Sparse Dictionary-Based Magnetic Resonance Superresolution Imaging with Joint Loss Function Learning

Table 6

The PSNR/SSIM value corresponding to the number of sample blocks of different sampling images (superresolution ratio 1 : 4).

Number of sample image blocks	Sample set 1	Sample set 2	Sample set 3	Sample set 4	Sample set 5
1000	—	—	—	—	—
5000	29.78/0.8625	25.29/0.7820	29.11/0.8679	27.04/0.8026	27.43/0.8247
10000	29.75/0.8632	25.30/0.7838	29.15/0.8712	27.09/0.8134	27.48/0.8296
50000	29.77/0.8714	25.35/0.7916	29.16/0.8745	27.11/0.8196	27.53/0.8377
100000	29.82/0.8755	25.34/0.7913	29.16/0.8758	27.09/0.8172	27.54/0.8401
150000	29.84/0.8761	25.38/0.7924	29.18/0.8832	27.08/0.8195	27.54/0.8412
200000	29.81/0.8759	25.36/0.7908	29.17/0.8807	27.09/0.8187	27.51/0.8407
500000	29.85/0.8764	25.39/0.7923	29.16/0.8776	27.10/0.8201	27.53/0.8411