A groupwise multiresolution network for DCE-MRI image registration
Abstract In four-dimensional time series such as dynamic contrast-enhanced (DCE) MRI, motion between individual time steps due to the patient’s breathing or movement leads to incorrect image analysis, e.g., when calculating perfusion. Image registration of the volumes of the individual time steps is...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-94275-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849390375286865920 |
|---|---|
| author | Anika Strittmatter Meike Weis Frank G. Zöllner |
| author_facet | Anika Strittmatter Meike Weis Frank G. Zöllner |
| author_sort | Anika Strittmatter |
| collection | DOAJ |
| description | Abstract In four-dimensional time series such as dynamic contrast-enhanced (DCE) MRI, motion between individual time steps due to the patient’s breathing or movement leads to incorrect image analysis, e.g., when calculating perfusion. Image registration of the volumes of the individual time steps is necessary to improve the accuracy of the subsequent image analysis. Both groupwise and multiresolution registration methods have shown great potential for medical image registration. To combine the advantages of groupwise and multiresolution registration, we proposed a groupwise multiresolution network for deformable medical image registration. We applied our proposed method to the registration of DCE-MR images for the assessment of lung perfusion in patients with congenital diaphragmatic hernia. The networks were trained unsupervised with Mutual Information and Gradient L2 loss. We compared the groupwise networks with a pairwise deformable registration network and a published groupwise network as benchmarks and the classical registration method SimpleElastix as baseline using four-dimensional DCE-MR scans of patients after congenital diaphragmatic hernia repair. Experimental results showed that our groupwise network yields results with high spatial alignment (SSIM up to 0.953 ± 0.025 or 0.936 ± 0.028 respectively), medically plausible transformation with low image folding (|J| ≤ 0: 0.0 ± 0.0%), and a low registration time of less than 10 seconds for a four-dimensional DCE-MR scan with 50 time steps. Furthermore, our results demonstrate that image registration with the proposed groupwise network enhances the accuracy of medical image analysis by leading to more homogeneous perfusion maps. |
| format | Article |
| id | doaj-art-a95575d7f2e943a6bec3ff87a0e4b2a1 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a95575d7f2e943a6bec3ff87a0e4b2a12025-08-20T03:41:40ZengNature PortfolioScientific Reports2045-23222025-03-0115111110.1038/s41598-025-94275-9A groupwise multiresolution network for DCE-MRI image registrationAnika Strittmatter0Meike Weis1Frank G. Zöllner2Computer Assisted Clinical Medicine, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Clinical Radiology and Nuclear Medicine, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg UniversityComputer Assisted Clinical Medicine, Medical Faculty Mannheim, Heidelberg UniversityAbstract In four-dimensional time series such as dynamic contrast-enhanced (DCE) MRI, motion between individual time steps due to the patient’s breathing or movement leads to incorrect image analysis, e.g., when calculating perfusion. Image registration of the volumes of the individual time steps is necessary to improve the accuracy of the subsequent image analysis. Both groupwise and multiresolution registration methods have shown great potential for medical image registration. To combine the advantages of groupwise and multiresolution registration, we proposed a groupwise multiresolution network for deformable medical image registration. We applied our proposed method to the registration of DCE-MR images for the assessment of lung perfusion in patients with congenital diaphragmatic hernia. The networks were trained unsupervised with Mutual Information and Gradient L2 loss. We compared the groupwise networks with a pairwise deformable registration network and a published groupwise network as benchmarks and the classical registration method SimpleElastix as baseline using four-dimensional DCE-MR scans of patients after congenital diaphragmatic hernia repair. Experimental results showed that our groupwise network yields results with high spatial alignment (SSIM up to 0.953 ± 0.025 or 0.936 ± 0.028 respectively), medically plausible transformation with low image folding (|J| ≤ 0: 0.0 ± 0.0%), and a low registration time of less than 10 seconds for a four-dimensional DCE-MR scan with 50 time steps. Furthermore, our results demonstrate that image registration with the proposed groupwise network enhances the accuracy of medical image analysis by leading to more homogeneous perfusion maps.https://doi.org/10.1038/s41598-025-94275-9Deep learningImage registrationMachine learningMedical imagesGroupwiseMultiresolution |
| spellingShingle | Anika Strittmatter Meike Weis Frank G. Zöllner A groupwise multiresolution network for DCE-MRI image registration Scientific Reports Deep learning Image registration Machine learning Medical images Groupwise Multiresolution |
| title | A groupwise multiresolution network for DCE-MRI image registration |
| title_full | A groupwise multiresolution network for DCE-MRI image registration |
| title_fullStr | A groupwise multiresolution network for DCE-MRI image registration |
| title_full_unstemmed | A groupwise multiresolution network for DCE-MRI image registration |
| title_short | A groupwise multiresolution network for DCE-MRI image registration |
| title_sort | groupwise multiresolution network for dce mri image registration |
| topic | Deep learning Image registration Machine learning Medical images Groupwise Multiresolution |
| url | https://doi.org/10.1038/s41598-025-94275-9 |
| work_keys_str_mv | AT anikastrittmatter agroupwisemultiresolutionnetworkfordcemriimageregistration AT meikeweis agroupwisemultiresolutionnetworkfordcemriimageregistration AT frankgzollner agroupwisemultiresolutionnetworkfordcemriimageregistration AT anikastrittmatter groupwisemultiresolutionnetworkfordcemriimageregistration AT meikeweis groupwisemultiresolutionnetworkfordcemriimageregistration AT frankgzollner groupwisemultiresolutionnetworkfordcemriimageregistration |