scholarly journals Diagnostic Performance of Deep LearnIng AlgoriThm for Analysis of Computed Tomography Myocardial PerfusION

2021 ◽  
Author(s):  
Giuseppe Muscogiuri ◽  
Mattia Chiesa ◽  
Andrea Baggiano ◽  
Pierino Spadafora ◽  
Rossella De Santis ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Diagnostic Accuracy ◽  
Learning Algorithm ◽  
Significant Coronary Artery Disease ◽  
Patient Specific ◽  
Fractional Flow ◽  
Flow Reserve ◽  
Specific Sensitivity ◽  
Sensitivity Specificity

Abstract Purpose: Artificial intelligence could play a key role in cardiac imaging analysis. To evaluate the diagnostic accuracy of a deep learning (DL) algorithm predicting hemodynamically significant coronary artery disease (CAD) by using a rest dataset of myocardial computed tomography perfusion (CTP) as compared to invasive evaluation. Methods: One hundred and twelve consecutive symptomatic patients scheduled for clinically indicated invasive coronary angiography (ICA) underwent CCTA plus static stress CTP and ICA with invasive fractional flow reserve (FFR) for stenoses ranging between 30% and 80%. Subsequently, a DL algorithm for the prediction of significant CAD by using the rest dataset (CTP-DLrest) and stress dataset (CTP-DLstress) was developed. The diagnostic accuracy for identification of significant CAD using CCTA, CCTA+CTPStress, CCTA+CTP-DLrest, and CCTA+CTP-DLstress were measured and compared. The time of analysis for CTPStress, CTP-DLrest and CTP-DLStress were recorded. Results: Patient-specific sensitivity, specificity, NPV, PPV, accuracy and area under the curve (AUC) of CCTA alone and CCTA+CTPStress were 100%, 33%, 100%, 54%, 63%, 67% and 86%, 89%, 89%, 86%, 88%, 87%, respectively. Patient-specific sensitivity, specificity, NPV, PPV, accuracy and AUC of CCTA+DLrest and CCTA+DLstress were 100%, 72%, 100%, 74%, 84%, 96% and 93%, 83%, 94%, 81%,88%,98%, respectively. All CCTA+CTPStress, CCTA+CTP-DLRest and CCTA+CTP-DLStress significantly improved detection of hemodynamically significant CAD (p<0.01).Time of CTP-DL was significantly lower as compared to human analysis (39.2±3.2 vs. 379.6±68.0 seconds, p<0.001).Conclusion: Evaluation of myocardial ischemia using a DL approach on rest CTP datasets is feasible and accurate. This approach may be a useful gatekeeper prior to CTPStress.

Additional value of deep learning computed tomographic angiography-based fractional flow reserve in detecting coronary stenosis and predicting outcomes

2021 ◽  
pp. 028418512098397
Author(s):  
Yang Li ◽  
Hong Qiu ◽  
Zhihui Hou ◽  
Jianfeng Zheng ◽  
Jianan Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Unstable Angina ◽  
Fractional Flow Reserve ◽  
Predictive Value ◽  
Computed Tomographic Angiography ◽  
Fractional Flow ◽  
Computed Tomographic ◽  
Flow Reserve ◽  
Sensitivity Specificity ◽  
Tomographic Angiography

Background Deep learning (DL) has achieved great success in medical imaging and could be utilized for the non-invasive calculation of fractional flow reserve (FFR) from coronary computed tomographic angiography (CCTA) (CT-FFR). Purpose To examine the ability of a DL-based CT-FFR in detecting hemodynamic changes of stenosis. Material and Methods This study included 73 patients (85 vessels) who were suspected of coronary artery disease (CAD) and received CCTA followed by invasive FFR measurements within 90 days. The diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristics curve (AUC) were compared between CT-FFR and CCTA. Thirty-nine patients who received drug therapy instead of revascularization were followed for up to 31 months. Major adverse cardiac events (MACE), unstable angina, and rehospitalization were evaluated and compared between the study groups. Results At the patient level, CT-FFR achieved 90.4%, 93.6%, 88.1%, 85.3%, and 94.9% in accuracy, sensitivity, specificity, PPV, and NPV, respectively. At the vessel level, CT-FFR achieved 91.8%, 93.9%, 90.4%, 86.1%, and 95.9%, respectively. CT-FFR exceeded CCTA in these measurements at both levels. The vessel-level AUC for CT-FFR also outperformed that for CCTA (0.957 vs. 0.599, P < 0.0001). Patients with CT-FFR ≤0.8 had higher rates of rehospitalization (hazard ratio [HR] 4.51, 95% confidence interval [CI] 1.08–18.9) and MACE (HR 7.26, 95% CI 0.88–59.8), as well as a lower rate of unstable angina (HR 0.46, 95% CI 0.07–2.91). Conclusion CT-FFR is superior to conventional CCTA in differentiating functional myocardial ischemia. In addition, it has the potential to differentiate prognoses of patients with CAD.

scholarly journals Feasibility and Validity of Computed Tomography-Derived Fractional Flow Reserve in Patients With Severe Aortic Stenosis

2020 ◽  
Author(s):  
Michael Michail ◽  
Abdul-Rahman Ihdayhid ◽  
Andrea Comella ◽  
Udit Thakur ◽  
James D. Cameron ◽  
...  
Keyword(s):  
Aortic Stenosis ◽  
Diagnostic Accuracy ◽  
Operating Characteristic ◽  
Severe Aortic Stenosis ◽  
Characteristic Curve ◽  
Fractional Flow ◽  
Predictive Values ◽  
Flow Reserve ◽  
Artery Disease ◽  
Sensitivity Specificity

Background: Coronary artery disease is common in patients with severe aortic stenosis. Computed tomography-derived fractional flow reserve (CT-FFR) is a clinically used modality for assessing coronary artery disease, however, its use has not been validated in patients with severe aortic stenosis. This study assesses the safety, feasibility, and validity of CT-FFR in patients with severe aortic stenosis. Methods: Prospectively recruited patients underwent standard-protocol invasive FFR and coronary CT angiography (CTA). CTA images were analyzed by central core laboratory (HeartFlow, Inc) for independent evaluation of CT-FFR. CT-FFR data were compared with FFR (ischemia defined as FFR ≤0.80). Results: Forty-two patients (68 vessels) underwent FFR and CTA; 39 patients (92.3%) and 60 vessels (88.2%) had interpretable CTA enabling CT-FFR computation. Mean age was 76.2±6.7 years (71.8% male). No patients incurred complications relating to premedication, CTA, or FFR protocol. Mean FFR and CT-FFR were 0.83±0.10 and 0.77±0.14, respectively. CT calcium score was 1373.3±1392.9 Agatston units. On per vessel analysis, there was positive correlation between FFR and CT-FFR (Pearson correlation coefficient, R =0.64, P <0.0001). Sensitivity, specificity, positive predictive value, and negative predictive values were 73.9%, 78.4%, 68.0%, and 82.9%, respectively, with 76.7% diagnostic accuracy. The area under the receiver-operating characteristic curve for CT-FFR was 0.83 (0.72–0.93, P <0.0001), which was higher than that of CTA and quantitative coronary angiography ( P =0.01 and P <0.001, respectively). Bland-Altman plot showed mean bias between FFR and CT-FFR as 0.059±0.110. On per patient analysis, the sensitivity, specificity, positive predictive, and negative predictive values were 76.5%, 77.3%, 72.2%, and 81.0% with 76.9% diagnostic accuracy. The per patient area under the receiver-operating characteristic curve analysis was 0.81 (0.67–0.95, P <0.0001). Conclusions: CT-FFR is safe and feasible in patients with severe aortic stenosis. Our data suggests that the diagnostic accuracy of CT-FFR in this cohort potentially enables its use in clinical practice and provides the foundation for future research into the use of CT-FFR for coronary evaluation pre-aortic valve replacement.

scholarly journals Added value of computed tomography fractional flow reserve in the diagnosis of coronary artery disease

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
J. Peper ◽  
J. Schaap ◽  
J. C. Kelder ◽  
B. J. W. M. Rensing ◽  
D. E. Grobbee ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Added Value ◽  
Patient Specific ◽  
Fractional Flow ◽  
Non Invasive ◽  
Basic Model ◽  
Flow Reserve ◽  
Lumped Parameter ◽  
Lumped Parameter Models ◽  
Artery Disease

AbstractMultiple non-invasive tests are performed to diagnose coronary artery disease (CAD), but all are limited to either anatomical or functional assessments. Computed tomography derived Fractional Flow Reserve (CT-FFR) based on patient-specific lumped parameter models is a new test combining both characteristics simulating invasive FFR. This study aims to evaluate the added value of CT-FFR over other non-invasive tests to diagnose CAD. Patients with clinical suspicion of angina pectoris between 2010 and 2011 were included in this cross-sectional study. All underwent stress electrocardiography (X-ECG), SPECT, CT coronary angiography (CCTA) and CT-FFR. Invasive coronary angiography (ICA) and FFR were used as reference standard. Five models mimicking the clinical workflow were fitted and the area under receiver operating characteristic (AUROC) curve was used for comparison. 44% of the patients included in the analysis had a FFR of ≤ 0.80. The basic model including pre-test-likelihood and X-ECG had an AUROC of 0.79. The SPECT-strategy had an AUROC of 0.90 (p = 0.008), CCTA-strategy of 0.88 (p < 0.001), 0.93 when adding CT-FFR (p = 0.40) compared to 0.94 when combining CCTA and SPECT. This study shows adding on-site CT-FFR based on patient-specific lumped parameter models leads to an increased AUROC compared to the basic model. It improves the diagnostic work-up beyond SPECT or CCTA and is non-inferior to the combined strategy of SPECT and CCTA in the diagnosis of hemodynamically relevant CAD.

P6190Dynamic stress CTP with a whole-heart coverage scanner in addition to cCTA and FFRCT

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
A Baggiano ◽  
M Guglielmo ◽  
G Muscogiuri ◽  
L Fusini ◽  
A Del Torto ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Diagnostic Accuracy ◽  
Radiation Exposure ◽  
Dynamic Stress ◽  
Functional Evaluation ◽  
Ct Scanner ◽  
Fractional Flow ◽  
Computed Tomography Perfusion ◽  
Flow Reserve ◽  
Whole Heart

Abstract Background Recently, new techniques such as dynamic stress computed tomography perfusion (stress-CTP) emerged as potential strategies to combine anatomical and functional evaluation in a one-shot scan. However, previous experience used technology that was associated with high radiation exposure. Purpose The aim of the study is to test the diagnostic accuracy of integrated evaluation of dynamic myocardial computed tomography perfusion (CTP) on top of coronary computed tomography angiography (cCTA) plus FFR computed tomography derived (FFRCT) by using a whole-heart coverage CT scanner as compared to invasive coronary angiography (ICA) plus clinically indicate invasive fractional flow reserve (FFR). Methods Eighty-five consecutive symptomatic patients scheduled for ICA were prospectively enrolled. All patients underwent rest cCTA followed by stress dynamic CTP with a whole-heart coverage CT scanner. FFRCT was also measured by using the rest cCTA dataset. The diagnostic accuracy to detect functionally significant CAD in a vessel-based model of cCTA alone, cCTA+FFRCT, cCTA+CTP or cCTA+FFRCT+CTP were assessed and compared by using ICA and invasive FFR as reference. The overall effective dose of dynamic CTP was also measured. Results The prevalence of obstructive CAD and functionally significant CAD were 77% and 57%, respectively. The sensitivity and specificity of cCTA alone, cCTA+FFRCT and cCTA+CTP, were 83% and 66%, 86% and 75%, 73% and 86%, respectively. Both the addition of FFRCT and CTP improves the area under the curve (AUC: 0.876 and 0.878, respectively) as compared to cCTA alone (0.826, p<0.05). The sequential strategy of cCTA+FFRCT+CTP showed the highest AUC (0.919, p<0.05) as compared to all other strategies. The mean ED for cCTA and stress CTP was 2.8±1.2 and 5.3±0.7 mSv, respectively. Conclusions The addition of dynamic stress CTP on top of cCTA and FFRCT provides additional diagnostic accuracy with acceptable radiation exposure.

scholarly journals Coronary artery stenosis-related perfusion ratio using dynamic computed tomography myocardial perfusion imaging: a pilot for identification of hemodynamically significant coronary artery disease

2019 ◽  
Vol 35 (4) ◽  
pp. 327-335 ◽  
Author(s):  
Natsumi Kuwahara ◽  
Yuki Tanabe ◽  
Teruhito Kido ◽  
Akira Kurata ◽  
Teruyoshi Uetani ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Coronary Artery Disease ◽  
Coronary Artery ◽  
Diagnostic Performance ◽  
Invasive Coronary Angiography ◽  
Significant Coronary Artery Disease ◽  
Fractional Flow ◽  
Coronary Cta ◽  
Flow Reserve ◽  
Artery Disease

Abstract The purpose of this study was to evaluate the feasibility of the stenosis-related quantitative perfusion ratio (QPR) for detecting hemodynamically significant coronary artery disease (CAD). Twenty-seven patients were retrospectively enrolled. All patients underwent dynamic myocardial computed tomography perfusion (CTP) and coronary computed tomography angiography (CTA) before invasive coronary angiography (ICA) measuring the fractional flow reserve (FFR). Coronary lesions with FFR ≤ 0.8 were defined as hemodynamically significant CAD. The myocardial blood flow (MBF) was calculated using dynamic CTP data, and CT-QPR was calculated as the CT-MBF relative to the reference CT-MBF. The stenosis-related CT-MBF and QPR were calculated using Voronoi diagram-based myocardial segmentation from coronary CTA data. The relationships between FFR and stenosis-related CT-MBF or QPR and the diagnostic performance of the stenosis-related CT-MBF and QPR were evaluated. Of 81 vessels, FFR was measured in 39 vessels, and 20 vessels (51%) in 15 patients were diagnosed as hemodynamically significant CAD. The stenosis-related CT-QPR showed better correlation (r = 0.70, p < 0.05) than CT-MBF (r = 0.56, p < 0.05). Sensitivity and specificity for detecting hemodynamically significant CAD were 95% and 58% for CT-MBF, and 95% and 90% for CT-QPR, respectively. The area under the receiver operating characteristic curve for the CT-QPR was significantly higher than that for the CT-MBF (0.94 vs. 0.79; p < 0.05). The stenosis-related CT-QPR derived from dynamic myocardial CTP and coronary CTA showed a better correlation with FFR and a higher diagnostic performance for detecting hemodynamically significant CAD than the stenosis-related CT-MBF.

scholarly journals Diagnostic accuracy of on-site coronary computed tomography-derived fractional flow reserve in the diagnosis of stable coronary artery disease

2021 ◽  
Author(s):  
J. Peper ◽  
J. Schaap ◽  
B. J. W. M. Rensing ◽  
J. C. Kelder ◽  
M. J. Swaans
Keyword(s):  
Computed Tomography ◽  
Coronary Artery Disease ◽  
Coronary Artery ◽  
Diagnostic Accuracy ◽  
Fractional Flow Reserve ◽  
Diagnostic Performance ◽  
Reference Standard ◽  
Fractional Flow ◽  
Flow Reserve ◽  
Artery Disease

Abstract Purpose Invasive fractional flow reserve (FFR), the reference standard for identifying significant coronary artery disease (CAD), can be estimated non-invasively by computed tomography-derived fractional flow reserve (CT-FFR). Commercially available off-site CT-FFR showed improved diagnostic accuracy compared to coronary computed tomography angiography (CCTA) alone. However, the diagnostic performance of this lumped-parameter on-site method is unknown. The aim of this cross-sectional study was to determine the diagnostic accuracy of on-site CT-FFR in patients with suspected CAD. Methods A total of 61 patients underwent CCTA and invasive coronary angiography with FFR measured in 88 vessels. Significant CAD was defined as FFR and CT-FFR below 0.80. CCTA with stenosis above 50% was regarded as significant CAD. The diagnostic performance of both CT-FFR and CCTA was assessed using invasive FFR as the reference standard. Results Of the 88 vessels included in the analysis, 34 had an FFR of ≤ 0.80. On a per-vessel basis, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy were 91.2%, 81.4%, 93.6%, 75.6% and 85.2% for CT-FFR and were 94.1%, 68.5%, 94.9%, 65.3% and 78.4% for CCTA. The area under the receiver operating characteristic curve was 0.91 and 0.85 for CT-FFR and CCTA, respectively, on a per-vessel basis. Conclusion On-site non-invasive FFR derived from CCTA improves diagnostic accuracy compared to CCTA without additional testing and has the potential to be integrated in the current clinical work-up for diagnosing stable CAD.

Sign in / Sign up

Export Citation Format

Share Document