Giuseppe Muscogiuri1, Mattia Chiesa1, Michela Trotta2, Marco Gatti3, Vitanio Palmisano4, Serena Dell'Aversana5, Francesca Baessato6, Annachiara Cavaliere7, Gloria Cicala8, Antonella Loffreno9, Giulia Rizzon7, Marco Guglielmo1, Andrea Baggiano1, Laura Fusini1, Luca Saba4, Daniele Andreini10, Mauro Pepi1, Mark G Rabbat11, Andrea I Guaricci12, Carlo N De Cecco13, Gualtiero Colombo1, Gianluca Pontone14. 1. Centro Cardiologico Monzino, IRCCS, Milan, Italy. 2. Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy. 3. Department of Surgical Sciences, Radiology Institute, University of Turin, Turin, Italy. 4. Department of Medical Imaging, University of Cagliari, Monserrato, Italy. 5. Department of Advanced Biomedical Sciences, University of Naples "Federico II,", Naples, Italy. 6. Section of Cardiology, Department of Medicine, University of Verona, Verona, Italy. 7. Department of Medicine, Institute of Radiology, University of Padova, Padua, Italy. 8. Section of Radiology, Department of Medicine and Surgery, University of Parma, Parma, Italy. 9. Department of Cardiology, University of Insubria, Varese, Italy. 10. Centro Cardiologico Monzino, IRCCS, Milan, Italy; Department of Cardiovascular Sciences and Community Health, University of Milan, Italy. 11. Loyola University of Chicago, Chicago, IL, USA; Edward Hines Jr. VA Hospital, Hines, IL, USA. 12. Institute of Cardiovascular Disease, Department of Emergency and Organ Transplantation, University Hospital "Policlinico Consorziale" of Bari, Bari, Italy. 13. Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA, USA. 14. Centro Cardiologico Monzino, IRCCS, Milan, Italy. Electronic address: gianluca.pontone@ccfm.it.
Abstract
BACKGROUND AND AIMS: Artificial intelligence (AI) is increasing its role in diagnosis of patients with suspicious coronary artery disease. The aim of this manuscript is to develop a deep convolutional neural network (CNN) to classify coronary computed tomography angiography (CCTA) in the correct Coronary Artery Disease Reporting and Data System (CAD-RADS) category. METHODS: Two hundred eighty eight patients who underwent clinically indicated CCTA were included in this single-center retrospective study. The CCTAs were stratified by CAD-RADS scores by expert readers and considered as reference standard. A deep CNN was designed and tested on the CCTA dataset and compared to on-site reading. The deep CNN analyzed the diagnostic accuracy of the following three Models based on CAD-RADS classification: Model A (CAD-RADS 0 vs CAD-RADS 1-2 vs CAD-RADS 3,4,5), Model 1 (CAD-RADS 0 vs CAD-RADS>0), Model 2 (CAD-RADS 0-2 vs CAD-RADS 3-5). Time of analysis for both physicians and CNN were recorded. RESULTS: Model A showed a sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 47%, 74%, 77%, 46% and 60%, respectively. Model 1 showed a sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 66%, 91%, 92%, 63%, 86%, respectively. Conversely, Model 2 demonstrated the following sensitivity, specificity, negative predictive value, positive predictive value and accuracy: 82%, 58%, 74%, 69%, 71%, respectively. Time of analysis was significantly lower using CNN as compared to on-site reading (530.5 ± 179.1 vs 104.3 ± 1.4 sec, p=0.01) CONCLUSIONS: Deep CNN yielded accurate automated classification of patients with CAD-RADS.
BACKGROUND AND AIMS: Artificial intelligence (AI) is increasing its role in diagnosis of patients with suspicious coronary artery disease. The aim of this manuscript is to develop a deep convolutional neural network (CNN) to classify coronary computed tomography angiography (CCTA) in the correct Coronary Artery Disease Reporting and Data System (CAD-RADS) category. METHODS: Two hundred eighty eight patients who underwent clinically indicated CCTA were included in this single-center retrospective study. The CCTAs were stratified by CAD-RADS scores by expert readers and considered as reference standard. A deep CNN was designed and tested on the CCTA dataset and compared to on-site reading. The deep CNN analyzed the diagnostic accuracy of the following three Models based on CAD-RADS classification: Model A (CAD-RADS 0 vs CAD-RADS 1-2 vs CAD-RADS 3,4,5), Model 1 (CAD-RADS 0 vs CAD-RADS>0), Model 2 (CAD-RADS 0-2 vs CAD-RADS 3-5). Time of analysis for both physicians and CNN were recorded. RESULTS: Model A showed a sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 47%, 74%, 77%, 46% and 60%, respectively. Model 1 showed a sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 66%, 91%, 92%, 63%, 86%, respectively. Conversely, Model 2 demonstrated the following sensitivity, specificity, negative predictive value, positive predictive value and accuracy: 82%, 58%, 74%, 69%, 71%, respectively. Time of analysis was significantly lower using CNN as compared to on-site reading (530.5 ± 179.1 vs 104.3 ± 1.4 sec, p=0.01) CONCLUSIONS: Deep CNN yielded accurate automated classification of patients with CAD-RADS.
Authors: Jonathan James Hyett Bray; Moghees Ahmad Hanif; Mohammad Alradhawi; Jacob Ibbetson; Surinder Singh Dosanjh; Sabrina Lucy Smith; Mahmood Ahmad; Dominic Pimenta Journal: Eur Heart J Open Date: 2022-03-17
Authors: Andrea Igoren Guaricci; Giuseppina Chiarello; Elisa Gherbesi; Laura Fusini; Nicolo' Soldato; Paola Siena; Raffaella Ursi; Roberta Ruggieri; Marco Guglielmo; Giuseppe Muscogiuri; Andrea Baggiano; Mark G Rabbat; Riccardo Memeo; Mario Lepera; Stefano Favale; Gianluca Pontone Journal: Eur Heart J Open Date: 2022-02-25
Authors: Gianluca Pontone; Alexia Rossi; Marco Guglielmo; Marc R Dweck; Oliver Gaemperli; Koen Nieman; Francesca Pugliese; Pal Maurovich-Horvat; Alessia Gimelli; Bernard Cosyns; Stephan Achenbach Journal: Eur Heart J Cardiovasc Imaging Date: 2022-03-22 Impact factor: 9.130
Authors: Francesca Baessato; Marco Guglielmo; Giuseppe Muscogiuri; Andrea Baggiano; Laura Fusini; Stefano Scafuri; Mario Babbaro; Rocco Mollace; Ada Collevecchio; Andrea I Guaricci; Gianluca Pontone Journal: Biomed Res Int Date: 2021-01-14 Impact factor: 3.411
Authors: Giuseppe Muscogiuri; Marly Van Assen; Christian Tesche; Carlo N De Cecco; Mattia Chiesa; Stefano Scafuri; Marco Guglielmo; Andrea Baggiano; Laura Fusini; Andrea I Guaricci; Mark G Rabbat; Gianluca Pontone Journal: Biomed Res Int Date: 2020-12-16 Impact factor: 3.411
Authors: Emanuele Di Virgilio; Francesco Monitillo; Daniela Santoro; Silvia D'Alessandro; Marco Guglielmo; Andrea Baggiano; Laura Fusini; Riccardo Memeo; Mark G Rabbat; Stefano Favale; Matteo Cameli; Andrea Igoren Guaricci; Gianluca Pontone Journal: J Clin Med Date: 2021-11-30 Impact factor: 4.241