MinimalGAN: diverse medical image synthesis for data augmentation using minimal training data | |
Zhang, Yipeng1,2,3; Wang, Quan1,2; Hu, Bingliang1,2 | |
作者部门 | 光谱成像技术研究室 |
发表期刊 | APPLIED INTELLIGENCE |
ISSN | 0924-669X;1573-7497 |
产权排序 | 1 |
摘要 | Image synthesis techniques have limited application in the medical field due to unsatisfactory authenticity and precision. Additionally, synthesizing diverse outputs is challenging when the training data are insufficient, as in many medical datasets. In this work, we propose an image-to-image network named the Minimal Generative Adversarial Network (MinimalGAN), to synthesize annotated, accurate, and diverse medical images with minimal training data. The primary concept is to make full use of the internal information of the image and decouple the style from the content by separating them in the self-coding process. After that, the generator is compelled to concentrate on content detail and style separately to synthesize diverse and high-precision images. The proposed MinimalGAN includes two image synthesis techniques; the first is style transfer. We synthesized a stylized retinal fundus dataset. The style transfer deception rate is much higher than that of traditional style transfer methods. The blood vessel segmentation performance increased when only using synthetic data. The other image synthesis technique is target variation. Unlike the traditional translation, rotation, and scaling on the whole image, this approach only performs the above operations on the segmented target being annotated. Experiments demonstrate that segmentation performance improved after utilizing synthetic data. |
关键词 | Image generation Data augmentation Image segmentation Medical imaging |
DOI | 10.1007/s10489-022-03609-x |
收录类别 | SCI ; EI |
语种 | 英语 |
WOS记录号 | WOS:000805752800005 |
出版者 | SPRINGER |
EI入藏号 | 20222312202688 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/95995 |
专题 | 光谱成像技术研究室 |
通讯作者 | Wang, Quan; Hu, Bingliang |
作者单位 | 1.Key Laboratory of Spectral Imaging Technology, Xi’an Institute of Optics and Precision Mechanics of the Chinese Academy of Sciences, Shaanxi, Xi’an; 710119, China 2.The Key Laboratory of Biomedical Spectroscopy of Xi’an, Shaanxi, Xi’an; 710119, China 3.School of Optoelectronics, University of Chinese Academy of Sciences, Beijing; 100190, China |
推荐引用方式 GB/T 7714 | Zhang, Yipeng,Wang, Quan,Hu, Bingliang. MinimalGAN: diverse medical image synthesis for data augmentation using minimal training data[J]. APPLIED INTELLIGENCE. |
APA | Zhang, Yipeng,Wang, Quan,&Hu, Bingliang. |
MLA | Zhang, Yipeng,et al."MinimalGAN: diverse medical image synthesis for data augmentation using minimal training data".APPLIED INTELLIGENCE |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
MinimalGAN diverse m(8189KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论