Name
Title | ||
|---|---|---|
Low-dose chest X-ray image super-resolution using generative adversarial nets with spectral normalization |
Abstract | ||
|---|---|---|
•Auxiliary label information is introduced to constrain the feature generation to attack the potential risk of pathological invariance, i.e., pathological information should not be changed.•Spectral normalization is introduced into the GANs-based medical image super-resolution to control the performance of the discriminator with theoretical guarantee.•Experiments about gradient convergence is conducted, which is used to prove the positive function of spectral normalization.•A more comprehensive evaluation is conducted, including objective evaluation, generative performance of GANs and assessment on diagnostic quality. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.bspc.2019.101600 | Biomedical Signal Processing and Control |
Keywords | Field | DocType |
Auxiliary information,Pathological invariance,Generative adversarial nets,Spectral normalization | Normalization (statistics),Discriminator,Pattern recognition,Qualitative Evaluations,Artificial intelligence,Feature generation,Generative grammar,Superresolution,Discriminative model,Mathematics | Journal |
Volume | ISSN | Citations |
55 | 1746-8094 | 1 |
PageRank | References | Authors |
0.36 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Liming Xu | 1 | 1 | 2.39 |
| Xianhua Zeng | 2 | 11 | 3.84 |
| Zhiwei Huang | 3 | 1 | 2.05 |
| Weisheng Li | 4 | 37 | 19.68 |
| He Zhang | 5 | 1 | 0.36 |