Application of deep learning with perceptual loss in conventional MR image translation(PDF)
《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]
- Issue:
- 2021年第2期
- Page:
- 178-185
- Research Field:
- 医学影像物理
- Publishing date:
Info
- Title:
- Application of deep learning with perceptual loss in conventional MR image translation
- Author(s):
- ZHANG Zeru1; 2; LI Zhaotong1; 2; LIU Liangyou1; 2; GAO Song1; WU Fengliang3
- 1. Institute of Medical Technology, Peking University Health Science Center, Beijing 100191, China 2. School of Health Humanities, Peking University, Beijing 100191, China 3. Department of Orthopedics, Peking University Third Hospital, Beijing 100191, China
- Keywords:
- Keywords: magnetic resonance imaging multi-modalities image translation generative adversarial network
- PACS:
- R445.2;R318
- DOI:
- DOI:10.3969/j.issn.1005-202X.2021.02.010
- Abstract:
- Abstract: Objective To research the feasibility of using deep neural networks to achieve image-to-image translation on conventional magnetic resonance (MR) images in a completely unsupervised way. Methods Perception loss was introduced into cycle generative adversarial network (CycleGAN), so that the proposed network could use the adversarial loss to learn image structure information, and combine cycle consistency loss with perceptual loss to generate high-quality MR image. The generated image was compared quantitatively with those generated by CycleGAN model and supervised CycleGAN model (S_CycleGAN). Results The quantitative evaluation showed that the proposed network with the introduction of perceptual loss was superior to CycleGAN model on imaging, and that the evaluation result of the T1-weighted image generated by the proposed network was also better than that of the image generated by S_CycleGAN model. However, the evaluation results of the T2-weighted images generated by the proposed network and S_CycleGAN model were similar. Conclusion The introduction of perceptual loss to CycleGAN can generate high-quality MR images in a completely unsupervised way, and then realize image-to-image translation on high-quality conventional MR images.
Last Update: 2021-02-02