scholarly journals Inter-operator reliability of an onsite machine learning-based prototype to estimate CT angiography-derived fractional flow reserve

2021 ◽  
Vol 22 (Supplement_3) ◽  
Author(s):  
Y Han ◽  
AI Ahmed ◽  
C Schwemmer ◽  
M Cocker ◽  
T Alnabelsi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ct Angiography ◽  
Fractional Flow Reserve ◽  
Coronary Ct Angiography ◽  
Cardiac Risk ◽  
Altman Analysis ◽  
Fractional Flow ◽  
Limits Of Agreement ◽  
Coronary Ct ◽  
Flow Reserve

Abstract Funding Acknowledgements Type of funding sources: None. Background Advances in computed tomography (CT) and machine learning have enabled on-site non-invasive assessment of fractional flow reserve (ML-FFRCT). However, reproducibility of measurements across operators is not well demonstrated. Purpose This study was designed to measure the inter-operator variability and reproducibility of Coronary CT Angiography–derived fractional flow reserve values using a post-processing prototype based on a machine learning algorithm (ML-FFRCT). Methods We included 60 symptomatic patients who underwent coronary CT angiography. FFRCT was calculated by 2 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 inter-operator 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 - 0.992) and 0.972 per segment (95% CI: 0.967 - 0.977). The absolute mean difference in FFRCT estimates was 0.012 per patient (95% CI for limits of agreement: -0.035 - 0.039) and 0.02 per segment (95% CI for limits of agreement: -0.077 - 0.080). Tight limits of agreement were seen on Bland-Altman analysis. Distal segments had greater variability compared to proximal/mid segments (absolute mean difference 0.011 vs 0.025, p < 0.001). Sensitivity analysis showed similar results across degrees of stenosis, image quality and those with cardiac risk factors such as hypertension, diabetes and dyslipidemia. Conclusion A high degree of inter-operator reproducibility can be achieved by onsite machine learning based ML-FFRCT assessment. Future research is required to evaluate the physiological relevance and prognostic value of ML-FFRCT.

scholarly journals Inter-Operator Reliability of an Onsite Machine Learning-Based Prototype to Estimate Ct Angiography-Derived Fractional Flow Reserve

2021 ◽  
Author(s):  
Yushui Han ◽  
Ahmed Ibrahim Ahmed ◽  
Chris Schwemmer ◽  
Myra Cocker ◽  
Talal S Alnabelsi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sensitivity Analysis ◽  
Ct Angiography ◽  
Coronary Ct Angiography ◽  
Altman Analysis ◽  
Fractional Flow ◽  
Limits Of Agreement ◽  
Bland Altman Analysis ◽  
Coronary Ct ◽  
Flow Reserve

Abstract Background: Advances in computed tomography (CT) and machine learning have enabled on-site non-invasive assessment of fractional flow reserve (FFRCT). Purpose: To assess the inter-operator variability of Coronary CT Angiography–derived FFRCT using a machine learning based post-processing prototype.Materials and Methods: We included 60 symptomatic patients who underwent coronary CT angiography. FFRCT was calculated by 2 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 inter-operator 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 - 0.992) and 0.972 per segment (95% CI: 0.967 - 0.977). The absolute mean difference in FFRCT estimates was 0.012 per patient (95% CI for limits of agreement: -0.035 - 0.039) and 0.02 per segment (95% CI for limits of agreement: -0.077 - 0.080). Tight limits of agreement were seen on Bland-Altman analysis. Distal segments had greater variability compared to 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 inter-operator reproducibility can be achieved by onsite machine learning based FFRCT assessment. Future research is required to evaluate the physiological relevance and prognostic value of FFRCT.

Coronary CT angiography–derived plaque quantification with artificial intelligence CT fractional flow reserve for the identification of lesion-specific ischemia

2018 ◽  
Vol 29 (5) ◽  
pp. 2378-2387 ◽  
Author(s):  
Philipp L. von Knebel Doeberitz ◽  
Carlo N. De Cecco ◽  
U. Joseph Schoepf ◽  
Taylor M. Duguay ◽  
Moritz H. Albrecht ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Ct Angiography ◽  
Fractional Flow Reserve ◽  
Coronary Ct Angiography ◽  
Fractional Flow ◽  
Coronary Ct ◽  
Flow Reserve ◽  
Plaque Quantification

scholarly journals Physiological Evaluation of Anomalous Aortic Origin of a Coronary Artery Using Computed Tomography–Derived Fractional Flow Reserve

2021 ◽  
Author(s):  
Julien Adjedj ◽  
Fabien Hyafil ◽  
Xavier Halna du Fretay ◽  
Patrick Dupouy ◽  
Jean‐Michel Juliard ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Coronary Artery ◽  
Ct Angiography ◽  
Fractional Flow Reserve ◽  
Coronary Ct Angiography ◽  
Functional Evaluation ◽  
Fractional Flow ◽  
Coronary Ct ◽  
Flow Reserve

Background With the emergence of coronary computed tomography (CT) angiography, anomalous aortic origin of a coronary artery (ANOCOR) is more frequently diagnosed. Fractional flow reserve derived from CT (FFRCT) is a noninvasive functional test providing anatomical and functional evaluation of the overall coronary tree. These unique features of anatomical and functional evaluation derived from CT could help for the management of patients with ANOCOR. We aimed to retrospectively evaluate the physiological and clinical impact of FFRCT analysis in the ANOCOR registry population. Methods and Results The ANOCOR registry included patients with ANOCOR detected during invasive coronary angiography or coronary CT angiography between January 2010 and January 2013, with a planned 5‐year follow‐up. We retrospectively performed FFRCT analysis in patients with coronary CT angiography of adequate quality. Follow‐up was performed with a clinical composite end point (cardiac death, myocardial infarction, and unplanned revascularization). We obtained successful FFRCT analyses and 5‐year clinical follow‐up in 54 patients (average age, 60±13 years). Thirty‐eight (70%) patients had conservative treatment, and 16 (30%) patients had coronary revascularization after coronary CT angiography. The presence of an ANOCOR course was associated with a moderate reduction of FFRCT value from 1.0 at the ostium to 0.90±0.10 downstream the ectopic course and 0.82±0.11 distally. No significant difference in FFRCT values was identified between at‐risk and not at‐risk ANOCOR. After a 5‐year follow‐up, only one unplanned percutaneous revascularization was reported. Conclusions The presence of ANOCOR was associated with a moderate hemodynamic decrease of FFRCT values and associated with a low risk of cardiovascular events after a 5‐year follow‐up in this middle‐aged population.

Impact of computed tomography (CT)-derived fractional flow reserve on reader confidence for interpretation of coronary CT angiography

2018 ◽  
Vol 108 ◽  
pp. 242-248 ◽  
Author(s):  
Christoph Artzner ◽  
Melissa Daubert ◽  
Wendy Ehieli ◽  
David Kong ◽  
Joseph Mammarappallil ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Ct Angiography ◽  
Fractional Flow Reserve ◽  
Coronary Ct Angiography ◽  
Fractional Flow ◽  
Coronary Ct ◽  
Flow Reserve
Sign in / Sign up

Export Citation Format

Share Document