Diagnostic performance of deep learning algorithm for analysis of computed tomography myocardial perfusion.

Autor: Muscogiuri G; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Chiesa M; Centro Cardiologico Monzino, IRCCS, Milan, Italy.; Department of Electronics, Information and Biomedical Engineering, Politecnico di Milano, 20133, Milan, Italy., Baggiano A; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Spadafora P; Department of Biomedical Sciences for Health, University of Milan, Milan, Italy., De Santis R; Department of Biomedical Sciences for Health, University of Milan, Milan, Italy., Guglielmo M; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Scafuri S; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Fusini L; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Mushtaq S; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Conte E; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Annoni A; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Formenti A; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Mancini ME; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Ricci F; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Ariano FP; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Spiritigliozzi L; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Babbaro M; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Mollace R; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Maragna R; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Giacari CM; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Andreini D; Centro Cardiologico Monzino, IRCCS, Milan, Italy.; Department of Clinical Sciences and Community Health, Cardiovascular Section, University of Milan, Milan, Italy., Guaricci AI; Department of Emergency and Organ Transplantation, Institute of Cardiovascular Disease, University Hospital 'Policlinico Consorziale' of Bari, Bari, Italy., Colombo GI; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Rabbat MG; Loyola University of Chicago, Chicago, IL, USA.; Edward Hines Jr. VA Hospital, Hines, IL, USA., Pepi M; Centro Cardiologico Monzino, IRCCS, Milan, Italy., Sardanelli F; Department of Electronics, Information and Biomedical Engineering, Politecnico di Milano, 20133, Milan, Italy.; Unit of Radiology, IRCCS Policlinico San Donato, San Donato Milanese, Milan, Italy., Pontone G; Centro Cardiologico Monzino, IRCCS, Milan, Italy. gianluca.pontone@ccfm.it.
Jazyk: angličtina
Zdroj: European journal of nuclear medicine and molecular imaging [Eur J Nucl Med Mol Imaging] 2022 Jul; Vol. 49 (9), pp. 3119-3128. Date of Electronic Publication: 2022 Feb 23.
DOI: 10.1007/s00259-022-05732-w
Abstrakt: Purpose: To evaluate the diagnostic accuracy of a deep learning (DL) algorithm predicting hemodynamically significant coronary artery disease (CAD) by using a rest dataset of myocardial computed tomography perfusion (CTP) as compared to invasive evaluation.
Methods: One hundred and twelve consecutive symptomatic patients scheduled for clinically indicated invasive coronary angiography (ICA) underwent CCTA plus static stress CTP and ICA with invasive fractional flow reserve (FFR) for stenoses ranging between 30 and 80%. Subsequently, a DL algorithm for the prediction of significant CAD by using the rest dataset (CTP-DL rest ) and stress dataset (CTP-DL stress ) was developed. The diagnostic accuracy for identification of significant CAD using CCTA, CCTA + CTP stress, CCTA + CTP-DL rest , and CCTA + CTP-DL stress was measured and compared. The time of analysis for CTP stress, CTP-DL rest , and CTP-DL Stress was recorded.
Results: Patient-specific sensitivity, specificity, NPV, PPV, accuracy, and area under the curve (AUC) of CCTA alone and CCTA + CTP Stress were 100%, 33%, 100%, 54%, 63%, 67% and 86%, 89%, 89%, 86%, 88%, 87%, respectively. Patient-specific sensitivity, specificity, NPV, PPV, accuracy, and AUC of CCTA + DL rest and CCTA + DL stress were 100%, 72%, 100%, 74%, 84%, 96% and 93%, 83%, 94%, 81%, 88%, 98%, respectively. All CCTA + CTP stress, CCTA + CTP-DL Rest , and CCTA + CTP-DL Stress significantly improved detection of hemodynamically significant CAD compared to CCTA alone (p < 0.01). Time of CTP-DL was significantly lower as compared to human analysis (39.2 ± 3.2 vs. 379.6 ± 68.0 s, p < 0.001).
Conclusion: Evaluation of myocardial ischemia using a DL approach on rest CTP datasets is feasible and accurate. This approach may be a useful gatekeeper prior to CTP stress . .
(© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje