Edge-Aware Pyramidal Deformable Network for Unsupervised Registration of Brain MR Images
Deformable image registration is of essential important for clinical diagnosis, treatment planning, and surgical navigation. However, most existing registration solutions require separate rigid alignment before deformable registration, and may not well handle the large deformation circumstances. We...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-01-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2020.620235/full |
| _version_ | 1818614187921768448 |
|---|---|
| author | Yiqin Cao Zhenyu Zhu Yi Rao Chenchen Qin Di Lin Qi Dou Dong Ni Yi Wang |
| author_facet | Yiqin Cao Zhenyu Zhu Yi Rao Chenchen Qin Di Lin Qi Dou Dong Ni Yi Wang |
| author_sort | Yiqin Cao |
| collection | DOAJ |
| description | Deformable image registration is of essential important for clinical diagnosis, treatment planning, and surgical navigation. However, most existing registration solutions require separate rigid alignment before deformable registration, and may not well handle the large deformation circumstances. We propose a novel edge-aware pyramidal deformable network (referred as EPReg) for unsupervised volumetric registration. Specifically, we propose to fully exploit the useful complementary information from the multi-level feature pyramids to predict multi-scale displacement fields. Such coarse-to-fine estimation facilitates the progressive refinement of the predicted registration field, which enables our network to handle large deformations between volumetric data. In addition, we integrate edge information with the original images as dual-inputs, which enhances the texture structures of image content, to impel the proposed network pay extra attention to the edge-aware information for structure alignment. The efficacy of our EPReg was extensively evaluated on three public brain MRI datasets including Mindboggle101, LPBA40, and IXI30. Experiments demonstrate our EPReg consistently outperformed several cutting-edge methods with respect to the metrics of Dice index (DSC), Hausdorff distance (HD), and average symmetric surface distance (ASSD). The proposed EPReg is a general solution for the problem of deformable volumetric registration. |
| first_indexed | 2024-12-16T16:14:02Z |
| format | Article |
| id | doaj.art-1edf9b16f58d4d26b0f4a8d4ae1d78e1 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-16T16:14:02Z |
| publishDate | 2021-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-1edf9b16f58d4d26b0f4a8d4ae1d78e12022-12-21T22:25:08ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2021-01-011410.3389/fnins.2020.620235620235Edge-Aware Pyramidal Deformable Network for Unsupervised Registration of Brain MR ImagesYiqin Cao0Zhenyu Zhu1Yi Rao2Chenchen Qin3Di Lin4Qi Dou5Dong Ni6Yi Wang7National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, ChinaNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, ChinaNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, ChinaTencent AI Lab, Shenzhen, ChinaThe College of Intelligence and Computing, Tianjin University, Tianjin, ChinaComputer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, ChinaNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, ChinaNational-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, ChinaDeformable image registration is of essential important for clinical diagnosis, treatment planning, and surgical navigation. However, most existing registration solutions require separate rigid alignment before deformable registration, and may not well handle the large deformation circumstances. We propose a novel edge-aware pyramidal deformable network (referred as EPReg) for unsupervised volumetric registration. Specifically, we propose to fully exploit the useful complementary information from the multi-level feature pyramids to predict multi-scale displacement fields. Such coarse-to-fine estimation facilitates the progressive refinement of the predicted registration field, which enables our network to handle large deformations between volumetric data. In addition, we integrate edge information with the original images as dual-inputs, which enhances the texture structures of image content, to impel the proposed network pay extra attention to the edge-aware information for structure alignment. The efficacy of our EPReg was extensively evaluated on three public brain MRI datasets including Mindboggle101, LPBA40, and IXI30. Experiments demonstrate our EPReg consistently outperformed several cutting-edge methods with respect to the metrics of Dice index (DSC), Hausdorff distance (HD), and average symmetric surface distance (ASSD). The proposed EPReg is a general solution for the problem of deformable volumetric registration.https://www.frontiersin.org/articles/10.3389/fnins.2020.620235/fulldeformable image registrationconvolutional neural networksbrain MR imageaffine registration3D registration |
| spellingShingle | Yiqin Cao Zhenyu Zhu Yi Rao Chenchen Qin Di Lin Qi Dou Dong Ni Yi Wang Edge-Aware Pyramidal Deformable Network for Unsupervised Registration of Brain MR Images Frontiers in Neuroscience deformable image registration convolutional neural networks brain MR image affine registration 3D registration |
| title | Edge-Aware Pyramidal Deformable Network for Unsupervised Registration of Brain MR Images |
| title_full | Edge-Aware Pyramidal Deformable Network for Unsupervised Registration of Brain MR Images |
| title_fullStr | Edge-Aware Pyramidal Deformable Network for Unsupervised Registration of Brain MR Images |
| title_full_unstemmed | Edge-Aware Pyramidal Deformable Network for Unsupervised Registration of Brain MR Images |
| title_short | Edge-Aware Pyramidal Deformable Network for Unsupervised Registration of Brain MR Images |
| title_sort | edge aware pyramidal deformable network for unsupervised registration of brain mr images |
| topic | deformable image registration convolutional neural networks brain MR image affine registration 3D registration |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2020.620235/full |
| work_keys_str_mv | AT yiqincao edgeawarepyramidaldeformablenetworkforunsupervisedregistrationofbrainmrimages AT zhenyuzhu edgeawarepyramidaldeformablenetworkforunsupervisedregistrationofbrainmrimages AT yirao edgeawarepyramidaldeformablenetworkforunsupervisedregistrationofbrainmrimages AT chenchenqin edgeawarepyramidaldeformablenetworkforunsupervisedregistrationofbrainmrimages AT dilin edgeawarepyramidaldeformablenetworkforunsupervisedregistrationofbrainmrimages AT qidou edgeawarepyramidaldeformablenetworkforunsupervisedregistrationofbrainmrimages AT dongni edgeawarepyramidaldeformablenetworkforunsupervisedregistrationofbrainmrimages AT yiwang edgeawarepyramidaldeformablenetworkforunsupervisedregistrationofbrainmrimages |