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

Autor: Richard R. Bayer, Maximilian J. Bauer, John W. Nance, Taylor M. Duguay, Domenico De Santis, Rock H. Savage, Akos Varga-Szemes, Moritz H. Albrecht, Philipp L. von Knebel Doeberitz, Marly van Assen, Christian Tesche, Stefan O. Schönberg, J. Trent Pannell, Addison A. Johnson, U. Joseph Schoepf, Carlo N. De Cecco
Přispěvatelé: Faculteit Medische Wetenschappen/UMCG
Rok vydání: 2018
Předmět:
Male
medicine.medical_specialty
PREDICTION
Computed Tomography Angiography
COMPUTED-TOMOGRAPHY ANGIOGRAPHY
Ischemia
Fractional flow reserve
AMERICAN-COLLEGE
GUIDELINES
Coronary Angiography
Coronary artery disease
angiography
coronary artery disease
spiral computed tomography
030218 nuclear medicine & medical imaging
Machine Learning
03 medical and health sciences
ATHEROSCLEROTIC LESIONS
0302 clinical medicine
medicine
ARTERY-DISEASE
Humans
Radiology
Nuclear Medicine and imaging
ASSOCIATION TASK-FORCE
Diagnosis
Computer-Assisted
Retrospective Studies
Computed tomography angiography
Framingham Risk Score
medicine.diagnostic_test
Receiver operating characteristic
business.industry
Angiography
Coronary Stenosis
General Medicine
Spiral computed tomography
Middle Aged
medicine.disease
DIAGNOSTIC PERFORMANCE
Plaque
Atherosclerotic
Fractional Flow Reserve
Myocardial
Stenosis
INCREMENTAL PROGNOSTIC VALUE
ROC Curve
030220 oncology & carcinogenesis
Female
Radiology
BURDEN
business
Zdroj: European Radiology, 29(5), 2378-2387. SPRINGER
ISSN: 1432-1084
0938-7994
DOI: 10.1007/s00330-018-5834-z
Popis: 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. 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. 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
Databáze: OpenAIRE
Externí odkaz: