AI-Derived Left Ventricular Mass From Noncontrast Cardiac Computed Tomography (CT): Correlation With Contrast CT Angiography and CMR
Authors' conclusion
The AI-based automated estimation of LV mass from noncontrast CT demonstrated excellent correlations and minimal biases when compared to contrast CTA and CMR.
Study context
- Population
- Consecutive patients who underwent coronary CT angiography (CTA) (noncontrast calcium scan and contrast CTA) and CMR; median interval 22 days (IQR 3–76)
- Participants
- 316 patients
- Comparison
- Artificial intelligence (AI)-derived LV mass from noncontrast CT vs contrast CTA and CMR
- Outcome
- Agreement of AI-derived LV mass with contrast CTA and CMR
Methodological detailsconsecutive patients
- Consecutive patients
Performance
As reported in the abstract
LV mass
Correlation (r)
0.84
P < 0.001
AI vs Contrast CTA · Bland-Altman bias 2.9; LV mass difference P = 0.133 (not significant)
Correlation (r)
0.85
P < 0.001
AI vs CMR · bias −9.4; LV mass higher with AI, P < 0.001
Further findings
- AI segmentation time
- 22 · average · seconds per case
Original publication
AI-Derived Left Ventricular Mass From Noncontrast Cardiac CT: Correlation With Contrast CT Angiography and CMR. JACC Adv. Published 12 September 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →