Coronary computed tomography angiography imaging features combined with computed tomography-fractional flow reserve, pericoronary fat attenuation index, and radiomics for the prediction of myocardial ischemia.
J Nucl Cardiol
; 30(5): 1838-1850, 2023 10.
Article
em En
| MEDLINE
| ID: mdl-36859595
ABSTRACT
BACKGROUND:
This study aimed to predict myocardial ischemia (MIS) by constructing models with imaging features, CT-fractional flow reserve (CT-FFR), pericoronary fat attenuation index (pFAI), and radiomics based on coronary computed tomography angiography (CCTA). METHODS ANDRESULTS:
This study included 96 patients who underwent CCTA and single photon emission computed tomography-myocardial perfusion imaging (SPECT-MPI). According to SPECT-MPI results, there were 72 vessels with MIS in corresponding supply area and 105 vessels with no-MIS. The conventional model [lesion length (LL), MDS (maximum stenosis diameter × 100% / reference vessel diameter), MAS (maximum stenosis area × 100% / reference vessel area) and CT value], radiomics model (radiomics features), and multi-faceted model (all features) were constructed using support vector machine. Conventional and radiomics models showed similar predictive efficacy [AUC 0.76, CI 0.62-0.90 vs. 0.74, CI 0.61-0.88; p > 0.05]. Adding pFAI to the conventional model showed better predictive efficacy than adding CT-FFR (AUC 0.88, CI 0.79-0.97 vs. 0.80, CI 0.68-0.92; p < 0.05). Compared with conventional and radiomics model, the multi-faceted model showed the highest predictive efficacy (AUC 0.92, CI 0.82-0.98, p < 0.05).CONCLUSION:
pFAI is more effective for predicting MIS than CT-FFR. A multi-faceted model combining imaging features, CT-FFR, pFAI, and radiomics is a potential diagnostic tool for MIS.Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Doença da Artéria Coronariana
/
Isquemia Miocárdica
/
Estenose Coronária
/
Reserva Fracionada de Fluxo Miocárdico
Tipo de estudo:
Prognostic_studies
/
Risk_factors_studies
Limite:
Humans
Idioma:
En
Revista:
J Nucl Cardiol
Assunto da revista:
CARDIOLOGIA
Ano de publicação:
2023
Tipo de documento:
Article
País de afiliação:
China