Artifact estimation network for MR images: effectiveness of batch normalization and dropout layers
Although this study was limited to phantom images, the same strategy may be applied to more complex tasks, such as those directed at improving the quality of MR and CT images. We conclude that the accuracy of motion artifact removal can be improved by integrating BN and dropout layers into a U-Net-based network, with due consideration of the correct location and dropout rate.
Authors
- Yusuke Sato (ORCID: https://orcid.org/0000-0003-2897-4766)
- Tomoko Maruyama (ORCID: https://orcid.org/0000-0002-3797-1615)
- Norio Hayashi (ORCID: https://orcid.org/0000-0001-9309-1113)
- Yoshihiro Kitoh
- Toshihiro Ogura
- Haruyuki Watanabe
- Masumi Uehara
Institutions
- Shinshu University Hospital (JP)
- Gunma University Hospital (JP)
- Gunma Prefectural College of Health Sciences (JP)
Publication Details
- Journal
- BMC Medical Imaging
- Published
- 2025-05-01
- DOI
- https://doi.org/10.1186/s12880-025-01663-8
- Citations
- 3
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 4.08