TY - JOUR
T1 - Performance of a deep learning algorithm for the evaluation of CAD-RADS classification with CCTA
AU - Muscogiuri, Giuseppe
AU - Chiesa, Mattia
AU - Trotta, Michela
AU - Gatti, Marco
AU - Palmisano, Vitanio
AU - Dell'Aversana, Serena
AU - Baessato, Francesca
AU - Cavaliere, Annachiara
AU - Cicala, Gloria
AU - Loffreno, Antonella
AU - Rizzon, Giulia
AU - Guglielmo, Marco
AU - Baggiano, Andrea
AU - Fusini, Laura
AU - Saba, Luca
AU - Andreini, Daniele
AU - Pepi, Mauro
AU - Rabbat, Mark G.
AU - Guaricci, Andrea I.
AU - De Cecco, Carlo N.
AU - Colombo, Gualtiero
AU - Pontone, Gianluca
PY - 2020/2
Y1 - 2020/2
N2 - 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.
AB - 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.
KW - Artificial intelligence
KW - CADRADS
KW - Convolutional neural network
KW - Coronary artery disease
KW - Plaque characterization
UR - http://www.scopus.com/inward/record.url?scp=85077720691&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077720691&partnerID=8YFLogxK
U2 - 10.1016/j.atherosclerosis.2019.12.001
DO - 10.1016/j.atherosclerosis.2019.12.001
M3 - Article
AN - SCOPUS:85077720691
VL - 294
SP - 25
EP - 32
JO - Atherosclerosis
JF - Atherosclerosis
SN - 0021-9150
ER -