Table 5 Quantitative comparison results of the weight \(\lambda\) of perceptual loss in the total loss.
From: A novel multimodel medical image fusion framework with edge enhancement and cross-scale transformer
Fusion tasks | CT and MRI image fusion | PET and MRI image fusion | SPECT and MRI image fusion | ||||||
|---|---|---|---|---|---|---|---|---|---|
\(\lambda =0\) | \(\lambda =0.02\) | \(\lambda =0.2\) | \(\lambda =0\) | \(\lambda =0.02\) | \(\lambda =0.2\) | \(\lambda =0\) | \(\lambda =0.02\) | \(\lambda =0.2\) | |
MI | 3.2786 | 3.6244 | 4.0026 | 3.9525 | 4.5539 | 4.5778 | 4.2731 | 4.5115 | 4.5400 |
Qabf | 0.6387 | 0.6497 | 0.5309 | 0.7503 | 0.7555 | 0.7550 | 0.7291 | 0.7378 | 0.7382 |
VIF | 0.6050 | 0.6707 | 0.9997 | 0.8064 | 0.8788 | 0.8797 | 0.8461 | 0.8796 | 0.8827 |
SSIM | 0.6653 | 0.6554 | 0.6840 | 0.6437 | 0.6487 | 0.6445 | 0.6264 | 0.6152 | 0.6228 |
Qcb | 0.6916 | 0.6981 | 0.7283 | 0.6396 | 0.6552 | 0.6455 | 0.6759 | 0.6779 | 0.6980 |
Qcv\(\downarrow\) | 1150.90 | 1150.07 | 916.17 | 70.60 | 71.50 | 71.42 | 51.02 | 50.37 | 50.32 |
