Clin Res Cardiol (2022). https://doi.org/10.1007/s00392-022-02002-5

Comparison of Machine-Learning Computed Tomography-based Fractional Flow Reserve and Stress Perfusion Cardiovascular Magnetic Resonance Imaging to Detect Myocardial Ischemia
S. Klenantz1, D. Loßnitzer2, F. André2, J. Görich3, J. Schöpf4, K. Pazzo4, A. Sommer3, M. Brado5, F. Gückel3, R. Sokiranski3, T. Becher1, I. Akin1, S. Buß3, S. Baumann1
1I. Medizinische Klinik, Universitätsklinikum Mannheim, Mannheim; 2Klinik für Innere Med. III, Kardiologie, Angiologie u. Pneumologie, Universitätsklinikum Heidelberg, Heidelberg; 3Das Radiologische Zentrum, Heidelberg; 4Medical University of South Carolina, Charleston, US; 5Das Radiologische Zentrum, Sinsheim;
Background:
Machine-Learning Computed Tomography-Based Fractional Flow Reserve (CT-FFRML) is a novel tool for the assessment of hemodynamic relevance of coronary artery stenoses. We examined the diagnostic performance of CT-FFRML compared to stress perfusion cardiovascular magnetic resonance (CMR) and tested if there is an additional value of CT-FFRML over coronary computed tomography angiography (cCTA).
 
Methods:
Our retrospective analysis included 269 vessels in 141 patients (mean age 67±9years, 78% males) who underwent clinically indicated cCTA and subsequent stress CMR within a period of 2 months. CT-FFRML values were calculated from standard cCTA.
 
Results:
CT-FFRML revealed no hemodynamic significance in 79% of the patients having ≥50% stenosis in cCTA. Chi² values for the statistical relationship between CT-FFRML and stress CMR was significant (p<0.0001). CT-FFRML and cCTA (≥70% stenosis) provided a per patient sensitivity of 88% (95%CI:64-99%) and 59% (95%CI:33-82%); specificity of 90% (95%CI:84-95%) and 85% (95%CI:78-91%); positive predictive value of 56% (95%CI:42-69%) and 36% (95%CI:24-50%); negative predictive value of 98% (95%CI:94-100%) and 94% (95%CI:90-96%); accuracy of 90% (95%CI:84-94%) and 82% (95%CI:75-88%) when compared to stress CMR. The accuracy of cCTA (≥50% stenosis) was 19% (95%CI:13-27%). The AUCs were 0.89 for CT-FFRML and 0.74 for cCTA (≥70% stenosis) and therefore significantly different (p<0.05).


cCTA (≥50%)

cCTA (≥70%)

CT-FFRML (≤0.80)

Sensitivity (%)

94 (71-100)

59 (33-82)

88 (64-99)

Specificity (%)

9 (5-15)

85 (78-91)

90 (84-95)

PPV (%)

12 (11-14)

36 (24-50)

56 (42-69)

NPV (%)

92 (60-99)

94 (90-96)

99 (94-100)

Accuracy (%)

19 (13-27)

82 (75-88)

90 (84-94)












Conclusion:
CT-FFRML compared to stress perfusion CMR as the reference standard shows high diagnostic power in the identification of patients with hemodynamically significant coronary artery stenosis. This could support the role of cCTA as gatekeeper for further downstream testing and may reduce the number of patients undergoing unnecessary invasive workup.



Fig. 1 53-year-old male patient with suspected CAD and arterial hypertension. (A) cCTA illustrates a moderately graded stenosis (50-69%) with unclear hemodynamic relevance caused by mixed structured plaques in the mid left anterior descending coronary artery (arrow). (B) Color-coded 3-dimensional mesh created by CT-FFRML software shows a flow-limiting stenosis with a measured value of 0.77 (arrow). (C) a midventricular short axis stress perfusion CMR image demonstrates a significant perfusion deficit in the left anterior descending coronary artery territory, which correlates with the myocardium subtended by the hemodynamically significant lesion identified on CT-FFRML; CAD = coronary artery disease; cCTA = coronary CT angiography; CT-FFRML= Fractional flow reserve derived from coronary computed tomography angiography based on machine learning algorithm; CMR = cardiovascular magnetic resonance imaging



Fig. 2 ROC of Agatston score, cCTA (stenosis ≥70%) and CT-FFRML with stress perfusion CMR as reference standard. The AUC for detection of ischemia inducing stenosis by CT-FFRML was 0.89. Agatston score and cCTA (stenosis ≥70%) provide AUC values of 0.70 and 0.74 (n=138). CAD = coronary artery disease; cCTA = coronary CT angiography; CT-FFRML = Fractional flow reserve derived from coronary computed tomography angiography based on machine learning algorithm; CMR = cardiovascular magnetic resonance imaging

https://dgk.org/kongress_programme/jt2022/aP1221.html