Learning from adversarial medical images for X-ray breast mass segmentation
文献类型：期刊论文
| 作者 | Shen, Tianyu1,2,3 ; Gou, Chao4; Wang, Fei-Yue1,2; He, Zilong5; Chen, Weiguo5
|
| 刊名 | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
 |
| 出版日期 | 2019-10-01 |
| 卷号 | 180页码:13 |
| 关键词 | Medical image synthesis Generative adversarial network X-ray breast mass Lesion segmentation |
| ISSN号 | 0169-2607 |
| DOI | 10.1016/j.cmpb.2019.105012 |
| 通讯作者 | Gou, Chao(gouchao.cas@gmail.com) ; Chen, Weiguo(chenweiguo1964@21cn.com) |
| 英文摘要 | Background and Objective: Simulation of diverse lesions in images is proposed and applied to overcome the scarcity of labeled data, which has hindered the application of deep learning in medical imaging. However, most of current studies focus on generating samples with class labels for classification and detection rather than segmentation, because generating images with precise masks remains a challenge. Therefore, we aim to generate realistic medical images with precise masks for improving lesion segmentation in mammagrams. Methods: In this paper, we propose a new framework for improving X-ray breast mass segmentation performance aided by generated adversarial lesion images with precise masks. Firstly, we introduce a conditional generative adversarial network (cGAN) to learn the distribution of real mass images as well as a mapping between images and corresponding segmentation masks. Subsequently, a number of lesion images are generated from various binary input masks using the generator in the trained cGAN. Then the generated adversarial samples are concatenated with original samples to produce a dataset with increased diversity. Furthermore, we introduce an improved U-net and train it on the previous augmented dataset for breast mass segmentation. Results: To demonstrate the effectiveness of our proposed method, we conduct experiments on publicly available mammogram database of INbreast and a private database provided by Nanfang Hospital in China. Experimental results show that an improvement up to 7% in Jaccard index can be achieved over the same model trained on original real lesion images. Conclusions: Our proposed method can be viewed as one of the first steps toward generating realistic X-ray breast mass images with masks for precise segmentation. (C) 2019 Elsevier B.V. All rights reserved. |
| WOS关键词 | SIMULATION ; INSERTION ; NODULES ; LESIONS |
| 资助项目 | National Natural Science Foundation of China[61806198] ; National Natural Science Foundation of China[61533019] ; Project of Youth Foundation of the State Key Laboratory for Management and Control of Complex Systems[Y6S9011F4N] |
| WOS研究方向 | Computer Science ; Engineering ; Medical Informatics |
| 语种 | 英语 |
| WOS记录号 | WOS:000488005200001 |
| 出版者 | ELSEVIER IRELAND LTD |
| 资助机构 | National Natural Science Foundation of China ; Project of Youth Foundation of the State Key Laboratory for Management and Control of Complex Systems |
| 源URL | [http://ir.ia.ac.cn/handle/173211/27007]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
| 通讯作者 | Gou, Chao; Chen, Weiguo |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Zhongguancun East Rd 95, Beijing 100190, Peoples R China 2.Qingdao Acad Intelligent Ind, Zhilidao Rd 1, Qingdao 266000, Shandong, Peoples R China 3.Univ Chinese Acad Sci, Beijing 049, Peoples R China 4.Sun Yat Sen Univ, Sch Intelligent Syst Engn, Guangzhou 510275, Guangdong, Peoples R China 5.Southern Med Univ, Nanfang Hosp, Dept Radiol, Guangzhou 510515, Guangdong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Shen, Tianyu,Gou, Chao,Wang, Fei-Yue,et al. Learning from adversarial medical images for X-ray breast mass segmentation[J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE,2019,180:13. |
| APA | Shen, Tianyu,Gou, Chao,Wang, Fei-Yue,He, Zilong,&Chen, Weiguo.(2019).Learning from adversarial medical images for X-ray breast mass segmentation.COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE,180,13. |
| MLA | Shen, Tianyu,et al."Learning from adversarial medical images for X-ray breast mass segmentation".COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 180(2019):13. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。