Lung CT Synthesis on Lung CT (synthetic sample set)
0.395MS-SSIM (Full Range)VQVAE
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| VQVAEApproach=Baseline, Reconstruction Model=-2026.03 | 0.395 | 0.37 | 0.405 | 0.432 | 0.756 | |
| WGAN-GPApproach=Baseline, Reconstruction Model=-2026.03 | 0.392 | 0.371 | 0.384 | 0.371 | 0.617 | |
| WGAN-GPApproach=Multi-channel, Reconstruction Model=MLP02026.03 | 0.382 | 0.335 | 0.357 | 0.402 | 0.642 | |
| WGAN-GPApproach=Multi-channel, Reconstruction Model=CNN3×3×32026.03 | 0.373 | 0.357 | 0.373 | 0.404 | 0.653 | |
| VQVAEApproach=Multi-channel, Reconstruction Model=CNN3×3×32026.03 | 0.365 | 0.329 | 0.368 | 0.371 | 0.754 | |
| VQVAEApproach=Multi-decoder, Reconstruction Model=CNN3×3×32026.03 | 0.365 | 0.341 | 0.368 | 0.354 | 0.701 | |
| VQVAEApproach=Multi-head, Reconstruction Model=MLP02026.03 | 0.365 | 0.311 | 0.373 | 0.363 | 0.698 | |
| VQVAEApproach=Multi-head, Reconstruction Model=CNN3×3×32026.03 | 0.362 | 0.329 | 0.361 | 0.354 | 0.714 | |
| VQVAEApproach=Multi-channel, Reconstruction Model=MLP02026.03 | 0.359 | 0.336 | 0.363 | 0.337 | 0.646 | |
| Score-based DMApproach=Multi-channel, Reconstruction Model=MLP02026.03 | 0.352 | 0.293 | 0.355 | 0.34 | 0.642 | |
| Score-based DMApproach=Baseline, Reconstruction Model=-2026.03 | 0.343 | 0.291 | 0.356 | 0.339 | 0.659 | |
| VQVAEApproach=Multi-decoder, Reconstruction Model=MLP02026.03 | 0.339 | 0.309 | 0.343 | 0.311 | 0.694 | |
| Test Dataset2026.03 | 0.337 | 0.321 | 0.348 | 0.327 | 0.644 | |
| Score-based DMApproach=Multi-channel, Reconstruction Model=CNN3×3×32026.03 | 0.331 | 0.296 | 0.358 | 0.344 | 0.642 |