Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 11, 2026Journal of Cardiovascular ImagingOpen Access

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

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Does artificial intelligence-based calcium scoring using 3D transesophageal echocardiography accurately quantify aortic valve calcium compared to computed tomography in patients with moderate or severe aortic stenosis?

Population

23 patients with moderate or severe aortic stenosis, median age 76 years, 56.5% male.

Comparison

Artificial intelligence-based calcium scoring… vs Computed tomography (CT) Agatston score

Design

Cross-sectional

Key result

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.

Authors

PFPaula FazendasRBRita BairrosLELuís B. Elvas

Discussion

Loading...

Member takes

Overview

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

Key Points

  • This study aims to evaluate the feasibility of artificial intelligence-based quantification of aortic valve calcium using 3D transesophageal echocardiography.
  • Prospective pilot study involving 23 patients with moderate or severe aortic stenosis.
  • Patients underwent 3D TEE and CT for comparison.
  • A computer vision model identified calcium speckles and calculated a calcium score from TEE images.
  • TEE calcium score shows a significant positive correlation with CT Agatston scores (r = 0.65, P < 0.001).
  • ROC analysis resulted in an area under the curve of 0.87 for severe calcification identification (sensitivity 89.5%, specificity 75.0%).
  • The automated TEE calcium score provides a promising radiation-free alternative to traditional CT scoring.

Study Design

Type

Observational (n=23)

Multicenter

No

Structured PICO

Does artificial intelligence-based calcium scoring using 3D transesophageal echocardiography accurately quantify aortic valve calcium compared to computed tomography 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-based calcium scoring using 3D transesophageal echocardiography (TEE)
C
Comparator
Computed tomography (CT) Agatston score
O
Outcome
Correlation between automated TEE calcium score and CT Agatston score, and diagnostic accuracy for severe calcificationsurrogate

Main Result

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

AI-based calcium quantification using 3D TEE is feasible and correlates well 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.

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/6a51de38c18d7f28ca5002b9https://doi.org/10.1186/s44348-026-00080-x
View Full Paper
Ask AI
Bookmark
Share