Abstract | ||
---|---|---|
In this paper, we proposeHybridGAN -a new medical MR image synthesis methods via generative adversarial learning. Specifically, our synthesizer generates MRI data in a sequential manner: first in order to improve the robustness of image synthesis, an input full-size real MR image is divided into an array of sub-images. Then, to avoid overfitting limited MRI encodings, these sub-images and an unlimited amount of random latent noise vectors become the input of automatic encoder for learning the marginal image distributions of real images. Finally, pseudo patches with constrained noise vectors are put intoRU-NET which is a component of ourHybridGANto generate a large number of synthetic MR images. InRU-NET, ASpliceLayeris then employed to fuse sub-images together in an interlaced manner into a full-size image. The experimental results show thatHybridGANcan effectively synthesize a large variety of MR images and display a good visual quality. Compared to the state-of-the-art synthesis methods, our method achieves a significant improvement in terms of both visual and quantitative evaluation metrics. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s11042-020-09387-3 | MULTIMEDIA TOOLS AND APPLICATIONS |
Keywords | DocType | Volume |
Generative models,Generative adversarial networks,MR image synthesis,Deep learning | Journal | 79.0 |
Issue | ISSN | Citations |
37-38 | 1380-7501 | 1 |
PageRank | References | Authors |
0.35 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jia Chen | 1 | 1 | 1.03 |
Shuang Luo | 2 | 1 | 0.35 |
Mingfu Xiong | 3 | 1 | 3.06 |
Tao Peng | 4 | 1 | 2.04 |
Ping Zhu | 5 | 1 | 1.70 |
MingHua Jiang | 6 | 13 | 10.96 |
Xiao Qin | 7 | 1836 | 125.69 |