Reconstruction of blood flow velocity with deep learning information fusion from spectral ct projections and vessel geometry

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not quantified in abstract

• Primary Outcome: Blood flow velocity reconstruction accuracy

• Nnt Or Sensitivity: Claims superior performance to PCA-net but no specific metrics provided

• Confidence Interval: Not reported

Clinical Application

Requires spectral CT capability and significant computational resources; implementation feasibility unclear Would require TGA approval for clinical use; potential applications in major tertiary centres with advanced CT capabilities and research programs Potentially applicable to patients requiring vascular flow assessment, but clinical validation needed

Abstract

In this work, we investigate a new deep learning reconstruction method of blood flow velocity within deformed vessels from contrast enhanced X-ray projections and vessel geometry. The principle of the method is to perform linear or nonlinear dimension reductions on the Radon projections and on the mesh of the vessel. These low dimensional projections are then fused to obtain the velocity field in the vessel. The accuracy of the reconstruction method is proved using various neural network architectures with realistic unsteady blood flows. The approach leverages the vessel geometry information and outperforms the simple PCA-net.

References

1. 1.Huang, S., Sigovan, M., & Sixou, B. (2024). Reconstruction of blood flow velocity with deep learning information fusion from spectral ct projections and vessel geometry. Computer Methods in Biomechanics and Biomedical Engineering. https://doi.org/10.1080/10255842.2024.2423883