Research Article
Study on Optimal Generative Network for Synthesizing Brain Tumor-Segmented MR Images
Table 1
Published works on cross-modality image synthesis.
| Modality | Publication | Method | Remarks |
| CT ⟶ MR | Jin et al. [18] | CycleGAN | Brain | MR ↔ CT | Zang et al. [19] | CycleGAN | (3D) Cardiac | MR ↔ CT | Hiasa et al. [20] | CycleGAN | Musculoskeletal | MR ↔ CT | Wolterink et al. [7] | CycleGAN | Brain | T1 ↔ T2 MR | Dar et al. [21] | CycleGAN | Brain | T1 ↔ T2 MR | Welander et al. [22] | CycleGAN | Brain |
|
|
In the third column, following the method denotes some modifications either on the architecture of the network or on the employed losses. |