Search

Lesion morphology poorly predicts functional significance of intermediate coronary artery stenosis. The aim of this study was to determine whether a coronary artery-based myocardial segmentation method that quantifies subtended myocardium can improve the diagnostic accuracy of intravascular ultrasound (IVUS)-derived parameters for detecting ischemia-producing lesions. Coronary computed tomography angiography, IVUS, and fractional flow reserve (FFR) data were analyzed in 101 non-left main lesions (20% to 80% angiographic stenosis). Using the coronary artery-based myocardial segmentation method, total left ventricular myocardial volume (Vtotal), myocardial volume subtended by the stenotic coronary segment (Vsub), and Vratio (the ratio of the Vsub to the Vtotal) were assessed. Both Vsub >30.7 cm(3) and Vratio >25.4% were determinants of FFR ≤0.75 (area under the curve = 0.696 and 0.744). Overall, an IVUS-measured minimum lumen area (IVUS-MLA) ≤2.83 mm(2) predicted FFR ≤0.75 with a sensitivity 88% and specificity 73%. Among lesions with IVUS-MLA ≤2.83 mm(2) and FFR >0.75, 89% showed Vsub <30.7 cm(3). In 50 lesions with Vsub >30.7 cm(3), an IVUS-MLA ≤2.85 mm(2) predicted FFR ≤0.75 with sensitivity 85%, specificity 92%, positive predictive value 92%, and negative predictive value 85%. Conversely, in 51 lesions with a Vsub ≤30.7 cm(3), IVUS-MLA ≤2.67 mm(2) showed sensitivity 100%, specificity 69%, positive predictive value 38%, and negative predictive value 100% for predicting FFR ≤0.75. Body surface area, reference lumen diameter, and vessel area had modest correlations with Vsub. In those lesion subsets, IVUS-MLA ≈2.8 mm(2) accurately predicted an FFR ≤0.75, whereas the clinical relevance of assessing and treating lesions with a smaller myocardial territory may be limited (ClinicalTrials.gov number NCT1696006). [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]