Enhancing the depth perception of DSA images with 2D–3D registration
ObjectiveToday, cerebrovascular disease has become an important health hazard. Therefore, it is necessary to perform a more accurate and less time-consuming registration of preoperative three-dimensional (3D) images and intraoperative two-dimensional (2D) projection images which is very important fo...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-02-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1122021/full |
| _version_ | 1828039552739049472 |
|---|---|
| author | Xiaofeng Zhang Yongzhi Deng Congyu Tian Shu Chen Yuanqing Wang Meng Zhang Qiong Wang Xiangyun Liao Weixin Si |
| author_facet | Xiaofeng Zhang Yongzhi Deng Congyu Tian Shu Chen Yuanqing Wang Meng Zhang Qiong Wang Xiangyun Liao Weixin Si |
| author_sort | Xiaofeng Zhang |
| collection | DOAJ |
| description | ObjectiveToday, cerebrovascular disease has become an important health hazard. Therefore, it is necessary to perform a more accurate and less time-consuming registration of preoperative three-dimensional (3D) images and intraoperative two-dimensional (2D) projection images which is very important for conducting cerebrovascular disease interventions. The 2D–3D registration method proposed in this study is designed to solve the problems of long registration time and large registration errors in 3D computed tomography angiography (CTA) images and 2D digital subtraction angiography (DSA) images.MethodsTo 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, using a multi-resolution fusion optimization strategy, the 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.ResultIn this study, we adopt two datasets of the brain vessels to validate and obtain similarity metric values which are 0.0037 and 0.0003, respectively. Using the registration method proposed in this study, the time taken for the experiment was calculated to be 56.55s and 50.8070s, respectively, for the two sets of data. The results show that the registration methods proposed in this study are both better than the Normalized Mutual (NM) and Normalized Mutual Information (NMI).ConclusionThe experimental results in this study show that in the 2D–3D registration process, to evaluate the registration results more accurately, we can use the similarity metric function containing the image gray information and spatial information. To improve the efficiency of the registration process, we can choose the algorithm with gradient optimization strategy. Our method has great potential to be applied in practical interventional treatment for intuitive 3D navigation. |
| first_indexed | 2024-04-10T16:42:48Z |
| format | Article |
| id | doaj.art-fbbac00d02864cf29251d496e365aa16 |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-04-10T16:42:48Z |
| publishDate | 2023-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-fbbac00d02864cf29251d496e365aa162023-02-08T05:59:12ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-02-011410.3389/fneur.2023.11220211122021Enhancing the depth perception of DSA images with 2D–3D registrationXiaofeng Zhang0Yongzhi Deng1Congyu Tian2Shu Chen3Yuanqing Wang4Meng Zhang5Qiong Wang6Xiangyun Liao7Weixin Si8Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaDepartment of Cardiovascular Surgery, Shanxi Clinical Medical Research Center for Cardiovascular Disease, Shanxi Institute of Cardiovascular Diseases, Shanxi Cardiovascular Hospital, Shanxi Medical University, Taiyuan, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaDepartment of Cardiovascular Surgery, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, ChinaShenzhen Second People's Hospital, Shenzhen, ChinaShenzhen Second People's Hospital, Shenzhen, ChinaGuangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaObjectiveToday, cerebrovascular disease has become an important health hazard. Therefore, it is necessary to perform a more accurate and less time-consuming registration of preoperative three-dimensional (3D) images and intraoperative two-dimensional (2D) projection images which is very important for conducting cerebrovascular disease interventions. The 2D–3D registration method proposed in this study is designed to solve the problems of long registration time and large registration errors in 3D computed tomography angiography (CTA) images and 2D digital subtraction angiography (DSA) images.MethodsTo 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, using a multi-resolution fusion optimization strategy, the 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.ResultIn this study, we adopt two datasets of the brain vessels to validate and obtain similarity metric values which are 0.0037 and 0.0003, respectively. Using the registration method proposed in this study, the time taken for the experiment was calculated to be 56.55s and 50.8070s, respectively, for the two sets of data. The results show that the registration methods proposed in this study are both better than the Normalized Mutual (NM) and Normalized Mutual Information (NMI).ConclusionThe experimental results in this study show that in the 2D–3D registration process, to evaluate the registration results more accurately, we can use the similarity metric function containing the image gray information and spatial information. To improve the efficiency of the registration process, we can choose the algorithm with gradient optimization strategy. Our method has great potential to be applied in practical interventional treatment for intuitive 3D navigation.https://www.frontiersin.org/articles/10.3389/fneur.2023.1122021/full2D–3D registrationweighted similarity measure functionmulti-resolution fusion optimization strategypyramid convolutiontreatment of cerebrovascular diseases |
| spellingShingle | Xiaofeng Zhang Yongzhi Deng Congyu Tian Shu Chen Yuanqing Wang Meng Zhang Qiong Wang Xiangyun Liao Weixin Si Enhancing the depth perception of DSA images with 2D–3D registration Frontiers in Neurology 2D–3D registration weighted similarity measure function multi-resolution fusion optimization strategy pyramid convolution treatment of cerebrovascular diseases |
| title | Enhancing the depth perception of DSA images with 2D–3D registration |
| title_full | Enhancing the depth perception of DSA images with 2D–3D registration |
| title_fullStr | Enhancing the depth perception of DSA images with 2D–3D registration |
| title_full_unstemmed | Enhancing the depth perception of DSA images with 2D–3D registration |
| title_short | Enhancing the depth perception of DSA images with 2D–3D registration |
| title_sort | enhancing the depth perception of dsa images with 2d 3d registration |
| topic | 2D–3D registration weighted similarity measure function multi-resolution fusion optimization strategy pyramid convolution treatment of cerebrovascular diseases |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1122021/full |
| work_keys_str_mv | AT xiaofengzhang enhancingthedepthperceptionofdsaimageswith2d3dregistration AT yongzhideng enhancingthedepthperceptionofdsaimageswith2d3dregistration AT congyutian enhancingthedepthperceptionofdsaimageswith2d3dregistration AT shuchen enhancingthedepthperceptionofdsaimageswith2d3dregistration AT yuanqingwang enhancingthedepthperceptionofdsaimageswith2d3dregistration AT mengzhang enhancingthedepthperceptionofdsaimageswith2d3dregistration AT qiongwang enhancingthedepthperceptionofdsaimageswith2d3dregistration AT xiangyunliao enhancingthedepthperceptionofdsaimageswith2d3dregistration AT weixinsi enhancingthedepthperceptionofdsaimageswith2d3dregistration |