Knowledge Commons of Institute of Automation,CAS
Fully Automatic Dual-Guidewire Segmentation for Coronary Bifurcation Lesion | |
Zhou, Yan-Jie1,3![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() | |
2019-07 | |
会议名称 | International Joint Conference on Neural Networks (IJCNN) |
会议日期 | 2019.07.14-19 |
会议地点 | Budapest, Hungary |
出版者 | IEEE |
摘要 | Interventional therapy for coronary bifurcation lesions has always been an intractable problem in percutaneous coronary intervention (PCI). Dual-guidewire detection can greatly assist physicians in interventional therapy of bifurcated lesions. Nevertheless, this task often comes with the challenges of X-ray images with a low signal noise ratio (SNR) as well as the thinner structure of the guidewire compared to other interventional tools. In this paper, a fully automatic detection method based on an improved U-Net and the modified focal loss is proposed for dual-guidewire segmentation in 2D X-ray fluoroscopy, which accomplishes accurate and robust segmentation. The main contributions of this paper are twofold: (1) the proposed method not only addresses the extreme foreground-background class imbalance generated by the slender guidewire structure but also solves the problem of misclassified examples caused by the guidewire-like structures and contrast agents; (2) the running speed is about 8 frames per second, which reaches near-real-time processing speed. Furthermore, data augmentation algorithms and transfer learning are used to further improve performance. The proposed method was verified on clinical 2D X-ray image sequences of 30 patients, in which the F1-score reached 0.932. The experiment results indicated that our approach is promising for assisting bifurcation lesion surgery. |
收录类别 | EI |
资助项目 | National Natural Science Foundation of China[61533016] ; Foundation for Innovative Research Groups of the National Natural Science Foundation of China[61421004] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDBS01040100] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDBS01040100] ; Foundation for Innovative Research Groups of the National Natural Science Foundation of China[61421004] ; National Natural Science Foundation of China[61533016] |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48551 |
专题 | 复杂系统认知与决策实验室_先进机器人 |
通讯作者 | Hou, Zeng-Guang |
作者单位 | 1.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.CAS Center for Excellence in Brain Science and Intelligence Technology, 3.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhou, Yan-Jie,Xie, Xiao-Liang,Bian, Gui-Bin,et al. Fully Automatic Dual-Guidewire Segmentation for Coronary Bifurcation Lesion[C]:IEEE,2019. |
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 | ||
10-Fully Automatic D(2076KB) | 会议论文 | 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