PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
January 15, 2026Frontiers in Bioengineering and Biotechnology0 citationsOpen Access

Automated three-dimensional left atrial analysis on computed tomography angiography: reproducibility and workflow efficiency of eight clinically relevant metrics using a deep learning pipeline

YFYouqi FanJYJian YeXWXiaoya Wang

Structured PICO

Does a deep learning-based CTA pipeline provide accurate, reproducible, and efficient quantification of left atrial metrics compared to expert manual measurements?

P
Population
407 patients undergoing computed tomography angiography (CTA) for left atrial analysis (divided into training n=270, validation n=87, and clinical evaluation n=50 cohorts)
I
Intervention
Deep learning-based CTA pipeline (MedNeXt-based model and geometry-driven framework) for automated quantification of eight clinically relevant left atrial metrics
C
Comparator
Expert manual measurements and annotations
O
Outcome
Agreement between automated and expert measurements for LA volume and diameters (AP/ML/SI) using intraclass correlation coefficients (ICCs) and Bland-Altman analysissurrogate

A deep learning pipeline for left atrial CTA analysis provides expert-level accuracy while reducing analysis time by approximately 92%, offering a highly efficient tool for pre-procedural planning.

Limitations

  • Pending prospective validation of procedural impact

Abstract

Background: Accurate and reproducible quantification of LA anatomy from CTA is essential for ablation, LAAC, and structural interventions, yet manual measurements are time-consuming and prone to inter-observer variability. Objectives: To validate a deep learning-based CTA pipeline for automated quantification of eight clinically relevant LA metrics, and to assess its agreement, repeatability, and efficiency compared with expert measurements. Methods: In this retrospective study, 407 patients were included and divided into training (n = 270), validation (n = 87), and clinical evaluation (n = 50) cohorts. A MedNeXt-based model performed multi-structure segmentation, and a geometry-driven framework computed eight metrics: LA volume, LAA volume, AP/ML/SI diameters, left/right PV ostial size, left/right PV inter-ostial angles, and LAA ostial size. Automated outputs were compared with expert annotations using intraclass correlation coefficients (ICCs) and Bland-Altman analysis (primary endpoints: LA volume and diameters). Workflow efficiency and usability (Likert scale, 1-5) were also assessed by electrophysiology/structural experts. Results: Automated measurements demonstrated excellent agreement with experts for primary endpoints (LA volume ICC = 0.999; AP/ML/SI diameter ICCs = 0.972-0.985), with minimal bias and narrow limits of agreement. Agreement for other metrics was good to excellent (typical ICCs ≥0.84). Analysis time was reduced from 15.3 ± 1.4 min to 0.5 ± 0.1 min per case (≈92% reduction; p < 0.001). Usability ratings were ≥4/5 in most cases, with 63%-76% classified as Grade A (fully usable without manual edits). Performance remained consistent across voxel-size strata. Conclusion: The proposed pipeline enables rapid, reproducible, and expert-level quantification of eight LA metrics on CTA, demonstrating technical feasibility for clinical integration pending prospective validation of procedural impact.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Fan et al. (2026) studied this question.

synapsesocial.com/papers/6a0633afac5820011f109fd2https://doi.org/10.3389/fbioe.2025.1697542
Ask AI
Helpful
Bookmark
Share
View Full Paper