期刊
MEDICAL IMAGE ANALYSIS
卷 79, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.media.2022.102461
关键词
Ultrasound image synthesis; Generative adversarial networks; COVID-19; Hip joint; Ovary and follicle
类别
资金
- National Nat-ural Science Foundation of China [62171290, 62101343, 61901275]
- Shenzhen-Hong Kong Joint Research Program [SGDX20201103095613036]
- SZU Top Ranking Project [860 0 0 0 0 0210]
- Shenzhen Science and Technology Innovations Committee [2020 08121434410 01]
- Shenzhen University Startup Fund [2019131]
This paper proposes a generative adversarial network (GAN) based image synthesis framework for generating realistic and high-resolution B-mode ultrasound (US) images. The framework incorporates auxiliary sketch guidance and a progressive training strategy to enhance structural details and resolution of the generated images. The method is versatile and has been validated on multiple US image datasets of different anatomical structures.
Ultrasound (US) imaging is widely used for anatomical structure inspection in clinical diagnosis. The training of new sonographers and deep learning based algorithms for US image analysis usually requires a large amount of data. However, obtaining and labeling large-scale US imaging data are not easy tasks, especially for diseases with low incidence. Realistic US image synthesis can alleviate this problem to a great extent. In this paper, we propose a generative adversarial network (GAN) based image synthesis framework. Our main contributions include: (1) we present the first work that can synthesize realistic B mode US images with high-resolution and customized texture editing features; (2) to enhance structural details of generated images, we propose to introduce auxiliary sketch guidance into a conditional GAN. We superpose the edge sketch onto the object mask and use the composite mask as the network input; (3) to generate high-resolution US images, we adopt a progressive training strategy to gradually generate high-resolution images from low-resolution images. In addition, a feature loss is proposed to minimize the difference of high-level features between the generated and real images, which further improves the quality of generated images; (4) the proposed US image synthesis method is quite universal and can also be generalized to the US images of other anatomical structures besides the three ones tested in our study (lung, hip joint, and ovary); (5) extensive experiments on three large US image datasets are conducted to validate our method. Ablation studies, customized texture editing, user studies, and segmentation tests demonstrate promising results of our method in synthesizing realistic US images. (c) 2022 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据