Feasibility of magnetization-transfer-contrast relaxation-enhanced angiography without contrast and triggering (REACT) imaging at 1.5 T combined with deep learning-based reconstruction for cardiovascular visualization
Year: 2025
Type: article
Abstract: Background: Relaxation-enhanced angiography without contrast and triggering (REACT) is a flow-independent three-dimensional (3D) magnetic resonance angiography sequence designed to minimize artifacts using the Dixon method and an inversion recovery pre-pulse. A magnetization transfer contrast (MTC) pre-pulse (MTC-REACT) may further enhance image quality. This study evaluates the feasibility of MTC-REACT and examines deep learning-based reconstruction to improve image quality for pulmonary veins. Methods: -test. Results: The Adaptive CS-Net reconstructed MTC-REACT images provided significantly higher SNR and CNR for right pulmonary veins (SNR 33.9±4.1, 30.3±3.4; CNR 33.3±3.4, 29.6±4.3), and left pulmonary veins (SNR 35.0±3.6, 31.2±4.3; CNR 34.6±4.2, 30.6±4.4) with all P values <0.05 compared to the CS-reconstructed MTC-REACT sequence. When Adaptive CS-Net reconstruction is used for both techniques, MTC-REACT images displayed significantly higher SNR and CNR compared to the REACT sequence for only left pulmonary veins (SNR 35±3.3, 32.4±4.6; CNR 34.6±3.4, 31.8±4.6). The Adaptive-CS-Net reconstructed MTC-REACT sequence consistently outperforms the CS-reconstructed MTC-REACT for pulmonary artery and vein imaging. Conclusions: The Adaptive-CS-Net reconstructed MTC-REACT images consistently deliver superior CNR, and SNR compared to the CS reconstructed images for pulmonary veins. Notably, the MTC-REACT technique enhances image quality for pulmonary veins compared to the REACT sequence, irrespective of the deep-learning reconstruction method's impact.
Authors: Sukran Erdem, Alexandra Jack, Pezad Doctor, Gerald Greil, Tarique Hussain, Qing Zou
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W4409018288