Back to all papers

Diagnostic performance of a coronary CT angiography-based deep learning model for the prediction of vessel-specific ischemia.

Authors

Peters B,Symons R,Oulkadi S,Van Breda A,Bataille Y,Kayaert P,Dewilde W,De Wilder K,Franssen WMA,Nchimi A,Ghekiere O

Affiliations (11)

  • UHasselt, School of Medicine and Life Sciences, Agoralaan, 3590, Diepenbeek, Belgium. [email protected].
  • Department of Radiology, Jessa Ziekenhuis, Stadsomvaart 11, 3500, Hasselt, Belgium. [email protected].
  • Department of Radiology, Imelda Hospital, Bonheiden, Belgium.
  • Department of Radiology, Jessa Ziekenhuis, Stadsomvaart 11, 3500, Hasselt, Belgium.
  • Department of Radiology, University Hospital Antwerpen, Edegem, Belgium.
  • Department of Radiology, University Hospital Leuven, Leuven, Belgium.
  • Department of Cardiology, Jessa Ziekenhuis, Hasselt, Belgium.
  • Department of Cardiology, Imelda Hospital, Bonheiden, Belgium.
  • SMRC Sports Medical Research Center, BIOMED Biomedical Research Institute, School of Medicine and Life Sciences, Hasselt University, Diepenbeek, Belgium.
  • GIGA Cardiovascular Sciences, Liège University (ULg), Domaine Universitaire du Sart Tilman, rue de l'Hôpital, Liège, Belgium.
  • UHasselt, School of Medicine and Life Sciences, Agoralaan, 3590, Diepenbeek, Belgium.

Abstract

Fractional flow reserve (FFR) and instantaneous wave-Free Ratio (iFR) pressure measurements during invasive coronary angiography (ICA) are the gold standard for assessing vessel-specific ischemia. Artificial intelligence has emerged to compute FFR based on coronary computed tomography angiography (CCTA) images (CT-FFR<sub>AI</sub>). We assessed a CT-FFR<sub>AI</sub> deep learning model for the prediction of vessel-specific ischemia compared to invasive FFR/iFR measurements. We retrospectively selected 322 vessels from 275 patients at two centers who underwent CCTA and invasive FFR and/or iFR measurements during ICA within three months. A junior and senior radiologist at each center supervised vessel centerline-building to generate curvilinear reformats that were processed for CT-FFR<sub>AI</sub> binary outcomes (≤ 0.80 or > 0.80) prediction. Reliability for CT-FFR<sub>AI</sub> outcomes based on radiologists' supervision was assessed with Cohen's κ. Diagnostic values of CT-FFR<sub>AI</sub> were calculated using invasive FFR ≤ 0.80 (n = 224) and invasive iFR ≤ 0.89 (n = 238) as the gold standard. A multinomial logistic regression model, including all false-positive and false-negative cases, assessed the impact of patient- and CCTA-related factors on diagnostic values of CT-FFR<sub>AI</sub>. Concordance for CT-FFR<sub>AI</sub> binary outcomes was substantial (κ = 0.725, p < 0.001). Sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of CT-FFR<sub>AI</sub> in predicting vessel-specific ischemia on a per-vessel analysis, based on senior radiologists' evaluations, were 85% (58/68) and 91% (78/86), 82% (128/156) and 78% (119/152), 67% (58/86) and 70% (78/111), 93% (128/138) and 94% (119/127), and 83% (186/224) and 83% (197/238), respectively. Coronary calcifications significantly reduced the diagnostic accuracy of CT-FFR<sub>AI</sub> (p < 0.001; OR, 1.002; 95% CI 1.001-1.003). CT-FFR<sub>AI</sub> demonstrates high diagnostic performance in predicting vessel-specific coronary ischemia compared to invasive FFR and iFR. Coronary calcifications negatively affect specificity, suggesting that further improvements in spatial resolution could enhance accuracy. Question How accurately can a new deep learning model (CT-FFR<sub>AI</sub>) assess vessel-specific ischemia from CCTA non-invasively compared to two validated pressure measurements during invasive coronary angiography? Findings CT-FFR<sub>AI</sub> achieved high diagnostic accuracy in predicting vessel-specific ischemia, with high sensitivity and negative predictive value, independent of scanner type and radiologists' experience. Clinical relevance CT-FFR<sub>AI</sub> provides a non-invasive alternative to Fractional Flow Reserve and instantaneous wave-Free Ratio measurements during invasive coronary angiography for detecting vessel-specific ischemia, potentially reducing the need for invasive procedures, lowering healthcare costs, and improving patient safety.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.