Skip to main content
. Author manuscript; available in PMC: 2022 Nov 1.
Published in final edited form as: J Cardiovasc Comput Tomogr. 2021 Mar 22;15(6):462–469. doi: 10.1016/j.jcct.2021.03.006

Figure 4. CT-FFR using computational fluid dynamics aided by deep learning.

Figure 4.

Case example of CT-FFR using computational fluid dynamics. (A) Multiplanar reformat of coronary CT angiography demonstrating obstructive stenosis in the proximal left anterior descending (red arrow) due to mixed plaque with high-risk features. (B) Corresponding CT-FFR value was 0.70. Lumen boundaries were identified using a DL algorithm embedded in commercial software. (C) Quantitative plaque analysis of the same lesion was performed using semi-automated research software, with calcified plaque shown in yellow overlay and noncalcified plaque in red overlay. CT-FFR = computed tomography-fractional flow reserve.