Artificial intelligence for aortic valve calcium score quantification by echocardiography
Abstract
Background. Aortic valve calcification (AVC), as measured by gold-standard computed tomography (CT) Agatston score, provides an anatomic assessment of aortic stenosis (AS) severity and is a key predictor of AS progression and need for valve replacement. AVC detection and quantification from transthoracic echocardiography (TTE) could expand AS early diagnosis and risk stratification, currently limited by CT availability and radiation exposure. Methods. A multi-view video-based deep learning framework was developed using 1166 TTE aortic valve videos from 187 TTE studies acquired in 110 patients with available AVC score by CT. EchoAVC architecture includes a feature extraction model followed by a quality-aware model that aggregates video-level information to obtain patient-level predictions for AVC detection and quantification (score). The framework was validated internally with 173 TTE studies from 86 patients across seven centres, and externally using 430 TTE studies from 280 patients across four different centres. The associations between EchoAVC estimations and AS severity, progression, and need for aortic valve replacement were examined. Results. EchoAVC demonstrated excellent performance in AVC detection (AUROC 0.98, accuracy 94.4%), and quantification (R = 0.64) in the external multi-centre testing set. EchoAVC score was correlated with echocardiographic AS severity descriptors, including aortic valve mean pressure gradient ({rho} = 0.749) and peak velocity ({rho} = 0.757), and predicted future increase in mean pressure gradient ({rho} = 0.382), peak velocity ({rho} = 0.433) and calcium score by CT ({rho} = 0.650). In 361 patients followed for a median of 3.8 years, 139 underwent aortic valve replacement. Baseline presence and extent of AVC as predicted by EchoAVC showed strong risk-stratification power for aortic valve replacement, remarkably in line with those obtained by CT, and incremental over TTE AS descriptors. EchoAVC was further tested in routine clinical practice images, confirming strong associations with AS severity and progression, including stratification for incident AS in previously unaffected individuals (p<0.001). Conclusions. EchoAVC enables accurate and non-invasive detection and quantification of AVC, offering substantial diagnostic and prognostic value for aortic stenosis progression and need for valve replacement. This technique holds promise as a scalable tool for early detection and clinical management of aortic valve stenosis.
Links & Resources
Authors
Cite This Paper
P., L., A., M., L., G., J., G., L., D., N., C., Z., Y., M., A. J., J., B., F., C., E., F., I., M., M., R. C. J., V., S., D., S., T., S., T., F., H., C., I., F., I., M. H., R., D. M., A., E., G., T., F., R. J., A., G. (2025). Artificial intelligence for aortic valve calcium score quantification by echocardiography. arXiv preprint arXiv:10.64898/2025.12.26.25343075.
Lopez-Gutierrez, P., Morales-Galan, A., Galian-Gay, L., Garrido-Oliver, J., Dux-Santoy, L., Craig, N., Ye, Z., Alegret, J. M., Bermejo, J., Calvo-Iglesias, F., Ferrer, E., Mendez, I., Robledo Carmona, J. M., Sanchez-Sanchez, V., Saura, D., Sevilla, T., Foley, T., Cuellar-Calabria, H., Ferreira-Gonzalez, I., Michelena, H. I., Dweck, M. R., Evangelista, A., Teixido-Tura, G., Rodriguez-Palomares, J. F., and Guala, A.. "Artificial intelligence for aortic valve calcium score quantification by echocardiography." arXiv preprint arXiv:10.64898/2025.12.26.25343075 (2025).