Back to the list
Congress: ECR25
Poster Number: C-19973
Type: Poster: EPOS Radiologist (scientific)
Authorblock: B. Liu1, J. Reis2; 1Shanghai/CN, 2Lisbon/PT
Disclosures:
Baiyun Liu: Employee: Medical
Joana Reis: Nothing to disclose
Keywords: Artificial Intelligence, Cardiac, Cardiovascular system, CAD, CT, CT-Angiography, CAD, Computer Applications-Detection, diagnosis, Efficacy studies, Calcifications / Calculi, Obstruction / Occlusion
Purpose This systematic review and meta-analysis aimed to evaluate existing evidence on the application of artificial intelligence (AI) to non-invasive coronary artery disease (CAD) imaging and assess the diagnostic performance of AI applications in CAD imaging.  
Read more Methods and materials Early and accurate diagnosis is essential for effective and timely treatment, which contributes to improved patient outcomes. Non-invasive imaging modalities, such as computed tomography (CT), coronary computed tomography angiography, and cardiac magnetic resonance, are being used increasingly for the diagnosis of coronary heart disease. AI applications have demonstrated great promise in enhancing cardiovascular imaging, for example by automating coronary artery segmentation and scoring [Wolterink 2016, Zeleznik 2021], coronary stenosis evaluation [Liang 2017], coronary plaque segmentation [Lin 2022b], functional assessment of...
Read more Results A total of 122 studies were selected for evidence mapping and 9 for the meta-analysis. Most studies were conducted in Asia (50.8%), followed by North America (24.6%) and Europe (23.8%), with more studies undertaken in China (n=49) and the USA (n=31) than in other countries. Of the studies using CT imaging modalities (n=111), AI-based analysis was used in 46 computerized tomography fractional flow reserve, 36 plaque or stenosis, and 29 calcium scoring studies. , the pooled sensitivity and specificity for...
Read more Conclusion This systematic review and meta-analysis evaluated existing evidence on the application of AI to non-invasive CAD imaging and the diagnostic performance of AI applications in CAD imaging. To our knowledge, this is the first meta-analysis to assess the diagnostic perfomance of AI applications for detection coronary arteries with ≥50% stenosis. We found that most studies were conducted in China and the USA, and the majority had sample sizes of 100–500 patients. AI applications demonstrated good diagnostic performance for detecting ≥50%...
Read more References Bai, W., M. Sinclair, G. Tarroni, et al. Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. J Cardiovasc Magn Reson 2018; 20(1):65;Bar, S., T. Nabeta, T. Maaniitty, et al. Prognostic value of a novel artificial intelligence-based coronary computed tomography angiography-derived ischaemia algorithm for patients with suspected coronary artery disease. Eur Heart J Cardiovasc Imaging 2024; 25(5):657-667;Han, D., J. Liu, Z. Sun, et al. Deep learning analysis in coronary computed tomographic angiography imaging for the assessment of patients with...
Read more
GALLERY