Xi Lin1, Qinqin Yang1, Jianfeng Bao2, Shuhui Cai1, Zhong Chen1, Congbo Cai1, and Jingliang Cheng2
1Department of Electronic Science, Xiamen University, Xiamen, China, 2Department of Magnetic Resonance Imaging, The First Affiliated Hospital of Zhengzhou University, Zhengzhou University, Zhengzhou, China
1Department of Electronic Science, Xiamen University, Xiamen, China, 2Department of Magnetic Resonance Imaging, The First Affiliated Hospital of Zhengzhou University, Zhengzhou University, Zhengzhou, China
In this work, overlapping echo acquisition together with deep learning-based reconstruction were proposed to achieve T2 mapping of abdomen in free-breathing for the first time.
Figure 2. The flowchart of training sample generation and reconstruction of T2 mapping. (a) The single contrast abdomen MRI images from TCGA-LIHC are preprocessed first to generate T2 and M0 templates, and then the simulated MOLED acquisition is implemented on MRiLab. (b) U-Net is trained to reconstruct T2 maps from MOLED data.
Figure 3. Reconstructed abdomen T2 maps from single-shot MOLED images. (a) T2 maps with contrast enhancement, the kidney, skeletal muscle, liver and spleen are circled in orange, red, yellow and purple, respectively. (b) T2 maps without contrast enhancement.
