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

Abstract

Purpose: Arti cial intelligence could play a key role in cardiac imaging analysis. To evaluate the diagnostic accuracy of a deep learning (DL) algorithm predicting hemodynamically signi cant 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 ow reserve (FFR) for stenoses ranging between 30% and 80%. Subsequently, a DL algorithm for the prediction of signi cant CAD by using the rest dataset (CTP-DL rest ) and stress dataset (CTP-DL stress ) was developed. The diagnostic accuracy for identi cation of signi cant CAD using CCTA, CCTA+CTP Stress , CCTA+CTP-DL rest , and CCTA+CTP-DL stress were measured and compared. The time of analysis for CTP Stress , CTP-DL rest and CTP-DL Stress were recorded.Results: Patient-speci c sensitivity, speci city, NPV, PPV, accuracy and area under the curve (AUC) of CCTA alone and CCTA+CTP Stress were 100%,

Application of AI in cardiovascular multimodality imaging

“…The application of AI in cardiac CT ranges from diagnosis to prognosis [ 13 , 38 ] and seems likely to play a key role in the future for speeding up the time of reporting [ 15 , 39 ], providing information regarding coronary plaques [ 20 ], and detection of myocardial ischemia [ 21 , 40 ].…”

Multimodality imaging in acute myocarditis

“…102,103 Subsequently, images are reconstructed in order to visualize coronary arteries, evaluating origin, course and quantifying stenosis and plaque characteristics. [104][105][106][107] CCTA images can also be used for the evaluation of other cardiac structures such as cardiac chambers and great arteries. [108][109][110][111] Another application of CCTA that is rapidly growing interest is represented by the possibility to acquire late iodine enhancement (LIE).…”

“…Subsequently, images are reconstructed in order to visualize coronary arteries, evaluating origin, course and quantifying stenosis and plaque characteristics 104–107 …”

Multimodality Imaging of Sudden Cardiac Death and Acute Complications in Acute Coronary Syndrome

“…The application of artificial intelligence (AI) in non-invasive cardiovascular imaging is rapidly growing [ 11 ]. In particular, the application of artificial intelligence can modify the approach to CAD in clinical practice speeding up the time of acquisition, reporting, and building models for risk stratification [ 12 , 100 , 166 , 167 , 168 ].…”

“…The application of AI in CCTA aimed to provide information regarding the stenosis, plaque characteristics, association with ischemia, and risk stratification [ 12 , 167 , 173 ].…”