A supervised network for fast image-guided radiotherapy (IGRT) registration

Journal of Medical Systems(2019)

引用 7|浏览22
暂无评分
摘要
3D/3D image registration in IGRT, which aligns planning Computed Tomography (CT) image set with on board Cone Beam CT (CBCT) image set in a short time with high accuracy, is still a challenge due to its high computational cost and complex anatomical structure of medical image. In order to overcome these difficulties, a new method is proposed which contains a coarse registration and a fine registration. For the coarse registration, a supervised regression convolutional neural networks (CNNs) is used to optimize the spatial variation by minimizing the loss when combine the CT images with the CBCT images. For the fine registration, intensity-based image registration is used to calculate the accurate spatial difference of the input image pairs. A coarse registration can get a rough result with a wide capture range in less than 0.5 s. Sequentially a fine registration can get accurate results in a reasonable short time. RSD-111 T chest phantom was used to test our new method. The set-up error was calculated in less than 10s in time scale, and was reduced to sub-millimeter level in spatial scale. The average residual errors in translation and rotation are within ±0.5 mm and ± 0.2°.
更多
查看译文
关键词
IGRT, CBCT, CNNs, Image registration, Intensity-based registration
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要