Knowledge Commons of Institute of Automation,CAS
Mass Image Synthesis in Mammogram with Contextual Information Based on GANs | |
Shen, Tianyu2,3; Hao, Kunkun4; Gou, Chao1; Wang, Fei-Yue2,5,6 | |
发表期刊 | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE |
ISSN | 0169-2607 |
2021-04-01 | |
卷号 | 202期号:2021页码:9 |
摘要 | Background and Objective: In medical imaging, the scarcity of labeled lesion data has hindered the application of many deep learning algorithms. To overcome this problem, the simulation of diverse lesions in medical images is proposed. However, synthesizing labeled mass images in mammograms is still challenging due to the lack of consistent patterns in shape, margin, and contextual information. Therefore, we aim to generate various labeled medical images based on contextual information in mammograms. Methods: In this paper, we propose a novel approach based on GANs to generate various mass images and then perform contextual infilling by inserting the synthetic lesions into healthy screening mammograms. Through incorporating features of both realistic mass images and corresponding masks into the adversarial learning scheme, the generator can not only learn the distribution of the real mass images but also capture the matching shape, margin and context information. Results: To demonstrate the effectiveness of our proposed method, we conduct experiments on publicly available mammogram database of DDSM and a private database provided by Nanfang Hospital in China. Qualitative and quantitative evaluations validate the effectiveness of our approach. Additionally, through the data augmentation by image generation of the proposed method, an improvement of 5.03% in detection rate can be achieved over the same model trained on original real lesion images. Conclusions: The results show that the data augmentation based on our method increases the diversity of dataset. Our method can be viewed as one of the first steps toward generating labeled breast mass images for precise detection and can be extended in other medical imaging domains to solve similar problems. ? 2021 Elsevier B.V. All rights reserved. Background and Objective: In medical imaging, the scarcity of labeled lesion data has hindered the application of many deep learning algorithms. To overcome this problem, the simulation of diverse lesions in medical images is proposed. However, synthesizing labeled mass images in mammograms is still challenging due to the lack of consistent patterns in shape, margin, and contextual information. Therefore, we aim to generate various labeled medical images based on contextual information in mammograms. Methods: In this paper, we propose a novel approach based on GANs to generate various mass images and then perform contextual infilling by inserting the synthetic lesions into healthy screening mammograms. Through incorporating features of both realistic mass images and corresponding masks into the adversarial learning scheme, the generator can not only learn the distribution of the real mass images but also capture the matching shape, margin and context information. Results: To demonstrate the effectiveness of our proposed method, we conduct experiments on publicly available mammogram database of DDSM and a private database provided by Nanfang Hospital in China. Qualitative and quantitative evaluations validate the effectiveness of our approach. Additionally, through the data augmentation by image generation of the proposed method, an improvement of 5.03% in detection rate can be achieved over the same model trained on original real lesion images. Conclusions: The results show that the data augmentation based on our method increases the diversity of dataset. Our method can be viewed as one of the first steps toward generating labeled breast mass images for precise detection and can be extended in other medical imaging domains to solve similar problems. |
关键词 | medical image synthesis generative adversarial network mammogram mass detection |
DOI | 10.1016/j.cmpb.2021.106019 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key R&D Program of China[2020YFB1600400] ; National Natural Science Foundation of China[61806198] ; National Natural Science Foundation of China[61533019] |
项目资助者 | National Key R&D Program of China ; National Natural Science Foundation of China |
WOS研究方向 | Computer Science ; Engineering ; Medical Informatics |
WOS类目 | Computer Science, Interdisciplinary Applications ; Computer Science, Theory & Methods ; Engineering, Biomedical ; Medical Informatics |
WOS记录号 | WOS:000639096300010 |
出版者 | ELSEVIER IRELAND LTD |
七大方向——子方向分类 | 医学影像处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44264 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
通讯作者 | Gou, Chao |
作者单位 | 1.Sun Yat Sen Univ, Sch Intelligent Syst Engn, Guangzhou, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 4.Xian Fiaotong Univ, Sch Software Engn, Xian, Peoples R China 5.Qingdao Acad Intelligent Ind, Qingdao, Peoples R China 6.Macau Univ Sci & Technol, Inst Syst Engn, Macau, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Shen, Tianyu,Hao, Kunkun,Gou, Chao,et al. Mass Image Synthesis in Mammogram with Contextual Information Based on GANs[J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE,2021,202(2021):9. |
APA | Shen, Tianyu,Hao, Kunkun,Gou, Chao,&Wang, Fei-Yue.(2021).Mass Image Synthesis in Mammogram with Contextual Information Based on GANs.COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE,202(2021),9. |
MLA | Shen, Tianyu,et al."Mass Image Synthesis in Mammogram with Contextual Information Based on GANs".COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 202.2021(2021):9. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Mass Image Synthesis(2029KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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