Deformable Cardiovascular Image Registration via Multi-Channel Convolutional Neural Network
Vascular image registration is an essential approach to combine the advantages of preoperative 3D computed tomography angiography images and intraoperative 2D X-ray/digital subtraction angiography (DSA) images together. Cardiovascular deformation caused by heartbeat and respiration is one of the mos...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8633360/ |
| _version_ | 1818641568287948800 |
|---|---|
| author | Shaoya Guan Cai Meng Yi Xie Qi Wang Kai Sun Tianmiao Wang |
| author_facet | Shaoya Guan Cai Meng Yi Xie Qi Wang Kai Sun Tianmiao Wang |
| author_sort | Shaoya Guan |
| collection | DOAJ |
| description | Vascular image registration is an essential approach to combine the advantages of preoperative 3D computed tomography angiography images and intraoperative 2D X-ray/digital subtraction angiography (DSA) images together. Cardiovascular deformation caused by heartbeat and respiration is one of the most vital factors that affect vascular image registration accuracy. Traditional optimized-based registration methods suffer severely from high computational complexity, which hinders the clinical applications of these methods seriously. To overcome these challenges, we developed a novel multi-channel convolutional neural network (MCNN) that combines a CNN with a periodic vascular diameter variation model. Our method is capable of registering simulated DSA images or real DSA images with their corresponding 3D models in a matter of milliseconds. Our presented MCNN model achieves excellent registration results of three different kinds of cardiovascular patients. The mean absolute error of all six transformation parameters of the MCNN model presented in this paper is less than 1 mm or 1°. The improvement to our MCNN model in registration accuracy is larger than 75% over a single-channel CNN model. Our MCNN method performs more effectively and stable than the state-of-the-art intensity-based methods, especially when vascular deformations occur. |
| first_indexed | 2024-12-16T23:29:14Z |
| format | Article |
| id | doaj.art-476f6deef9dd434286391afa55086f20 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T23:29:14Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-476f6deef9dd434286391afa55086f202022-12-21T22:11:56ZengIEEEIEEE Access2169-35362019-01-017175241753410.1109/ACCESS.2019.28949438633360Deformable Cardiovascular Image Registration via Multi-Channel Convolutional Neural NetworkShaoya Guan0https://orcid.org/0000-0002-3642-0192Cai Meng1https://orcid.org/0000-0002-0711-5949Yi Xie2Qi Wang3https://orcid.org/0000-0003-3462-5458Kai Sun4Tianmiao Wang5School of Mechanical Engineering and Automation, Beihang University, Beijing, ChinaSchool of Astronautics, Beihang University, Beijing, ChinaSchool of Astronautics, Beihang University, Beijing, ChinaSchool of Astronautics, Beihang University, Beijing, ChinaSchool of Astronautics, Beihang University, Beijing, ChinaSchool of Mechanical Engineering and Automation, Beihang University, Beijing, ChinaVascular image registration is an essential approach to combine the advantages of preoperative 3D computed tomography angiography images and intraoperative 2D X-ray/digital subtraction angiography (DSA) images together. Cardiovascular deformation caused by heartbeat and respiration is one of the most vital factors that affect vascular image registration accuracy. Traditional optimized-based registration methods suffer severely from high computational complexity, which hinders the clinical applications of these methods seriously. To overcome these challenges, we developed a novel multi-channel convolutional neural network (MCNN) that combines a CNN with a periodic vascular diameter variation model. Our method is capable of registering simulated DSA images or real DSA images with their corresponding 3D models in a matter of milliseconds. Our presented MCNN model achieves excellent registration results of three different kinds of cardiovascular patients. The mean absolute error of all six transformation parameters of the MCNN model presented in this paper is less than 1 mm or 1°. The improvement to our MCNN model in registration accuracy is larger than 75% over a single-channel CNN model. Our MCNN method performs more effectively and stable than the state-of-the-art intensity-based methods, especially when vascular deformations occur.https://ieeexplore.ieee.org/document/8633360/2D/3D Registrationconvolutional neural networkmulti channelperiodic variation modelvascular deformation |
| spellingShingle | Shaoya Guan Cai Meng Yi Xie Qi Wang Kai Sun Tianmiao Wang Deformable Cardiovascular Image Registration via Multi-Channel Convolutional Neural Network IEEE Access 2D/3D Registration convolutional neural network multi channel periodic variation model vascular deformation |
| title | Deformable Cardiovascular Image Registration via Multi-Channel Convolutional Neural Network |
| title_full | Deformable Cardiovascular Image Registration via Multi-Channel Convolutional Neural Network |
| title_fullStr | Deformable Cardiovascular Image Registration via Multi-Channel Convolutional Neural Network |
| title_full_unstemmed | Deformable Cardiovascular Image Registration via Multi-Channel Convolutional Neural Network |
| title_short | Deformable Cardiovascular Image Registration via Multi-Channel Convolutional Neural Network |
| title_sort | deformable cardiovascular image registration via multi channel convolutional neural network |
| topic | 2D/3D Registration convolutional neural network multi channel periodic variation model vascular deformation |
| url | https://ieeexplore.ieee.org/document/8633360/ |
| work_keys_str_mv | AT shaoyaguan deformablecardiovascularimageregistrationviamultichannelconvolutionalneuralnetwork AT caimeng deformablecardiovascularimageregistrationviamultichannelconvolutionalneuralnetwork AT yixie deformablecardiovascularimageregistrationviamultichannelconvolutionalneuralnetwork AT qiwang deformablecardiovascularimageregistrationviamultichannelconvolutionalneuralnetwork AT kaisun deformablecardiovascularimageregistrationviamultichannelconvolutionalneuralnetwork AT tianmiaowang deformablecardiovascularimageregistrationviamultichannelconvolutionalneuralnetwork |