MA-VoxelMorph: Multi-scale attention-based VoxelMorph for nonrigid registration of thoracoabdominal CT images
This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement. However, fine structure registration of complex thoracoabdominal...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Publishing
2025-01-01
|
| Series: | Journal of Innovative Optical Health Sciences |
| Subjects: | |
| Online Access: | https://www.worldscientific.com/doi/10.1142/S1793545824500226 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585108707606528 |
|---|---|
| author | Qing Huang Lei Ren Tingwei Quan Minglei Yang Hongmei Yuan Kai Cao |
| author_facet | Qing Huang Lei Ren Tingwei Quan Minglei Yang Hongmei Yuan Kai Cao |
| author_sort | Qing Huang |
| collection | DOAJ |
| description | This paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement. However, fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging. To deal with this problem, we propose a 3D multi-scale attention VoxelMorph (MA-VoxelMorph) registration network. To alleviate the large deformation problem, a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction, and position-aware axial attention for long-distance dependencies between pixels capture. To further improve the large deformation and fine structure registration results, a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers. Our method was evaluated on four public lung datasets (DIR-Lab dataset, Creatis dataset, Learn2Reg dataset, OASIS dataset) and a local dataset. Results proved that the proposed method achieved better registration performance than current state-of-the-art methods, especially in handling the registration of large deformations and fine structures. It also proved to be fast in 3D image registration, using about 1.5 s, and faster than most methods. Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries. |
| format | Article |
| id | doaj-art-f4aed34b77f4446d856e81b2781db110 |
| institution | Kabale University |
| issn | 1793-5458 1793-7205 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | World Scientific Publishing |
| record_format | Article |
| series | Journal of Innovative Optical Health Sciences |
| spelling | doaj-art-f4aed34b77f4446d856e81b2781db1102025-01-27T05:49:52ZengWorld Scientific PublishingJournal of Innovative Optical Health Sciences1793-54581793-72052025-01-01180110.1142/S1793545824500226MA-VoxelMorph: Multi-scale attention-based VoxelMorph for nonrigid registration of thoracoabdominal CT imagesQing Huang0Lei Ren1Tingwei Quan2Minglei Yang3Hongmei Yuan4Kai Cao5School of Computer Science & Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, Hubei 430205, P. R. ChinaSchool of Computer Science & Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, Hubei 430205, P. R. ChinaBritton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics-Huazhong, University of Science and Technology, Wuhan, Hubei 430074, P. R. ChinaBeijing Wandong Medical Technology Co., Ltd., Beijing 100015, P. R. ChinaBeijing Wandong Medical Technology Co., Ltd., Beijing 100015, P. R. ChinaChanghai Hospital of Shanghai, Shanghai 200433, P. R. ChinaThis paper aims to develop a nonrigid registration method of preoperative and intraoperative thoracoabdominal CT images in computer-assisted interventional surgeries for accurate tumor localization and tissue visualization enhancement. However, fine structure registration of complex thoracoabdominal organs and large deformation registration caused by respiratory motion is challenging. To deal with this problem, we propose a 3D multi-scale attention VoxelMorph (MA-VoxelMorph) registration network. To alleviate the large deformation problem, a multi-scale axial attention mechanism is utilized by using a residual dilated pyramid pooling for multi-scale feature extraction, and position-aware axial attention for long-distance dependencies between pixels capture. To further improve the large deformation and fine structure registration results, a multi-scale context channel attention mechanism is employed utilizing content information via adjacent encoding layers. Our method was evaluated on four public lung datasets (DIR-Lab dataset, Creatis dataset, Learn2Reg dataset, OASIS dataset) and a local dataset. Results proved that the proposed method achieved better registration performance than current state-of-the-art methods, especially in handling the registration of large deformations and fine structures. It also proved to be fast in 3D image registration, using about 1.5 s, and faster than most methods. Qualitative and quantitative assessments proved that the proposed MA-VoxelMorph has the potential to realize precise and fast tumor localization in clinical interventional surgeries.https://www.worldscientific.com/doi/10.1142/S1793545824500226Thoracoabdominal CT image registrationlarge deformationfine structuremulti-scaleattention mechanism |
| spellingShingle | Qing Huang Lei Ren Tingwei Quan Minglei Yang Hongmei Yuan Kai Cao MA-VoxelMorph: Multi-scale attention-based VoxelMorph for nonrigid registration of thoracoabdominal CT images Journal of Innovative Optical Health Sciences Thoracoabdominal CT image registration large deformation fine structure multi-scale attention mechanism |
| title | MA-VoxelMorph: Multi-scale attention-based VoxelMorph for nonrigid registration of thoracoabdominal CT images |
| title_full | MA-VoxelMorph: Multi-scale attention-based VoxelMorph for nonrigid registration of thoracoabdominal CT images |
| title_fullStr | MA-VoxelMorph: Multi-scale attention-based VoxelMorph for nonrigid registration of thoracoabdominal CT images |
| title_full_unstemmed | MA-VoxelMorph: Multi-scale attention-based VoxelMorph for nonrigid registration of thoracoabdominal CT images |
| title_short | MA-VoxelMorph: Multi-scale attention-based VoxelMorph for nonrigid registration of thoracoabdominal CT images |
| title_sort | ma voxelmorph multi scale attention based voxelmorph for nonrigid registration of thoracoabdominal ct images |
| topic | Thoracoabdominal CT image registration large deformation fine structure multi-scale attention mechanism |
| url | https://www.worldscientific.com/doi/10.1142/S1793545824500226 |
| work_keys_str_mv | AT qinghuang mavoxelmorphmultiscaleattentionbasedvoxelmorphfornonrigidregistrationofthoracoabdominalctimages AT leiren mavoxelmorphmultiscaleattentionbasedvoxelmorphfornonrigidregistrationofthoracoabdominalctimages AT tingweiquan mavoxelmorphmultiscaleattentionbasedvoxelmorphfornonrigidregistrationofthoracoabdominalctimages AT mingleiyang mavoxelmorphmultiscaleattentionbasedvoxelmorphfornonrigidregistrationofthoracoabdominalctimages AT hongmeiyuan mavoxelmorphmultiscaleattentionbasedvoxelmorphfornonrigidregistrationofthoracoabdominalctimages AT kaicao mavoxelmorphmultiscaleattentionbasedvoxelmorphfornonrigidregistrationofthoracoabdominalctimages |