基于自监督网络的肝脏磁共振R2*参数图像重建

陆琪琪,连梓锋,李嘉龙,斯文彬,麦兆华,冯衍秋

Magnetic Resonance R2* Parameter Mapping of Liver Based on Self-supervised Deep Neural Network

LU Qiqi,LIAN Zifeng,LI Jialong,SI Wenbin,MAI Zhaohua,FENG Yanqiu

表1 不同方法在仿真肝脏测试数据上得到的定量结果（均值±标准差）

Table 1 Quantitative results of different methods on the simulated testing datasets (mean ± standard deviation)

Methods NRMSE SSIM Methods NRMSE SSIM EXP 0.0616±0.0358 0.9571±0.0506 UNet-EXP 0.0623±0.0348 0.9572±0.0492 M2NCM 0.0605±0.0354 0.9548±0.0502 UNet-M2 0.0576±0.0286 0.9582±0.0466 M1NCM 0.0581±0.0325 0.9561±0.0494 UNet-TV 0.0494±0.0145 0.9724±0.0201 PCANR 0.0453±0.0122 0.9754±0.0182 UNet-TVp 0.0438±0.0100 0.9796±0.0117