PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
October 15, 2025European Heart Journal - Digital HealthOpen Access

Deep learning-based quantification of epicardial adipose tissue volume from non-contrast computed tomography images: A multi-centre study

View Full Paper
Ask AI
Bookmark
Share

Authors

SLShuang LengNCNicholas ChengETEddy Tan

Discussion

Loading...

Member takes

Overview

This multi-centre study uses AI to automate epicardial adipose tissue quantification, improving CAD risk assessment.

Key Points

  • AI-generated epicardial adipose tissue volumes correlated highly with expert annotations, achieving r=0.975.
  • Using 1,243 non-contrast computed tomography scans, the model efficiently quantifies EAT volume in about 30 seconds per scan.
  • Assessment of the model showed strong performance in ethnically diverse populations, including a subgroup of non-Asians.
  • Quantification of EAT was significantly associated with obstructive coronary artery disease, enhancing risk prediction metrics.

Cite This Study

Leng et al. (2025) studied this question.

synapsesocial.com/papers/68efd921056559ef4287743bhttps://doi.org/10.1093/ehjdh/ztaf116
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1An enhanced deep learning method for the quantification of epicardial adipose tissue2024 · 9 citations
  2. 2Automated Deep Learning Segmentation and Quantification of Epicardial Adipose Tissue from Coronary Computed Tomography Angiography: Validation and Clinical Implications2026
  3. 3Fully Automated CT Quantification of Epicardial Adipose Tissue by Deep Learning: A Multicenter Study2019 · 146 citations
  4. 4Deep learning segmentation and quantification method for assessing epicardial adipose tissue in CT calcium score scans2022 · 51 citations
  5. 5Deep Learning for Quantification of Epicardial and Thoracic Adipose Tissue From Non-Contrast CT2018 · 203 citations