Magdalena M Dobrolinska1, Sergiy V Lazarenko2, Friso M van der Zant2, Lonneke Does2, Niels van der Werf3,4, Niek H J Prakken5, Marcel J W Greuter5,6, Riemer H J A Slart5,7, Remco J J Knol2. 1. Medical Imaging Center, Departments of Radiology, Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, PO Box 30.001, 9700 RB, Groningen, The Netherlands. magdalena.dobrolinska@gmail.com. 2. Department of Nuclear Medicine, Northwest Clinics, Alkmaar, The Netherlands. 3. Department of Radiology, University of Utrecht, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands. 4. Department of Radiology & Nuclear Medicine, Erasmus University Medical Center Rotterdam, Postbus 2040, 3000 CA, Rotterdam, The Netherlands. 5. Medical Imaging Center, Departments of Radiology, Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, PO Box 30.001, 9700 RB, Groningen, The Netherlands. 6. Department of Robotics and Mechatronics, Faculty of Electrical Engineering, Mathematics & Computer Science, University of Twente, P.O. Box 217, 7500 AE, Enschede, The Netherlands. 7. Department of Biomedical Photonic Imaging, Faculty of Science and Technology, University of Twente, Drienerlolaan 5, 7522 NB, Enschede, The Netherlands.
Abstract
BACKGROUND: Coronary artery calcium is a well-known predictor of major adverse cardiac events and is usually scored manually from dedicated, ECG-triggered calcium scoring CT (CSCT) scans. In clinical practice, a myocardial perfusion PET scan is accompanied by a non-ECG triggered low dose CT (LDCT) scan. In this study, we investigated the accuracy of patients' cardiovascular risk categorisation based on manual, visual, and automatic AI calcium scoring using the LDCT scan. METHODS: We retrospectively enrolled 213 patients. Each patient received a 13N-ammonia PET scan, an LDCT scan, and a CSCT scan as the gold standard. All LDCT and CSCT scans were scored manually, visually, and automatically. For the manual scoring, we used vendor recommended software (Syngo.via, Siemens). For visual scoring a 6-points risk scale was used (0; 1-10; 11-100; 101-400; 401-100; > 1 000 Agatston score). The automatic scoring was performed with deep learning software (Syngo.via, Siemens). All manual and automatic Agatston scores were converted to the 6-point risk scale. Manual CSCT scoring was used as a reference. RESULTS: The agreement of manual and automatic LDCT scoring with the reference was low [weighted kappa 0.59 (95% CI 0.53-0.65); 0.50 (95% CI 0.44-0.56), respectively], but the agreement of visual LDCT scoring was strong [0.82 (95% CI 0.77-0.86)]. CONCLUSIONS: Compared with the gold standard manual CSCT scoring, visual LDCT scoring outperformed manual LDCT and automatic LDCT scoring.
BACKGROUND: Coronary artery calcium is a well-known predictor of major adverse cardiac events and is usually scored manually from dedicated, ECG-triggered calcium scoring CT (CSCT) scans. In clinical practice, a myocardial perfusion PET scan is accompanied by a non-ECG triggered low dose CT (LDCT) scan. In this study, we investigated the accuracy of patients' cardiovascular risk categorisation based on manual, visual, and automatic AI calcium scoring using the LDCT scan. METHODS: We retrospectively enrolled 213 patients. Each patient received a 13N-ammonia PET scan, an LDCT scan, and a CSCT scan as the gold standard. All LDCT and CSCT scans were scored manually, visually, and automatically. For the manual scoring, we used vendor recommended software (Syngo.via, Siemens). For visual scoring a 6-points risk scale was used (0; 1-10; 11-100; 101-400; 401-100; > 1 000 Agatston score). The automatic scoring was performed with deep learning software (Syngo.via, Siemens). All manual and automatic Agatston scores were converted to the 6-point risk scale. Manual CSCT scoring was used as a reference. RESULTS: The agreement of manual and automatic LDCT scoring with the reference was low [weighted kappa 0.59 (95% CI 0.53-0.65); 0.50 (95% CI 0.44-0.56), respectively], but the agreement of visual LDCT scoring was strong [0.82 (95% CI 0.77-0.86)]. CONCLUSIONS: Compared with the gold standard manual CSCT scoring, visual LDCT scoring outperformed manual LDCT and automatic LDCT scoring.
Authors: Ahmad M Slim; Scott Jerome; Ron Blankstein; Wm Guy Weigold; Amit R Patel; Dinesh K Kalra; Ryan Miller; Kelley Branch; Mark G Rabbat; Harvey Hecht; Edward D Nicol; Todd C Villines; Leslee J Shaw Journal: J Cardiovasc Comput Tomogr Date: 2017-08-31
Authors: John W McEvoy; Seth S Martin; Zeina A Dardari; Michael D Miedema; Veit Sandfort; Joseph Yeboah; Matthew J Budoff; David C Goff; Bruce M Psaty; Wendy S Post; Khurram Nasir; Roger S Blumenthal; Michael J Blaha Journal: Circulation Date: 2016-11-23 Impact factor: 29.690
Authors: Andrew J Einstein; Lynne L Johnson; Sabahat Bokhari; Jessica Son; Randall C Thompson; Timothy M Bateman; Sean W Hayes; Daniel S Berman Journal: J Am Coll Cardiol Date: 2010-11-30 Impact factor: 24.094
Authors: Matthew J Budoff; Leslee J Shaw; Sandy T Liu; Steven R Weinstein; Tristen P Mosler; Philip H Tseng; Ferdinand R Flores; Tracy Q Callister; Paolo Raggi; Daniel S Berman Journal: J Am Coll Cardiol Date: 2007-04-20 Impact factor: 24.094
Authors: Robyn L McClelland; Neal W Jorgensen; Matthew Budoff; Michael J Blaha; Wendy S Post; Richard A Kronmal; Diane E Bild; Steven Shea; Kiang Liu; Karol E Watson; Aaron R Folsom; Amit Khera; Colby Ayers; Amir-Abbas Mahabadi; Nils Lehmann; Karl-Heinz Jöckel; Susanne Moebus; J Jeffrey Carr; Raimund Erbel; Gregory L Burke Journal: J Am Coll Cardiol Date: 2015-10-13 Impact factor: 24.094
Authors: François Mach; Colin Baigent; Alberico L Catapano; Konstantinos C Koskinas; Manuela Casula; Lina Badimon; M John Chapman; Guy G De Backer; Victoria Delgado; Brian A Ference; Ian M Graham; Alison Halliday; Ulf Landmesser; Borislava Mihaylova; Terje R Pedersen; Gabriele Riccardi; Dimitrios J Richter; Marc S Sabatine; Marja-Riitta Taskinen; Lale Tokgozoglu; Olov Wiklund Journal: Eur Heart J Date: 2020-01-01 Impact factor: 29.983
Authors: Allison W Peng; Zeina A Dardari; Roger S Blumenthal; Omar Dzaye; Olufunmilayo H Obisesan; S M Iftekhar Uddin; Khurram Nasir; Ron Blankstein; Matthew J Budoff; Martin Bødtker Mortensen; Parag H Joshi; John Page; Michael J Blaha Journal: Circulation Date: 2021-03-02 Impact factor: 29.690
Authors: Matthew J Budoff; Rebekah Young; Gregory Burke; J Jeffrey Carr; Robert C Detrano; Aaron R Folsom; Richard Kronmal; Joao A C Lima; Kiang J Liu; Robyn L McClelland; Erin Michos; Wendy S Post; Steven Shea; Karol E Watson; Nathan D Wong Journal: Eur Heart J Date: 2018-07-01 Impact factor: 35.855
Authors: Mallory S Lo-Kioeng-Shioe; Andrea L Vavere; Armin Arbab-Zadeh; Joanne D Schuijf; Carlos E Rochitte; Marcus Y Chen; Matthias Rief; Klaus F Kofoed; Melvin E Clouse; Arthur J Scholte; Julie M Miller; Aisha Betoko; Michael J Blaha; Christopher Cox; Jaap W Deckers; Joao A C Lima Journal: J Am Heart Assoc Date: 2019-03-19 Impact factor: 5.501