFRCT was calculated by two independent operators after training using a machine learning-based on-site prototype. FFRCT was measured 1 cm distal to the coronary plaque or in the middle of the segments if no coronary lesions were present. Intraclass correlation coefficient (ICC) and Bland-Altman analysis were used to evaluate interoperator variability effect in FFRCT estimates. Sensitivity analysis was done by cardiac risk factors, degree of stenosis and image quality. RESULTS: A total of 535 coronary segments in 60 patients were assessed. The overall ICC was 0.986 per patient (95% CI 0.977 to 0.992) and 0.972 per segment (95% CI 0.967 to 0.977). The absolute mean difference in FFRCT estimates was 0.012 per patient (95% CI for limits of agreement: -0.035 to 0.039) and 0.02 per segment (95% CI for limits of agreement: -0.077 to 0.080). Tight limits of agreement were seen on Bland-Altman analysis. Distal segments had greater variability compared with proximal/mid segments (absolute mean difference 0.011 vs 0.025, p<0.001). Results were similar on sensitivity analysis. CONCLUSION: A high degree of interoperator and intraoperator reproducibility can be achieved by on-site machine learning-based FFRCT assessment. Future research is required to evaluate the physiological relevance and prognostic value of FFRCT.

Fully Automated Artery-Specific Calcium Scoring Based on Machine Learning in Low-Dose Computed Tomography Screening.

PURPOSE: Evaluation of machine learning-based fully automated artery-specific coronary artery calcium (CAC) scoring software, using semi-automated software as a reference. METHODS: A total of 505 patients underwent non-contrast-enhanced calcium scoring computed tomography (CSCT). Automated, machine learning-based software quantified the Agatston score (AS), volume score (VS), and mass score (MS) of each coronary artery [right coronary artery (RCA), left main (LM), circumflex (CX) and left anterior descending (LAD)]. Identified CAC of readers who annotated the data with semi-automated software served as a reference standard. Statistics included comparisons of evaluation time, agreement of identified CAC, and comparisons of the AS, VS, and MS of the reference standard and the fully automated algorithm. RESULTS: The machine learning-based software correlated strongly with the reference standard for the AS, VS, and MS (Spearman's rho > 0.969) (p < 0.001), with excellent agreement (ICC > 0.919) (p < 0.001). The mean assessment time of the reference standard was 59 seconds (IQR 39-140) and that of the automated algorithm was 5.9 seconds (IQR 3.9-16) (p < 0.001). The Bland-Altman plots mean difference and 1.96 upper and lower limits of agreement for all arteries combined were: AS 0.996 (1.33 to 0.74), VS 0.995 (1.40 to 0.71), and MS 0.995 (1.35 to 0.74). The mean bias was minimal: 0.964-1.0429. Risk class assignment showed high accuracy for the AS in total (weighed κ = 0.99) and for each individual artery (κ = 0.96-0.99) with corresponding correct risk group assignment in 497 of 505 patients (98.4 %). CONCLUSION: The fully automated artery-specific coronary calcium scoring algorithm is a time-saving procedure and shows excellent correlation and agreement compared with the clinically established semi-automated approach. KEY POINTS: · Very high correlation and agreement between fully automatic and semi-automatic calcium scoring software.. · Less time-consuming than conventional semi-automatic methods.. · Excellent tool for artery-specific calcium scoring in a clinical setting.. CITATION FORMAT: · Winkelmann MT, Jacoby J, Schwemmer C et al. Fully Automated Artery-Specific Calcium Scoring Based on Machine Learning in Low-Dose Computed Tomography Screening. Fortschr Röntgenstr 2022; 194: 763 - 770.

Coronary CT Fractional Flow Reserve before Transcatheter Aortic Valve Replacement: Clinical Outcomes.

Background The role of CT angiography-derived fractional flow reserve (CT-FFR) in pre-transcatheter aortic valve replacement (TAVR) assessment is uncertain. Purpose To evaluate the predictive value of on-site machine learning-based CT-FFR for adverse clinical outcomes in candidates for TAVR. Materials and Methods This observational retrospective study included patients with severe aortic stenosis referred to TAVR after coronary CT angiography (CCTA) between September 2014 and December 2019. Clinical end points comprised major adverse cardiac events (MACE) (nonfatal myocardial infarction, unstable angina, cardiac death, or heart failure admission) and all-cause mortality. CT-FFR was obtained semiautomatically using an on-site machine learning algorithm. The ability of CT-FFR (abnormal if ≤0.75) to predict outcomes and improve the predictive value of the current noninvasive work-up was assessed. Survival analysis was performed, and the C-index was used to assess the performance of each predictive model. To compare nested models, the likelihood ratio χ2 test was performed. Results A total of 196 patients (mean age ± standard deviation, 75 years ± 11; 110 women [56%]) were included; the median time of follow-up was 18 months. MACE occurred in 16% (31 of 196 patients) and all-cause mortality in 19% (38 of 196 patients). Univariable analysis revealed CT-FFR was predictive of MACE (hazard ratio [HR], 4.1; 95% CI: 1.6, 10.8; P = .01) but not all-cause mortality (HR, 1.2; 95% CI: 0.6, 2.2; P = .63). CT-FFR was independently associated with MACE (HR, 4.0; 95% CI: 1.5, 10.5; P = .01) when adjusting for potential confounders. Adding CT-FFR as a predictor to models that include CCTA and clinical data improved their predictive value for MACE (P = .002) but not all-cause mortality (P = .67), and it showed good discriminative ability for MACE (C-index, 0.71). Conclusion CT angiography-derived fractional flow reserve was associated with major adverse cardiac events in candidates for transcatheter aortic valve replacement and improved the predictive value of coronary CT angiography assessment. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Choe in this issue.

Deep learning for vessel-specific coronary artery calcium scoring: validation on a multi-centre dataset.

AIMS: To present and validate a fully automated, deep learning (DL)-based branch-wise coronary artery calcium (CAC) scoring algorithm on a multi-centre dataset. METHODS AND RESULTS: We retrospectively included 1171 patients referred for a CAC computed tomography examination. Total CAC scores for each case were manually evaluated by a human reader. Next, each dataset was fully automatically evaluated by the DL-based software solution with output of the total CAC score and sub-scores per coronary artery (CA) branch [right coronary artery (RCA), left main (LM), left anterior descending (LAD), and circumflex (CX)]. Three readers independently manually scored the CAC for all CA branches for 300 cases from a single centre and formed the consensus using a majority vote rule, serving as the reference standard. Established CAC cut-offs for the total Agatston score were used for risk group assignments. The performance of the algorithm was evaluated using metrics for risk class assignment based on total Agatston score, and unweighted Cohen's Kappa for branch label assignment. The DL-based software solution yielded a class accuracy of 93% (1085/1171) with a sensitivity, specificity, and accuracy of detecting non-zero coronary calcium being 97%, 93%, and 95%. The overall accuracy of the algorithm for branch label classification was 94% (LM: 89%, LAD: 91%, CX: 93%, RCA: 100%) with a Cohen's kappa of k = 0.91. CONCLUSION: Our results demonstrate that fully automated total and vessel-specific CAC scoring is feasible using a DL-based algorithm. There was a high agreement with the manually assessed total CAC from a multi-centre dataset and the vessel-specific scoring demonstrated consistent and reproducible results.

Prognostic Value of Computed Tomography-Derived Fractional Flow Reserve Comparison With Myocardial Perfusion Imaging.

OBJECTIVES: The aim of this study was to compare the incremental prognostic value of coronary computed tomography (CT) angiography (CCTA)-derived machine learning fractional flow reserve CT (ML-FFRct) versus that of ischemia detected on single-photon emission-computed tomography (SPECT) myocardial perfusion imaging (MPI) on incident cardiovascular outcomes. BACKGROUND: SPECT MPI and ML-FFRct are noninvasive tools that can assess the hemodynamic significance of coronary atherosclerotic disease. METHODS: We studied a retrospective cohort of consecutive patients who underwent clinically indicated CCTA and SPECT MPI. ML-FFRct was computed using a ML prototype. The primary outcome was all-cause mortality and nonfatal myocardial infarction (D/MI), and the secondary outcome was D/MI and unplanned revascularization, percutaneous coronary intervention (PCI) or coronary artery bypass graft (CABG) occurring more than 90 days postimaging. Multiple nested multivariate cox regression was used to model a scenario wherein an initial anatomical assessment was followed by a functional assessment. RESULTS: A total of 471 patients (mean age: 64 ± 13 year; 53% males) were included. Comorbidities were prevalent (78% hypertension, 66% diabetes, 81% dyslipidemia). ML-FFRct was <0.8 in at least 1 proximal/midsegment was present in 41.6% of patients, and ischemia on MPI was present in 13.8%. After a median follow-up of 18 months, 7% of patients (n = 33) experienced D/MI. On multivariate Cox proportional analysis, the presence of ischemia on MPI but not ML-FFRct significantly predicted D/MI (HR: 2.3; 95% CI: 1.0-5.0; P = 0.047; or HR: 0.7; 95% CI: 0.3-1.4; P = 0.306 respectively) when added to CCTA obstructive stenosis. Furthermore, the model with SPECT ischemia had higher global chi-square result and significantly improved reclassification. Results were similar using the secondary outcome and on several sensitivity analyses. CONCLUSIONS: In a high-risk patient cohort, SPECT MPI but not ML-FFRct adds independent and incremental prognostic information to CCTA-based anatomical assessment and clinical risk factors in predicting incident outcomes.

Machine Learning and Coronary Artery Calcium Scoring.

PURPOSE OF REVIEW: To summarize current artificial intelligence (AI)-based applications for coronary artery calcium scoring (CACS) and their potential clinical impact. RECENT FINDINGS: Recent evolution of AI-based technologies in medical imaging has accelerated progress in CACS performed in diverse types of CT examinations, providing promising results for future clinical application in this field. CACS plays a key role in risk stratification of coronary artery disease (CAD) and patient management. Recent emergence of AI algorithms, particularly deep learning (DL)-based applications, have provided considerable progress in CACS. Many investigations have focused on the clinical role of DL models in CACS and showed excellent agreement between those algorithms and manual scoring, not only in dedicated coronary calcium CT but also in coronary CT angiography (CCTA), low-dose chest CT, and standard chest CT. Therefore, the potential of AI-based CACS may become more influential in the future.

A fully automated software platform for structural mitral valve analysis.

OBJECTIVE: To evaluate a novel fully automated mitral valve analysis software platform for cardiac computer tomography angiography (CCTA)-based structural heart therapy procedure planning. METHODS: The study included 52 patients (25 women; mean age, 66.9 ± 12.4 years) who had undergone CCTA prior to transcatheter mitral valve replacement (TMVR) or surgical mitral valve intervention (replacement or repair). Therapeutically relevant mitral valve annulus parameters (projected area, circumference, trigone-to-trigone (T-T) distance, anterior-posterior (AP) diameter, and anterolateral-posteromedial (AL-PM) diameter) were measured. Results of the fully automated mitral valve analysis software platform with and without manual adjustments were compared with the reference standard of a user-driven measurement program (3mensio, Pie Medical Imaging). Measurements were compared between the fully automated software, both with and without manual adjustment, and the user-driven program using intraclass correlation coefficients (ICC). A secondary analysis included the time to obtain all measurements. RESULTS: Fully automated measurements showed a good to excellent agreement (circumference, ICC = 0.70; projected area, ICC = 0.81; T-T distance, ICC = 0.64; AP, ICC = 0.62; and AL-PM diameter, ICC = 0.78) compared with the user-driven analysis. There was an excellent agreement between fully automated measurement with manual adjustments and user-driven analysis regarding circumference (ICC = 0.91), projected area (ICC = 0.93), T-T distance (ICC = 0.80), AP (ICC = 0.78), and AL-PM diameter (ICC = 0.79). The time required for mitral valve analysis was significantly lower using the fully automated software with manual adjustments compared with the standard assessment (134.4 ± 36.4 s vs. 304.3 ± 77.7 s) (p < 0.01). CONCLUSION: The fully automated mitral valve analysis software, when combined with manual adjustments, demonstrated a strong correlation compared with the user-driven software while reducing the total time required for measurement. KEY POINTS: • The novel software platform allows for a fully automated analysis of mitral valve structures. • An excellent agreement was found between the fully automated measurement with manual adjustments and the user-driven analysis. • The software showed quicker measurement time compared with the standard analysis of the mitral valve.

Multimodal Multiparametric Three-dimensional Image Fusion in Coronary Artery Disease: Combining the Best of Two Worlds.

PURPOSE: To allow for comprehensive noninvasive diagnostics of coronary artery disease (CAD) by using three-dimensional (3D) image fusion of CT coronary angiography, CT-derived fractional flow reserve (CT FFR), whole-heart dynamic 3D cardiac MRI perfusion, and 3D cardiac MRI late gadolinium enhancement (LGE). MATERIALS AND METHODS: Seventeen patients (54 years ± 10 [standard deviation], one female) who underwent cardiac CT and cardiac MRI were included (combined subcohort of three prospective trials). Software facilitating multimodal 3D image fusion was developed. Postprocessing of CT data included segmentation of the coronary tree and heart contours, calculation of CT FFR values, and color coding of the coronary tree according to CT FFR. Postprocessing of cardiac MRI data included segmentation of the left ventricle (LV) in cardiac MRI perfusion and cardiac MRI LGE, co-registration of cardiac MRI to CT data, and projection of cardiac MRI perfusion and LGE values onto the high spatial resolution LV from CT. RESULTS: Image quality was rated as good to excellent (scores: 2.5-2.6; 3 = excellent). CT coronary angiography revealed significant stenoses in seven of 17 cases (41%). CT FFR was possible in 16 of 17 cases (94%) and showed pathologic flow in seven of 17 cases (41%), six of which coincided with cases revealing significant stenoses at CT coronary angiography. Cardiac MRI perfusion identified eight of 17 patients (47%) with hypoperfusion (ischemic burden of 17% ± 5). Cardiac MRI LGE showed myocardial scar in three of 17 cases (18%, scar burden of 7% ± 4). Conventional two-dimensional readout of CT coronary angiography and cardiac MRI resulted in eight of 17 cases (47%) with uncertain findings. Most of these divergent findings could be solved when adding information from CT FFR and 3D image fusion (six of eight, 75%). CONCLUSION: Multimodal 3D cardiac image fusion is feasible and may help with comprehensive noninvasive CAD diagnostics.Supplemental material is available for this article.© RSNA, 2020.

Association of Serum Lipid Profile With Coronary Computed Tomographic Angiography-derived Morphologic and Functional Quantitative Plaque Markers.

PURPOSE: Recent advances in image quality of coronary computed tomographic angiography (cCTA) have enabled improved characterization of coronary plaques. Thus, we investigated the association between quantitative morphological plaque markers obtained by cCTA and serum lipid levels in patients with suspected or known coronary artery disease. MATERIALS AND METHODS: We retrospectively analyzed data of 119 statin-naive patients (55±14 y, 66% men) who underwent clinically indicated cCTA between January 2013 and February 2017. Patients were subdivided into a plaque and a no-plaque group. Quantitative and morphologic plaque markers, such as segment involvement score, segment stenosis score, remodeling index, napkin-ring sign, total plaque volume, calcified plaque volume, and noncalcified plaque volume (NCPV) and plaque composition, were analyzed using a semiautomated plaque software prototype. Total cholesterol, low-density lipoprotein (LDL), high-density lipoprotein, low-density lipoprotein/high-density lipoprotein ratio, and triglycerides were determine in both groups. RESULTS: Higher age (61±11 y vs. 52±14 y, P<0.0001) and a higher likelihood of male gender (77% vs. 56%, P<0.0001) were observed in the plaque group. Differences in lipid levels were neither observed for differentiation between plaque presence or absence, nor after subcategorization for plaque composition. LDL serum levels >160 mg/dL correlated with higher NCPV compared with patients with LDL between 100 and 160 mg/dL (112 vs. 27 mm, P=0.037). Other markers were comparable between the different groups. CONCLUSION: Statin-naive patients with known or suspected coronary artery disease did not show differences in lipid levels related to plaque composition by cCTA. Patients with plaques tended to be men and were significantly older. High LDL levels correlated with high NCPV.

Diagnostic Accuracy of a Machine-Learning Approach to Coronary Computed Tomographic Angiography-Based Fractional Flow Reserve: Result From the MACHINE Consortium.

BACKGROUND: Coronary computed tomographic angiography (CTA) is a reliable modality to detect coronary artery disease. However, CTA generally overestimates stenosis severity compared with invasive angiography, and angiographic stenosis does not necessarily imply hemodynamic relevance when fractional flow reserve (FFR) is used as reference. CTA-based FFR (CT-FFR), using computational fluid dynamics (CFD), improves the correlation with invasive FFR results but is computationally demanding. More recently, a new machine-learning (ML) CT-FFR algorithm has been developed based on a deep learning model, which can be performed on a regular workstation. In this large multicenter cohort, the diagnostic performance ML-based CT-FFR was compared with CTA and CFD-based CT-FFR for detection of functionally obstructive coronary artery disease. METHODS AND RESULTS: At 5 centers in Europe, Asia, and the United States, 351 patients, including 525 vessels with invasive FFR comparison, were included. ML-based and CFD-based CT-FFR were performed on the CTA data, and diagnostic performance was evaluated using invasive FFR as reference. Correlation between ML-based and CFD-based CT-FFR was excellent (R=0.997). ML-based (area under curve, 0.84) and CFD-based CT-FFR (0.84) outperformed visual CTA (0.69; P<0.0001). On a per-vessel basis, diagnostic accuracy improved from 58% (95% confidence interval, 54%-63%) by CTA to 78% (75%-82%) by ML-based CT-FFR. The per-patient accuracy improved from 71% (66%-76%) by CTA to 85% (81%-89%) by adding ML-based CT-FFR as 62 of 85 (73%) false-positive CTA results could be correctly reclassified by adding ML-based CT-FFR. CONCLUSIONS: On-site CT-FFR based on ML improves the performance of CTA by correctly reclassifying hemodynamically nonsignificant stenosis and performs equally well as CFD-based CT-FFR.

Aortic root evaluation prior to transcatheter aortic valve implantation-Correlation of manual and semi-automatic measurements.

BACKGROUND: Pre-procedural TAVI planning requires highly sophisticated and time-consuming manual measurements performed by experienced readers. Semi-automatic software may assist with partial automation of assessment of multiple parameters. The aim of this study was to evaluate differences between manual and semi-automatic measurements in terms of agreement and time. METHODS: One hundred and twenty TAVI candidates referred for the retrospectively ECG-gated CTA (2nd and 3rd generation dual source CT) were evaluated. Fully manual and semi-automatic measurements of fourteen aortic root parameters were assessed in the 20% phase of the R-R interval. Reading time was compared using paired samples t-test. Inter-software agreement was calculated using the Intraclass correlation coefficient (ICC) in a 2-way mixed effects model. Differences between manual and semi-automatic measurements were evaluated using Bland-Altman analysis. RESULTS: The time needed for evaluation using semi-automatic assessment (3 min 24 s ± 1 min 7 s) was significantly lower (p<0.001) compared to a fully manual approach (6 min 31 sec ± 1 min 1 sec). Excellent inter-software agreement was found (ICC = 0.93 ± 0.0; range:0.90-0.95). The same prosthesis size from manual and semi-automatic measurements was selected in 92% of cases, when sizing was based on annular area. Prosthesis sizing based on annular short diameter and perimeter agreed in 99% and 96% cases, respectively. CONCLUSION: Use of semi-automatic software in pre-TAVI evaluation results in comparable results in respect of measurements and selected valve prosthesis size, while necessary reading time is significantly lower.

Coronary CT Angiography-derived Fractional Flow Reserve: Machine Learning Algorithm versus Computational Fluid Dynamics Modeling.

Purpose To compare two technical approaches for determination of coronary computed tomography (CT) angiography-derived fractional flow reserve (FFR)-FFR derived from coronary CT angiography based on computational fluid dynamics (hereafter, FFRCFD) and FFR derived from coronary CT angiography based on machine learning algorithm (hereafter, FFRML)-against coronary CT angiography and quantitative coronary angiography (QCA). Materials and Methods A total of 85 patients (mean age, 62 years ± 11 [standard deviation]; 62% men) who had undergone coronary CT angiography followed by invasive FFR were included in this single-center retrospective study. FFR values were derived on-site from coronary CT angiography data sets by using both FFRCFD and FFRML. The performance of both techniques for detecting lesion-specific ischemia was compared against visual stenosis grading at coronary CT angiography, QCA, and invasive FFR as the reference standard. Results On a per-lesion and per-patient level, FFRML showed a sensitivity of 79% and 90% and a specificity of 94% and 95%, respectively, for detecting lesion-specific ischemia. Meanwhile, FFRCFD resulted in a sensitivity of 79% and 89% and a specificity of 93% and 93%, respectively, on a per-lesion and per-patient basis (P = .86 and P = .92). On a per-lesion level, the area under the receiver operating characteristics curve (AUC) of 0.89 for FFRML and 0.89 for FFRCFD showed significantly higher discriminatory power for detecting lesion-specific ischemia compared with that of coronary CT angiography (AUC, 0.61) and QCA (AUC, 0.69) (all P < .0001). Also, on a per-patient level, FFRML (AUC, 0.91) and FFRCFD (AUC, 0.91) performed significantly better than did coronary CT angiography (AUC, 0.65) and QCA (AUC, 0.68) (all P < .0001). Processing time for FFRML was significantly shorter compared with that of FFRCFD (40.5 minutes ± 6.3 vs 43.4 minutes ± 7.1; P = .042). Conclusion The FFRML algorithm performs equally in detecting lesion-specific ischemia when compared with the FFRCFD approach. Both methods outperform accuracy of coronary CT angiography and QCA in the detection of flow-limiting stenosis.

Comparison of invasively measured FFR with FFR derived from coronary CT angiography for detection of lesion-specific ischemia: Results from a PC-based prototype algorithm.

BACKGROUND: We evaluated the diagnostic accuracy of a novel prototype for on-site determination of CT-based FFR (cFFR) on a standard personal computer (PC) compared to invasively measured FFR in patients with suspected coronary artery disease. METHODS: A total of 91 vessels in 71 patients (mean age 65 ±â€¯9 years) in whom coronary CT angiography had been performed due to suspicion of coronary artery disease, and who subsequently underwent invasive coronary angiography with FFR measurement were analyzed. For both cFFR and FFR, a threshold of ≤0.80 was used to indicate a hemodynamically relevant stenosis. The mean time needed to calculate cFFR was 12.4 ±â€¯3.4 min. A very close correlation between cFFR and FFR could be shown (r = 0.85; p < 0.0001) with Bland-Altman analysis showing moderate agreement between FFR and cFFR with mild systematic overestimation of FFR values in CT (mean difference 0.0049, 95% limits of agreement ±2SD -0.007 to 0.008). Compared to FFR, the sensitivity of cFFR to detect hemodynamically significant lesions was 91% (19/21, 95% CI: 70%-99%), specificity was 96% (67/70, 95% CI: 88%-99%), positive predictive value 86% (95% CI: 65%-97%) and negative predictive value was 97% (95% CI: 90%-100%) with an accuracy of 93%. CONCLUSION: cFFR obtained using an on-site algorithm implemented on a standard PC shows high diagnostic accuracy to detect lesions causing ischemia as compared to FFR. Importantly, the time needed for analysis is short which may be useful for improving clinical workflow.

A machine-learning approach for computation of fractional flow reserve from coronary computed tomography.

Fractional flow reserve (FFR) is a functional index quantifying the severity of coronary artery lesions and is clinically obtained using an invasive, catheter-based measurement. Recently, physics-based models have shown great promise in being able to noninvasively estimate FFR from patient-specific anatomical information, e.g., obtained from computed tomography scans of the heart and the coronary arteries. However, these models have high computational demand, limiting their clinical adoption. In this paper, we present a machine-learning-based model for predicting FFR as an alternative to physics-based approaches. The model is trained on a large database of synthetically generated coronary anatomies, where the target values are computed using the physics-based model. The trained model predicts FFR at each point along the centerline of the coronary tree, and its performance was assessed by comparing the predictions against physics-based computations and against invasively measured FFR for 87 patients and 125 lesions in total. Correlation between machine-learning and physics-based predictions was excellent (0.9994, P < 0.001), and no systematic bias was found in Bland-Altman analysis: mean difference was -0.00081 ± 0.0039. Invasive FFR ≤ 0.80 was found in 38 lesions out of 125 and was predicted by the machine-learning algorithm with a sensitivity of 81.6%, a specificity of 83.9%, and an accuracy of 83.2%. The correlation was 0.729 (P < 0.001). Compared with the physics-based computation, average execution time was reduced by more than 80 times, leading to near real-time assessment of FFR. Average execution time went down from 196.3 ± 78.5 s for the CFD model to ∼2.4 ± 0.44 s for the machine-learning model on a workstation with 3.4-GHz Intel i7 8-core processor.

Interventional heart wall motion analysis with cardiac C-arm CT systems.

Today, quantitative analysis of three-dimensional (3D) dynamics of the left ventricle (LV) cannot be performed directly in the catheter lab using a current angiographic C-arm system, which is the workhorse imaging modality for cardiac interventions. Therefore, myocardial wall analysis is completely based on the 2D angiographic images or pre-interventional 3D/4D imaging. In this paper, we present a complete framework to study the ventricular wall motion in 4D (3D+t) directly in the catheter lab. From the acquired 2D projection images, a dynamic 3D surface model of the LV is generated, which is then used to detect ventricular dyssynchrony. Different quantitative features to evaluate LV dynamics known from other modalities (ultrasound, magnetic resonance imaging) are transferred to the C-arm CT data. We use the ejection fraction, the systolic dyssynchrony index a 3D fractional shortening and the phase to maximal contraction (ϕi, max) to determine an indicator of LV dyssynchrony and to discriminate regionally pathological from normal myocardium. The proposed analysis tool was evaluated on simulated phantom LV data with and without pathological wall dysfunctions. The LV data used is publicly available online at https://conrad.stanford.edu/data/heart. In addition, the presented framework was tested on eight clinical patient data sets. The first clinical results demonstrate promising performance of the proposed analysis tool and encourage the application of the presented framework to a larger study in clinical practice.