← Back to the feed
AI & softwareResearch findings

Evaluation of AI-Based Quantitative Coronary Angiography Accuracy

Original published 2025.01.29 09:00 KSTAdded to Blackdeck 2026.11.02 11:58 KST

What has changed?

Achieves 93% lesion detection accuracy, outperforming visual estimation and manual QCA

Key points

  1. AI-based QCA achieves 93% lesion detection accuracy, surpassing manual QCA and visual estimation
  2. Strong correlations (R² = 0.65–0.83) are observed in stenosis, MLD, and lesion length measurements
  3. High sensitivity (>92%) is maintained in both major vessels and side branches

Connect it to your work

AI-QCA demonstrates superior lesion detection compared to visual assessment

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. medicineEnhancing quantitative coronary angiography (QCA) with advanced artificial intelligence: comparison with manual QCA and visual estimation.