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

Abstract

Objectives We sought to investigate the diagnostic performance of coronary CT angiography (cCTA)-derived plaque markers combined with deep machine learning-based fractional flow reserve (CT-FFR) to identify lesion-specific ischemia using invasive FFR as the reference standard. Methods Eighty-four patients (61 ± 10 years, 65% male) who had undergone cCTA followed by invasive FFR were included in this single-center retrospective, IRB-approved, HIPAA-compliant study. Various plaque markers were derived from cCTA using a semi-automatic software prototype and deep machine learning-based CT-FFR. The discriminatory value of plaque markers and CT-FFR to identify lesion-specific ischemia on a per-vessel basis was evaluated using invasive FFR as the reference standard. Results One hundred three lesion-containing vessels were investigated. 32/103 lesions were hemodynamically significant by invasive FFR. In a multivariate analysis (adjusted for Framingham risk score), the following markers showed predictive value for lesion-specific ischemia (odds ratio [OR]): lesion length (OR 1.15, p = 0.037), non-calcified plaque volume (OR 1.02, p = 0.007), napkin-ring sign (OR 5.97, p = 0.014), and CT-FFR (OR 0.81, p < 0.0001). A receiver operating characteristics analysis showed the benefit of identifying plaque markers over cCTA stenosis grading alone, with AUCs increasing from 0.61 with ≥ 50% stenosis to 0.83 with addition of plaque markers to detect lesion-specific ischemia. Further incremental benefit was realized with the addition of CT-FFR (AUC 0.93). Conclusion Coronary CTA-derived plaque markers portend predictive value to identify lesion-specific ischemia when compared to cCTA stenosis grading alone. The addition of CT-FFR to plaque markers shows incremental discriminatory power. Key Points• Coronary CT angiography (cCTA)-derived quantitative plaque markers of atherosclerosis portend high discriminatory power to identify lesion-specific ischemia.

Impact of machine-learning CT-derived fractional flow reserve for the diagnosis and management of coronary artery disease in the randomized CRESCENT trials

“…In the CRESCENT I and II trials, a tiered cardiac CT approach mitigated the cost and burden associated with the diagnostic work-up without limiting the diagnostic performance compared with functional testing [11,12]. However, CCTA is limited in the ability to determine which patients might benefit most from revascularization, and may result in overtreatment [5,18,19]. CT-FFR has the ability to identify a specific coronary lesion that causes ischemia and opens the way to a treatment strategy at a coronary artery lesion-specific level without additional imaging [7].…”

“…Because the anatomic stenosis severity is a weak predictor of hemodynamic significance, functional evaluation is recommended for therapeutic decision-making [3]. CT-derived fractional flow reserve (CT-FFR) can compute FFR values from standard CCTA images without requiring additional testing and radiation exposure, and has shown a good correlation and agreement with invasive FFR in several studies [4][5][6][7]. On-site CT-FFR software enables CT-FFR analyses on standard workstation without transferring CT images [8,9].…”

Latest Advances in Cardiac CT

“…64 ML-based fractional flow reserve has also been shown to perform well at predicting ischaemic lesions. 65,66 The integration of ML into the clinical realm is likely to become reality in the coming decade. As electronic patient records are being increasingly used, the scope for ML is increasing.…”

Machine Learning for Assessment of Coronary Artery Disease in Cardiac CT: A Survey

“…By only performing CFD simulations once in a training phase, the time required to perform FFR CT was reduced by two orders of magnitude. The diagnostic value of this method has been demonstrated thoroughly (64)(65)(66)(67)(68)(69)(70)(71)(72)(73)(74)(75)(76). Yu…”