F3 - ReconResNet: Regularised Residual Learning for MR Image Reconstruction of Undersampled Cartesian and Radial Data
Soumick Chatterjee, Mario Breitkopf, Chompunuch Sarasaen, Hadya Yassin, Georg Rose, Andreas Nürnberger, Oliver Speck
MRI is an inherently slow process, which leads to long scan time for high-resolution imaging. The speed of acquisition can be increased by ignoring parts of the data (undersampling). Consequently, this leads to the degradation of image quality. This work proposes a deep learning based MRI reconstruction framework to reconstruct highly undersampled Cartesian or radial MR acquisitions, which includes a modified regularised version of ResNet as the network backbone to remove artefacts from the undersampled image, followed by data consistency steps that fusions the network output with the data already available from undersampled k-space in order to further improve reconstruction quality. The performance of this framework for various undersampling patterns has also been tested, and it has been observed that the framework is robust to deal with various sampling patterns - results in very high quality reconstruction (highest SSIM being 0.990 +/-0.006 for acceleration factor of 3.5), while being compared with the fully sampled reconstruction. It has been shown that the proposed framework can successfully reconstruct even for an acceleration factor of 20 for Cartesian (0.968 +/-0.005) and 17 for radially (0.962 +/-0.012) sampled data.
Thursday 8th July
F1-9 (short): Imaging: Reconstruction and Clinical Data - 13:45 - 14:30 (UTC+2)