Evaluation of an AI-based, automatic coronary artery calcium scoring software.

OBJECTIVES: To evaluate an artificial intelligence (AI)-based, automatic coronary artery calcium (CAC) scoring software, using a semi-automatic software as a reference. METHODS: This observational study included 315 consecutive, non-contrast-enhanced calcium scoring computed tomography (CSCT) scans. A semi-automatic and an automatic software obtained the Agatston score (AS), the volume score (VS), the mass score (MS), and the number of calcified coronary lesions. Semi-automatic and automatic analysis time were registered, including a manual double-check of the automatic results. Statistical analyses were Spearman's rank correlation coefficient (⍴), intra-class correlation (ICC), Bland Altman plots, weighted kappa analysis (κ), and Wilcoxon signed-rank test. RESULTS: The correlation and agreement for the AS, VS, and MS were ⍴ = 0.935, 0.932, 0.934 (p < 0.001), and ICC = 0.996, 0.996, 0.991, respectively (p < 0.001). The correlation and agreement for the number of calcified lesions were ⍴ = 0.903 and ICC = 0.977 (p < 0.001), respectively. The Bland Altman mean difference and 1.96 SD upper and lower limits of agreements for the AS, VS, and MS were - 8.2 (- 115.1 to 98.2), - 7.4 (- 93.9 to 79.1), and - 3.8 (- 33.6 to 25.9), respectively. Agreement in risk category assignment was 89.5% and κ = 0.919 (p < 0.001). The median time for the semi-automatic and automatic method was 59 s (IQR 35-100) and 36 s (IQR 29-49), respectively (p < 0.001). CONCLUSIONS: There was an excellent correlation and agreement between the automatic software and the semi-automatic software for three CAC scores and the number of calcified lesions. Risk category classification was accurate but showing an overestimation bias tendency. Also, the automatic method was less time-demanding. KEY POINTS: • Coronary artery calcium (CAC) scoring is an excellent candidate for artificial intelligence (AI) development in a clinical setting. • An AI-based, automatic software obtained CAC scores with excellent correlation and agreement compared with a conventional method but was less time-consuming.

Effect of Tube Voltage on Diagnostic Performance of Fractional Flow Reserve Derived From Coronary CT Angiography With Machine Learning: Results From the MACHINE Registry.

OBJECTIVE. Coronary CT angiography (CCTA)-based methods allow noninvasive estimation of fractional flow reserve (cFFR), recently through use of a machine learning (ML) algorithm (cFFRML). However, attenuation values vary according to the tube voltage used, and it has not been shown whether this significantly affects the diagnostic performance of cFFR and cFFRML. Therefore, the purpose of this study is to retrospectively evaluate the effect of tube voltage on the diagnostic performance of cFFRML. MATERIALS AND METHODS. A total of 525 coronary vessels in 351 patients identified in the MACHINE consortium registry were evaluated in terms of invasively measured FFR and cFFRML. CCTA examinations were performed with a tube voltage of 80, 100, or 120 kVp. For each tube voltage value, correlation (assessed by Spearman rank correlation coefficient), agreement (evaluated by intraclass correlation coefficient and Bland-Altman plot analysis), and diagnostic performance (based on ROC AUC value, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy) of the cFFRML in terms of detection of significant stenosis were calculated. RESULTS. For tube voltages of 80, 100, and 120 kVp, the Spearman correlation coefficient for cFFRML in relation to the invasively measured FFR value was ρ = 0.684, ρ = 0.622, and ρ = 0.669, respectively (p < 0.001 for all). The corresponding intraclass correlation coefficient was 0.78, 0.76, and 0.77, respectively (p < 0.001 for all). Sensitivity was 100.0%, 73.5%, and 85.0%, and specificity was 76.2%, 79.0%, and 72.8% for tube voltages of 80, 100, and 120 kVp, respectively. The ROC AUC value was 0.90, 0.82, and 0.80 for 80, 100, and 120 kVp, respectively (p < 0.001 for all). CONCLUSION. CCTA-derived cFFRML is a robust method, and its performance does not vary significantly between examinations performed using tube voltages of 100 kVp and 120 kVp. However, because of rapid advancements in CT and postprocessing technology, further research is needed.

Long-term prognostic value of coronary computed tomography angiography in chest pain patients.

BACKGROUND: Coronary computed tomography angiography (CCTA) is increasingly used to detect coronary artery disease (CAD), but long-term follow-up studies are still scarce. PURPOSE: To evaluate the prognostic value of CCTA in patients with suspected CAD. MATERIAL AND METHODS: A total of 1205 consecutive CCTA patients with chest pain were classified as normal coronary arteries, non-obstructive CAD, or obstructive CAD. The primary outcome was major adverse cardiac event (MACE), defined as a composite outcome including cardiac death, myocardial infarction, unstable angina pectoris, or late revascularization (after >90 days). RESULTS: Over 7.5 years follow-up (median = 3.1 years), Kaplan-Meier estimates demonstrated a MACE in 1.0%, 4.6%, and 20.7% in normal coronary arteries, non-obstructive CAD, and obstructive CAD, respectively. Log rank test for pairwise comparisons showed significant differences between non-obstructive CAD and normal coronary arteries ( P = 0.023) and between obstructive CAD and normal coronary arteries ( P < 0.001). In a multivariable analysis, adjusting for classical risk factors, non-obstructive CAD and obstructive CAD were independent predictors of MACE, with hazard ratios (HR) of 3.22 ( P = 0.041) and 25.18 ( P < 0.001), respectively. CONCLUSION: Patients with normal coronary arteries have excellent long-term prognosis, but the risk for MACE increases with non-obstructive and obstructive CAD. Both non-obstructive and obstructive CAD are independently associated with future ischemic events.

Software-based on-site estimation of fractional flow reserve using standard coronary CT angiography data.

BACKGROUND: The significance of a coronary stenosis can be determined by measuring the fractional flow reserve (FFR) during invasive coronary angiography. Recently, methods have been developed which claim to be able to estimate FFR using image data from standard coronary computed tomography angiography (CCTA) exams. PURPOSE: To evaluate the accuracy of non-invasively computed fractional flow reserve (cFFR) from CCTA. MATERIAL AND METHODS: A total of 23 vessels in 21 patients who had undergone both CCTA and invasive angiography with FFR measurement were evaluated using a cFFR software prototype. The cFFR results were compared to the invasively obtained FFR values. Correlation was calculated using Spearman's rank correlation, and agreement using intraclass correlation coefficient (ICC). Sensitivity, specificity, accuracy, negative predictive value, and positive predictive value for significant stenosis (defined as both FFR ≤0.80 and FFR ≤0.75) were calculated. RESULTS: The mean cFFR value for the whole group was 0.81 and the corresponding mean invFFR value was 0.84. The cFFR sensitivity for significant stenosis (FFR ≤0.80/0.75) on a per-lesion basis was 0.83/0.80, specificity was 0.76/0.89, and accuracy 0.78/0.87. The positive predictive value was 0.56/0.67 and the negative predictive value was 0.93/0.94. The Spearman rank correlation coefficient was ρ = 0.77 (P < 0.001) and ICC = 0.73 (P < 0.001). CONCLUSION: This particular CCTA-based cFFR software prototype allows for a rapid, non-invasive on-site evaluation of cFFR. The results are encouraging and cFFR may in the future be of help in the triage to invasive coronary angiography.

Can segmented 3D images be used for stenosis evaluation in coronary CT angiography?

BACKGROUND: Thanks to the development of computed tomography (CT) scanners and computer software, accurate coronary artery segmentation can be achieved with minimum user interaction. However, the question remains whether we can use these segmented images for reliable diagnosis. PURPOSE: To retrospectively evaluate the diagnostic accuracy of coronary CT angiography (CCTA) using segmented 3D data for the detection of significant stenosis. MATERIAL AND METHODS: CCTA data-sets from 30 patients were acquired with a 64-slice CT scanner and segmented using the region growing (RG) method and the "virtual contrast injection" (VC) method. Three types of images of each patient were reviewed by different reviewers for the presence of stenosis with diameter reduction of 50% or more. The evaluation was performed on four main arteries of each patient (120 arteries in total). For the original series, the reviewer was allowed to use all the 2D and 3D visualization tools available (conventional method). For the segmented results from RG and VC, only maximum intensity projection was used. Evaluation results were compared with catheter angiography (CA) for each artery in a blinded fashion. RESULTS: Overall, 34 arteries with significant stenosis were identified by CA. The percentage of evaluable arteries, accuracy and negative predictive value for detecting stenosis were, respectively, 86%, 74%, and 93% for the conventional method, 83%, 71%, and 92% for VC, and 64%, 56%, and 93% for RG. Accuracy was significantly lower for the RG method than for the other two methods (P < 0.01), whereas there was no significant difference in accuracy between the VC method and the conventional method (P = 0.22). CONCLUSION: The diagnostic accuracy for the RG-segmented 3D data is lower than those with access to 2D images, whereas the VC method shows diagnostic accuracy similar to the conventional method.

The efficacy of 2D, non-linear noise reduction filtering in cardiac imaging: a pilot study.

BACKGROUND: Computed tomography (CT) is becoming increasingly popular as a non-invasive method for visualizing the coronary arteries but patient radiation doses are still an issue. Postprocessing filters such as 2D adaptive non-linear filters might help to reduce the dose without loss of image quality. PURPOSE: To investigate whether the use of a 2D, non-linear adaptive noise reduction filter can improve image quality in cardiac computed tomography angiography (CCTA). MATERIAL AND METHODS: CCTA examinations were performed in 36 clinical patients on a dual source CT using two patient dose levels: maximum dose during diastole and reduced dose (20% of maximum dose) during systole. One full-dose and one reduced-dose image were selected from each of the examinations. The reduced-dose image was duplicated and one copy postprocessed using a 2D non-linear adaptive noise reduction filter, resulting in three images per patient. Image quality was assessed using visual grading with three criteria from the European guidelines for assessment of image quality and two additional criteria regarding the left main artery and the overall image quality. Also, the HU value and its standard deviation were measured in the ascending and descending aorta. Data were analyzed using Visual Grading Regression and paired t-test. RESULT: For all five criteria, there was a significant (P < 0.01 or better) improvement in perceived image quality when comparing postprocessed low-dose images with low-dose images without noise reduction. Comparing full dose images with postprocessed low-dose images resulted in a considerably larger, significant (P < 0.001) difference. Also, there was a significant reduction of the standard deviation of the HU values in the ascending and descending aorta when comparing postprocessed low-dose images with low-dose images without postprocessing. CONCLUSION: Even with an 80% dose reduction, there was a significant improvement in the perceived image quality when using a 2D noise-reduction filter, though not approaching the quality of full-dose images. This indicates that cardiac CT examinations could benefit from noise-reducing postprocessing with 2D non-linear adaptive filters.

Influence of coronary stenosis location on diagnostic performance of machine learning-based fractional flow reserve from CT angiography.

BACKGROUND: Compared with invasive fractional flow reserve (FFR), coronary CT angiography (cCTA) is limited in detecting hemodynamically relevant lesions. cCTA-based FFR (CT-FFR) is an approach to overcome this insufficiency by use of computational fluid dynamics. Applying recent innovations in computer science, a machine learning (ML) method for CT-FFR derivation was introduced and showed improved diagnostic performance compared to cCTA alone. We sought to investigate the influence of stenosis location in the coronary artery system on the performance of ML-CT-FFR in a large, multicenter cohort. METHODS: Three hundred and thirty patients (75.2% male, median age 63 years) with 502 coronary artery stenoses were included in this substudy of the MACHINE (Machine Learning Based CT Angiography Derived FFR: A Multi-Center Registry) registry. Correlation of ML-CT-FFR with the invasive reference standard FFR was assessed and pooled diagnostic performance of ML-CT-FFR and cCTA was determined separately for the following stenosis locations: RCA, LAD, LCX, proximal, middle, and distal vessel segments. RESULTS: ML-CT-FFR correlated well with invasive FFR across the different stenosis locations. Per-lesion analysis revealed improved diagnostic accuracy of ML-CT-FFR compared with conventional cCTA for stenoses in the RCA (71.8% [95% confidence interval, 63.0%-79.5%] vs. 54.8% [45.7%-63.8%]), LAD (79.3 [73.9-84.0] vs. 59.6 [53.5-65.6]), LCX (84.1 [76.0-90.3] vs. 63.7 [54.1-72.6]), proximal (81.5 [74.6-87.1] vs. 63.8 [55.9-71.2]), middle (81.2 [75.7-85.9] vs. 59.4 [53.0-65.6]) and distal stenosis location (67.4 [57.0-76.6] vs. 51.6 [41.1-62.0]). CONCLUSION: In a multicenter cohort with high disease prevalence, ML-CT-FFR offered improved diagnostic performance over cCTA for detecting hemodynamically relevant stenoses regardless of their location.

Non-invasive investigations of potential renal artery stenosis in renal insufficiency.

BACKGROUND: The diagnostic value of non-invasive methods for diagnosing renal artery stenosis in patients with renal insufficiency is incompletely known. METHODS: Forty-seven consecutive patients with moderately impaired renal function and a clinical suspicion of renal artery stenosis were investigated with computed tomography angiography (CTA), gadolinium-enhanced magnetic resonance angiography (MRA), contrast-enhanced Doppler ultrasound and captopril renography. The primary reference standard was stenosis reducing the vessel diameter by at least 50% on CTA, and an alternative reference standard ('morphological and functional stenosis') was defined as at least 50% diameter reduction on CTA or MRA, combined with a positive finding from ultrasound or captopril renography. RESULTS: The frequency of positive findings, calculated on the basis of individual patients, was 70% for CTA, 60% for MRA, 53% for ultrasound and 30% for captopril renography. Counting kidneys rather than patients, corresponding frequencies were 53%, 41%, 29% and 15%, respectively. In relation to the CTA standard, the sensitivity (and specificity) at the patient level was 0.81 (0.79) for MRA, 0.70 (0.89) for ultrasound and 0.42 (1.00) for captopril renography, and at the kidney level 0.76 (0.82), 0.53 (0.81) and 0.30 (0.86), respectively. Relative to the alternative reference standard, corresponding values at the patient level were 1.00 (0.62) for CTA, 0.90 (0.69) for MRA, 0.91 (1.00) for ultrasound and 0.67 (1.00) for captopril renography, and at the kidney level 0.96 (0.76), 0.85 (0.79), 0.71 (0.97) and 0.50 (0.97), respectively. CONCLUSIONS: CTA and MRA are superior to ultrasound and captopril renography at diagnosing morphological stenosis, but ultrasound may be useful as a screening method and captopril renography for verifying renin-dependent hypertension.

Influence of Coronary Calcium on Diagnostic Performance of Machine Learning CT-FFR: Results From MACHINE Registry.

OBJECTIVES: This study was conducted to investigate the influence of coronary artery calcium (CAC) score on the diagnostic performance of machine-learning-based coronary computed tomography (CT) angiography (cCTA)-derived fractional flow reserve (CT-FFR). BACKGROUND: CT-FFR is used reliably to detect lesion-specific ischemia. Novel CT-FFR algorithms using machine-learning artificial intelligence techniques perform fast and require less complex computational fluid dynamics. Yet, influence of CAC score on diagnostic performance of the machine-learning approach has not been investigated. METHODS: A total of 482 vessels from 314 patients (age 62.3 ± 9.3 years, 77% male) who underwent cCTA followed by invasive FFR were investigated from the MACHINE (Machine Learning based CT Angiography derived FFR: a Multi-center Registry) registry data. CAC scores were quantified using the Agatston convention. The diagnostic performance of CT-FFR to detect lesion-specific ischemia was assessed across all Agatston score categories (CAC 0, >0 to <100, 100 to <400, and ≥400) on a per-vessel level with invasive FFR as the reference standard. RESULTS: The diagnostic accuracy of CT-FFR versus invasive FFR was superior to cCTA alone on a per-vessel level (78% vs. 60%) and per patient level (83% vs. 73%) across all Agatston score categories. No statistically significant differences in the diagnostic accuracy, sensitivity, or specificity of CT-FFR were observed across the categories. CT-FFR showed good discriminatory power in vessels with high Agatston scores (CAC ≥400) and high performance in low-to-intermediate Agatston scores (CAC >0 to <400) with a statistically significant difference in the area under the receiver-operating characteristic curve (AUC) (AUC: 0.71 [95% confidence interval (CI): 0.57 to 0.85] vs. 0.85 [95% CI: 0.82 to 0.89], p = 0.04). CT-FFR showed superior diagnostic value over cCTA in vessels with high Agatston scores (CAC ≥ 400: AUC 0.71 vs. 0.55, p = 0.04) and low-to-intermediate Agatston scores (CAC >0 to <400: AUC 0.86 vs. 0.63, p < 0.001). CONCLUSIONS: Machine-learning-based CT-FFR showed superior diagnostic performance over cCTA alone in CAC with a significant difference in the performance of CT-FFR as calcium burden/Agatston calcium score increased. (Machine Learning Based CT Angiography Derived FFR: a Multicenter, Registry [MACHINE] NCT02805621).

Comparison of the Diagnostic Performance of Coronary Computed Tomography Angiography-Derived Fractional Flow Reserve in Patients With Versus Without Diabetes Mellitus (from the MACHINE Consortium).

Coronary computed tomography angiography-derived fractional flow reserve (CT-FFR) is a noninvasive application to evaluate the hemodynamic impact of coronary artery disease by simulating invasively measured FFR based on CT data. CT-FFR is based on the assumption of a normal coronary microvascular response. We assessed the diagnostic performance of a machine-learning based application for on-site computation of CT-FFR in patients with and without diabetes mellitus with suspected coronary artery disease. The study population included 75 diabetic and 276 nondiabetic patients who were enrolled in the MACHINE consortium. The overall diagnostic performance of coronary CT angiography alone and in combination with CT-FFR were analyzed with direct invasive FFR comparison in 110 coronary vessels of the diabetic group and in 415 coronary vessels of the nondiabetic group. Per-vessel discrimination of lesion-specific ischemia by CT-FFR was assessed by the area under the receiver operating characteristic curves. The overall diagnostic accuracy of CT-FFR in diabetic patients was 83% and in nondiabetic patients 75% (p = 0.088), showing improvement over the diagnostic accuracy of coronary CT angiography, which was 58% and 65% (p = 0.223), respectively. In addition, the diagnostic accuracy of CT-FFR was similar between diabetic and nondiabetic patients per stratified CT-FFR group (CT-FFR < 0.6, 0.6 to 0.69, 0.7 to 0.79, 0.8 to 0.89, ≥0.9). The area under the curves for diabetic and nondiabetic patients were also comparable, 0.88 and 0.82 (p = 0.113), respectively. In conclusion, on-site machine-learning CT-FFR analysis improved the diagnostic performance of coronary CT angiography and accurately discriminated lesion-specific ischemia in both diabetic and nondiabetic patients suspected of coronary artery disease.

Gender differences in the diagnostic performance of machine learning coronary CT angiography-derived fractional flow reserve -results from the MACHINE registry.

PURPOSE: This study investigated the impact of gender differences on the diagnostic performance of machine-learning based coronary CT angiography (cCTA)-derived fractional flow reserve (CT-FFRML) for the detection of lesion-specific ischemia. METHOD: Five centers enrolled 351 patients (73.5% male) with 525 vessels in the MACHINE (Machine leArning Based CT angiograpHy derIved FFR: a Multi-ceNtEr) registry. CT-FFRML and invasive FFR ≤ 0.80 were considered hemodynamically significant, whereas cCTA luminal stenosis ≥50% was considered obstructive. The diagnostic performance to assess lesion-specific ischemia in both men and women was assessed on a per-vessel basis. RESULTS: In total, 398 vessels in men and 127 vessels in women were included. Compared to invasive FFR, CT-FFRML reached a sensitivity, specificity, positive predictive value, and negative predictive value of 78% (95%CI 72-84), 79% (95%CI 73-84), 75% (95%CI 69-79), and 82% (95%CI: 76-86) in men vs. 75% (95%CI 58-88), 81 (95%CI 72-89), 61% (95%CI 50-72) and 89% (95%CI 82-94) in women, respectively. CT-FFRML showed no statistically significant difference in the area under the receiver-operating characteristic curve (AUC) in men vs. women (AUC: 0.83 [95%CI 0.79-0.87] vs. 0.83 [95%CI 0.75-0.89], p = 0.89). CT-FFRML was not superior to cCTA alone [AUC: 0.83 (95%CI: 0.75-0.89) vs. 0.74 (95%CI: 0.65-0.81), p = 0.12] in women, but showed a statistically significant improvement in men [0.83 (95%CI: 0.79-0.87) vs. 0.76 (95%CI: 0.71-0.80), p = 0.007]. CONCLUSIONS: Machine-learning based CT-FFR performs equally in men and women with superior diagnostic performance over cCTA alone for the detection of lesion-specific ischemia.

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.

Large variation in blood flow between left ventricular segments, as detected by adenosine stress dynamic CT perfusion.

BACKGROUND: Dynamic cardiac CT perfusion (CTP) is based on repeated imaging during the first-pass contrast agent inflow. It is a relatively new method that still needs validation. PURPOSE: To evaluate the variation in adenosine stress dynamic CTP blood flow as compared to (99m) Tc SPECT. Secondarily, to compare manual and automatic segmentation. METHODS: Seventeen patients with manifest coronary artery disease were included. Nine were excluded from evaluation for various reasons. All patients were examined with dynamic stress CTP and stress/rest SPECT. CTP blood flow was compared with SPECT on a per segment basis. Results for manual and automated AHA segmentation were compared. RESULTS: CTP showed a positive correlation with SPECT, with correlation coefficients of 0·38 and 0·41 for manual and automatic segmentation, respectively (P<0·0001). There was no significant difference between the correlation coefficients of the manual and automated segmentation procedures (P = 0·75). The average per individual global CTP blood flow value for normal segments varied by a factor of 1·9 (manual and automatic segmentation). For the whole patient group, the CTP blood flow value in normal segments varied by a factor of 2·9/2·7 (manual/automatic segmentation). Within each patient, the average per segment blood flow in normal segments varied by a factor of 1·3-2·0/1·2-2·1 (manual/automatic segmentation). CONCLUSION: A positive but rather weak correlation was found between CTP and (99m) Tc SPECT. Large variations in CTP blood flow suggest that a cut-off value for stress myocardial blood flow is inadequate to detect ischaemic segments. Dynamic CTP is hampered by a limited coverage.