AUTHOR=Zhang Xiaofeng , Deng Yongzhi , Tian Congyu , Chen Shu , Wang Yuanqing , Zhang Meng , Wang Qiong , Liao Xiangyun , Si Weixin 

TITLE=Enhancing the depth perception of DSA images with 2D–3D registration

JOURNAL=Frontiers in Neurology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2023.1122021

DOI=10.3389/fneur.2023.1122021

ISSN=1664-2295

ABSTRACT=Objective: With cerebrovascular disease becoming an important health hazard, performing a more accurate and less time-consuming registration of preoperative 3D images
and intraoperative 2D projection images is of great importance for cerebrovascular disease
interventions. Our proposed 2D-3D registration method is designed to solve the problems of long registration time and large registration errors in 3D CTA images and 2D DSA image.

Methods: To make a more comprehensive and active diagnosis, treatment and surgery plan for patients with cerebrovascular diseases, we propose a weighted similarity measure function, the normalized mutual information-gradient difference (NMG), which can evaluate the 2D-3D registration results. Then a multi-resolution fusion optimization strategy, use multi-resolution fused regular step gradient descent optimization (MR-RSGD) method is presented to attain the optimal value of the registration results in the process of the optimization algorithm. 


Result: In this paper, we adopt two datasets of brain vessels to validate and obtain similarity metric values are 0.0037 and 0.0003, using the registration method proposed in this paper, the time taken for the experiment was 56.55s and 50.8070s for the two sets of data. The results show that the registration methods proposed in this paper are both better than NM and NMI.

Conclusion: The experimental results in this paper show that in the 2D-3D registration process, in order to more accurately evaluate the registration results, we can use the similarity metric function containing the image gray information and spatial information. In order to improve the efficiency of the registration process, we can choose the algorithm with gradient optimization strategy. Our method has the great potential to be applied in practical interventional treatment for intuitive 3D navigation.