Artificial intelligence–based calcium scoring using 3D transesophageal echocardiography in aortic stenosis: a pilot study

Q: What are the key findings of this study?

AI-based calcium quantification using 3D transesophageal echocardiography significantly correlated with CT Agatston scores (r = 0.65) and identified severe calcification with an AUC of 0.87.

Q: What is the clinical evidence from this study?

Study design: Observational. Population: Aortic stenosis (n=23). Intervention: AI-based calcium scoring using 3D transesophageal echocardiography vs. CT Agatston score. Primary outcome: Identification of severe calcification (AUC 0.87, 95% CI 0.69-1.00).

Q: What does this research mean for the field?

Artificial intelligence-based calcium quantification using 3D transesophageal echocardiography is feasible and significantly correlates with standard CT-derived Agatston scores in patients with aortic stenosis. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Paula Fazendas; Rita Bairros; Luís B. Elvas; Liliana Brochado; João C. Ferreira; Rita Gomes; A R Pereira; Cristina Martins; José Pereira; Cândida Lourenço; Tomás Brandão; Hélder Pereira; Ana G. Almeida

doi:10.1186/s44348-026-00080-x

July 9, 2026Journal of Cardiovascular ImagingOpen Access

Artificial intelligence–based calcium scoring using 3D transesophageal echocardiography in aortic stenosis: a pilot study

View Full Paper

Ask AI

Bookmark

Share

Key result

AI-based 3D TEE calcium scoring correlates with CT and identifies severe calcification with 0.87 AUC.

AUC 0.87
95% CI 0.69-1.00
n=23

Figures

Why the study?

CT calcium scoring for aortic stenosis involves radiation exposure, and transthoracic AI methods rely on acoustic window quality, prompting evaluation of radiation-free 3D TEE.

Does AI-based calcium quantification using 3D TEE correlate with CT Agatston scores in patients with moderate or severe aortic stenosis?

Key Points

To evaluate the feasibility of artificial intelligence–based quantification of aortic valve calcium using 3D transesophageal echocardiography.
In this prospective pilot study, 23 patients (median age, 76 years; 56.5% male) with moderate or severe aortic stenosis underwent both 3D transesophageal echocardiography (TEE) and computed tomography (CT).
Multiplanar reconstruction generated 1.5-mm diastolic short-axis slices, and a computer vision model quantified calcium-related speckles across 11 frames per patient using an optimal intensity threshold of 100.
The automated TEE calcium score significantly correlated with CT Agatston scores across the full cohort (Spearman R = 0.55, P = 0.008) and after excluding one extreme outlier with CT > 10,000 (r = 0.65, P < 0.001).
Receiver operating characteristic analysis demonstrated an area under the curve of 0.87 (95% CI, 0.69–1.00) for identifying severe calcification at a cutoff of 68,813 pixels (sensitivity, 89.5%; specificity, 75.0%).
For detecting very likely severe calcification, the model achieved an area under the curve of 0.82 (95% CI, 0.54–0.95) at a cutoff of 471,062 pixels (sensitivity, 80.0%; specificity, 83.3%).

Study Design

Type

Observational (n=23)

Multicenter

No

Structured PICO

Does AI-based calcium quantification using 3D TEE correlate with CT Agatston scores in patients with moderate or severe aortic stenosis?

P

Population

23 older adults (median age 76) with moderate or severe aortic stenosis who underwent both 3D transesophageal echocardiography and cardiac CT within a 3-month interval.

E

Exposure

Artificial intelligence (AI)-based calcium quantification using 3D transesophageal echocardiography (TEE), deriving an automated TEE calcium score from the sum of calcium pixels across 11 frames per patient.

C

Comparator

Computed tomography (CT) Agatston score (reference standard).

O

Outcome

Correlation between the automated TEE calcium score and the CT Agatston score, and diagnostic accuracy (AUC) for identifying severe calcification.surrogate

Main Result

Effect estimate: AUC 0.87 (95% CI 0.69-1.00)

AI-based calcium quantification using 3D TEE is feasible and correlates significantly with CT-derived Agatston scores, offering a potential radiation-free alternative for assessing aortic valve calcification.

Limitations

Small sample size requiring further validation in larger, multicenter cohorts.
The current model requires manual identification of the region of interest (ROI), introducing potential user variability.
Mean delay of 65 days between TEE and CT scans.
Current model requires manual identification of the ROI, which introduces potential user variability.

Implication

Supports feasibility of AI calcium scoring on 3D TEE; leaves open validation against CT and clinical outcomes.

Abstract

Background Aortic valve calcium scoring by computed tomography (CT) is an established method for assessing aortic stenosis severity but is limited by radiation exposure and availability. Artificial intelligence (AI)-based calcium detection using transthoracic echocardiography has shown promise but depends on acoustic window quality. Transesophageal echocardiography (TEE), particularly 3D TEE, may overcome these limitations by providing improved visualization without radiation. The objective of this study is to evaluate the feasibility of AI-based quantification of aortic valve calcium using 3D TEE. Methods In this prospective pilot study, 23 patients (median age, 76 years; 56.5% male) with moderate or severe aortic stenosis underwent 3D TEE and CT. Multiplanar reconstruction generated 1.5-mm diastolic short-axis slices. A computer vision–based model identified calcium-related speckles. An automated TEE calcium score was derived from the sum of calcium pixels across 11 frames per patient, which was compared with the CT Agatston score. Results The TEE calcium score showed a significant positive correlation with CT Agatston scores (r = 0.65, P < 0.001). Receiver operating characteristic analysis yielded an area under the curve of 0.87 (95% confidence interval, 0.69–1.00) for identifying severe calcification (cutoff, 68,813 pixels; sensitivity, 89.5%; specificity, 75.0%). Conclusions AI-based calcium quantification using 3D TEE is feasible and correlates with CT-derived scores. This radiation-free approach may provide a promising alternative for assessing aortic valve calcification.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Fazendas et al. (2026) conducted an observational in Aortic stenosis (n=23). AI-based calcium scoring using 3D transesophageal echocardiography vs. CT Agatston score was evaluated on Identification of severe calcification (AUC 0.87, 95% CI 0.69-1.00). AI-based calcium quantification using 3D transesophageal echocardiography significantly correlated with CT Agatston scores (r = 0.65) and identified severe calcification with an AUC of 0.87.

synapsesocial.com/papers/6a51de38c18d7f28ca5002b9 https://doi.org/10.1186/s44348-026-00080-x

View Full Paper

Ask AI

Bookmark

Share

Artificial intelligence–based calcium scoring using 3D transesophageal echocardiography in aortic stenosis: a pilot study

Figures

Key Points

Study Design

Structured PICO

Main Result

Limitations

Implication

Abstract

Discussion

Cite This Study

Artificial intelligence–based calcium scoring using 3D transesophageal echocardiography in aortic stenosis: a pilot study

Figures

Key Points

Study Design

Structured PICO

Main Result

Limitations

Implication

Abstract

Discussion

Cite This Study

Keep reading

More related papers

More from Journal of Cardiovascular Imaging

Keep reading

More related papers

More from Journal of Cardiovascular Imaging