首页 | 本学科首页   官方微博 | 高级检索  
检索        


Influence of coronary stenosis location on diagnostic performance of machine learning-based fractional flow reserve from CT angiography
Institution:1. Heart & Vascular Center, Medical University of South Carolina, Charleston, SC, USA;2. Department of Cardiology, Campus Kerckhoff of Justus-Liebig-University Giessen, Bad Nauheim, Germany;3. First Department of Medicine-Cardiology, University Medical Centre Mannheim, Mannheim, Germany;4. Department of Internal Medicine I, St.-Johannes-Hospital, Dortmund, Germany;5. Department of Radiology, Erasmus University Medical Center, Rotterdam, the Netherlands;6. Department of Radiology and Department of Medical and Health Sciences, Center for Medical Image Science and Visualization, CMIV, Linköping University, Linköping, Sweden;7. Coronary Disease and Structural Heart Diseases Department, Invasive Cardiology and Angiology Department, Institute of Cardiology, Warsaw, Poland;8. Department of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea;1. Department of Cardiovascular Medicine, Heart and Vascular Institute, Cleveland Clinic, Ohio, USA;2. Department of Thoracic and Cardiovascular Surgery, Heart Vascular and Thoracic Institute, Cleveland Clinic, Cleveland, OH, USA;3. Department of Nuclear Medicine/PET and Cardiac Radiology, Mercy Hospital, St Louis, MO, USA;1. Department of Radiology, Charité Medical School–Humboldt, Berlin, Germany;2. InCor Heart Institute, University of São Paulo Medical School, Brazil, São Paulo, Brazil;3. Johns Hopkins Hospital and School of Medicine, 600 N Wolfe St, Blalock 524, Baltimore, MD, 21287, USA;4. Cardiology Branch, National Heart Lung and Blood Institute, National Institutes of Health, Bethesda, MD, USA;5. Memorial Heart Center, Iwate Medical University, Morioka, Japan;6. Department of Radiology, St. Luke''s International Hospital, Tokyo, Japan;7. Department of Radiology, Mie University Hospital, Tsu, Japan;8. Beth Israel Deaconess Medical Center, Harvard University, Boston, Mass, USA;9. Department of Cardiology, Rigs Hospitalet, University of Copenhagen, Denmark;10. Department of Medicine/Cardiology, Charité Medical School–Humboldt, Berlin, Germany;11. Department of Medical Imaging, Toronto General Hospital, Toronto, Ontario, Canada;12. Radiology Sector, Hospital Israelita Albert Einstein, São Paulo, Brazil;13. Department of Cardiology, Leiden University Medical Center, Leiden, the Netherlands;14. Keio University School of Medicine, Tokyo, Japan;15. Department of Cardiology, National Heart Centre, Singapore;p. Medi-Rad Associates, CT Centre, Mount Elizabeth Hospital, Singapore;q. Department of Radiology, University of Cincinnati, Cincinnati, OH, USA;r. Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA;s. Department of Nuclear Medicine and Cardiovascular Imaging, Brigham and Women''s Hospital, Boston, MA, USA;1. Hugh Monroe Wilson Professor of Radiology, Professor of Biomedical Engineering, Head, Cardiac CT/MRIWashington University School of Medicine, St. Louis, MO, USA;2. Principal, The Korris Group, Washington, D.C, USA;1. Wakayama Medical University, Wakayama, Japan;2. Department of Radiology, University of British Columbia, Vancouver, BC, Canada;3. Duke University School of Medicine, Durham, NC, USA;4. Erasmus Medical Center, Rotterdam, The Netherlands;5. Onze-Lieve-Vrouwziekenhuis Aalst, Aalst, Belgium;6. HeartFlow, Redwood City, CA, USA;7. Centro Cardiologico Monzino, IRCCS, University of Milan, Milan, Italy, Yonsei University Health System, Seoul, South Korea;8. Aarhus University Hospital, Aarhus Skejby, Denmark;9. Leiden University Medical Center, Leiden, The Netherlands;10. William Beaumont Hospital, Royal Oaks, MI, USA;11. Loyola University Medical Center, Maywood, IL, USA;12. University of Southern Denmark, Odense, Denmark;13. Liverpool Heart and Chest Hospital, Liverpool, UK;14. Gifu Heart Center, Gifu, Japan;15. Aichi Medical University, Aichi, Japan;p. Shin Koga Hospital, Fukuoka, Japan;q. Iwate Medical University, Iwate, Japan;1. William Beaumont Hospital, Royal Oaks, MI, USA;2. Wakayama Medical University, Wakayama, Japan;3. Aichi Medical University, Aichi, Japan;4. Leiden University Medical Center, Leiden, The Netherlands;5. Department of Radiology, University of British Columbia, Vancouver, BC, Canada;6. Onze-Lieve-Vrouwziekenhuis Aalst, Aalst, Belgium;7. Shin Koga Hospital, Fukuoka, Japan;8. Gifu Heart Center, Gifu, Japan;9. Iwate Medical University, Iwate, Japan;10. Erasmus Medical Center, Rotterdam, The Netherlands;11. Aarhus University Hospital, Aarhus Skejby, Denmark;12. Duke University School of Medicine, Durham, NC, USA;13. Centro Cardiologico Monzino, IRCCS, University of Milan, Milan, Italy;14. Loyola University Medical Center, Maywood, IL, USA;15. HeartFlow, Redwood City, CA, USA;p. University of Southern Denmark, Odense, Denmark
Abstract:BackgroundCompared with invasive fractional flow reserve (FFR), coronary CT angiography (cCTA) is limited in detecting hemodynamically relevant lesions. cCTA-based FFR (CT-FFR) is an approach to overcome this insufficiency by use of computational fluid dynamics. Applying recent innovations in computer science, a machine learning (ML) method for CT-FFR derivation was introduced and showed improved diagnostic performance compared to cCTA alone. We sought to investigate the influence of stenosis location in the coronary artery system on the performance of ML-CT-FFR in a large, multicenter cohort.MethodsThree hundred and thirty patients (75.2% male, median age 63 years) with 502 coronary artery stenoses were included in this substudy of the MACHINE (Machine Learning Based CT Angiography Derived FFR: A Multi-Center Registry) registry. Correlation of ML-CT-FFR with the invasive reference standard FFR was assessed and pooled diagnostic performance of ML-CT-FFR and cCTA was determined separately for the following stenosis locations: RCA, LAD, LCX, proximal, middle, and distal vessel segments.ResultsML-CT-FFR correlated well with invasive FFR across the different stenosis locations. Per-lesion analysis revealed improved diagnostic accuracy of ML-CT-FFR compared with conventional cCTA for stenoses in the RCA (71.8% 95% confidence interval, 63.0%–79.5%] vs. 54.8% 45.7%–63.8%]), LAD (79.3 73.9–84.0] vs. 59.6 53.5–65.6]), LCX (84.1 76.0–90.3] vs. 63.7 54.1–72.6]), proximal (81.5 74.6–87.1] vs. 63.8 55.9–71.2]), middle (81.2 75.7–85.9] vs. 59.4 53.0–65.6]) and distal stenosis location (67.4 57.0–76.6] vs. 51.6 41.1–62.0]).ConclusionIn a multicenter cohort with high disease prevalence, ML-CT-FFR offered improved diagnostic performance over cCTA for detecting hemodynamically relevant stenoses regardless of their location.
Keywords:Atherosclerosis  Coronary artery disease  Coronary computed tomography angiography  Fractional flow reserve  Machine learning  AUC"}  {"#name":"keyword"  "$":{"id":"kwrd0040"}  "$$":[{"#name":"text"  "_":"area under the receiver operating characteristics curve  cCTA"}  {"#name":"keyword"  "$":{"id":"kwrd0050"}  "$$":[{"#name":"text"  "_":"coronary CT angiography  CI"}  {"#name":"keyword"  "$":{"id":"kwrd0060"}  "$$":[{"#name":"text"  "_":"95% confidence interval  CT-FFR"}  {"#name":"keyword"  "$":{"id":"kwrd0070"}  "$$":[{"#name":"text"  "_":"fractional flow reserve from coronary CT angiography  FFR"}  {"#name":"keyword"  "$":{"id":"kwrd0080"}  "$$":[{"#name":"text"  "_":"fractional flow reserve  LAD"}  {"#name":"keyword"  "$":{"id":"kwrd0090"}  "$$":[{"#name":"text"  "_":"left anterior descending coronary artery  LCX"}  {"#name":"keyword"  "$":{"id":"kwrd0100"}  "$$":[{"#name":"text"  "_":"left circumflex coronary artery  ML"}  {"#name":"keyword"  "$":{"id":"kwrd0110"}  "$$":[{"#name":"text"  "_":"machine learning  NPV"}  {"#name":"keyword"  "$":{"id":"kwrd0120"}  "$$":[{"#name":"text"  "_":"negative predictive value  PPV"}  {"#name":"keyword"  "$":{"id":"kwrd0130"}  "$$":[{"#name":"text"  "_":"positive predictive value  RCA"}  {"#name":"keyword"  "$":{"id":"kwrd0140"}  "$$":[{"#name":"text"  "_":"right coronary artery
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号