---

Dynamic cardiac cine imaging

---

Cardiac magnetic resonance (CMR) is a critical imaging modality for the clinical assessment of cardiovascular diseases. However, conventional CMR acquisitions are inherently time-consuming, which can lead to patient discomfort, increased susceptibility to motion artifacts, and degraded image quality. This project leverages spiral k-space sampling strategies, particularly spiral balanced steady-state free precession (Spiral bSSFP), to accelerate CMR acquisition. We also develop deep learning–based reconstruction methods to recover high-quality images from accelerated acquisitions, enabling faster and more efficient CMR imaging.

[MICCAI-CMRxRecon'23] C³-Net for Accelerated Cardiac MRI Reconstruction

1. C³-Net: Complex-Valued Cascading Cross-Domain Convolutional Neural Network for Reconstruction Undersampled CMR Images. Paper Code Slides
   Q Dou, K Yan, S Chen, Z Wang, X Feng, CH Meyer

[Exercise CMR] Real-Time Cine under in-magnet staged exercise

TBD