An ITK Implementation of a Physics-based Non-rigid Registration Method for Brain Deformation in Image-guided Neurosurgery
As part of the ITK v4 project efforts, we have developed ITK filters for physics-based non-rigid registration (PBNRR), which satisfies the following requirements: account for tissue properties in the registration, improve accuracy compared to rigid registration, and reduce execution time using GPU a...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2014-04-01
|
| Series: | Frontiers in Neuroinformatics |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fninf.2014.00033/full |
| _version_ | 1818253775708618752 |
|---|---|
| author | Yixun eLiu Yixun eLiu Andriy eKot Fotis eDrakopoulos Chengjun eYao Andrey eFedorov Andrey eFedorov Andinet eEnquobahrie Olivier eClatz Nikos P Chrisochoides |
| author_facet | Yixun eLiu Yixun eLiu Andriy eKot Fotis eDrakopoulos Chengjun eYao Andrey eFedorov Andrey eFedorov Andinet eEnquobahrie Olivier eClatz Nikos P Chrisochoides |
| author_sort | Yixun eLiu |
| collection | DOAJ |
| description | As part of the ITK v4 project efforts, we have developed ITK filters for physics-based non-rigid registration (PBNRR), which satisfies the following requirements: account for tissue properties in the registration, improve accuracy compared to rigid registration, and reduce execution time using GPU and multi-core accelerators. The implementation has three main components: (1) Feature Point Selection, (2) Block Matching (mapped to both multi-core and GPU processors), and (3) a Robust Finite Element Solver. The use of multi-core and GPU accelerators in ITK v4 provides substantial performance improvements. For example, for the non-rigid registration of brain MRIs, the performance of the block matching filter on average is about 10 times faster when 12 hyperthreaded multi-cores are used and about 83 times faster when the NVIDIA Tesla GPU is used in Dell Workstation. |
| first_indexed | 2024-12-12T16:45:26Z |
| format | Article |
| id | doaj.art-f8cb663b28b04158918d2852fbf2426a |
| institution | Directory Open Access Journal |
| issn | 1662-5196 |
| language | English |
| last_indexed | 2024-12-12T16:45:26Z |
| publishDate | 2014-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroinformatics |
| spelling | doaj.art-f8cb663b28b04158918d2852fbf2426a2022-12-22T00:18:29ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962014-04-01810.3389/fninf.2014.0003367311An ITK Implementation of a Physics-based Non-rigid Registration Method for Brain Deformation in Image-guided NeurosurgeryYixun eLiu0Yixun eLiu1Andriy eKot2Fotis eDrakopoulos3Chengjun eYao4Andrey eFedorov5Andrey eFedorov6Andinet eEnquobahrie7Olivier eClatz8Nikos P Chrisochoides9Old Dominion UniversityNational Institutes of HealthOld Dominion UniversityOld Dominion UniversityHuashanOld Dominion UniversityBrigham And Women’s Hospital, Harvard Medical SchoolKitwareAsclepios Research Laboratory, INRIA Sophia AntipolisOld Dominion UniversityAs part of the ITK v4 project efforts, we have developed ITK filters for physics-based non-rigid registration (PBNRR), which satisfies the following requirements: account for tissue properties in the registration, improve accuracy compared to rigid registration, and reduce execution time using GPU and multi-core accelerators. The implementation has three main components: (1) Feature Point Selection, (2) Block Matching (mapped to both multi-core and GPU processors), and (3) a Robust Finite Element Solver. The use of multi-core and GPU accelerators in ITK v4 provides substantial performance improvements. For example, for the non-rigid registration of brain MRIs, the performance of the block matching filter on average is about 10 times faster when 12 hyperthreaded multi-cores are used and about 83 times faster when the NVIDIA Tesla GPU is used in Dell Workstation.http://journal.frontiersin.org/Journal/10.3389/fninf.2014.00033/fullgpubiomechanical modelITKnon-rigid registrationtumor resectionimage-guided neurosurgery |
| spellingShingle | Yixun eLiu Yixun eLiu Andriy eKot Fotis eDrakopoulos Chengjun eYao Andrey eFedorov Andrey eFedorov Andinet eEnquobahrie Olivier eClatz Nikos P Chrisochoides An ITK Implementation of a Physics-based Non-rigid Registration Method for Brain Deformation in Image-guided Neurosurgery Frontiers in Neuroinformatics gpu biomechanical model ITK non-rigid registration tumor resection image-guided neurosurgery |
| title | An ITK Implementation of a Physics-based Non-rigid Registration Method for Brain Deformation in Image-guided Neurosurgery |
| title_full | An ITK Implementation of a Physics-based Non-rigid Registration Method for Brain Deformation in Image-guided Neurosurgery |
| title_fullStr | An ITK Implementation of a Physics-based Non-rigid Registration Method for Brain Deformation in Image-guided Neurosurgery |
| title_full_unstemmed | An ITK Implementation of a Physics-based Non-rigid Registration Method for Brain Deformation in Image-guided Neurosurgery |
| title_short | An ITK Implementation of a Physics-based Non-rigid Registration Method for Brain Deformation in Image-guided Neurosurgery |
| title_sort | itk implementation of a physics based non rigid registration method for brain deformation in image guided neurosurgery |
| topic | gpu biomechanical model ITK non-rigid registration tumor resection image-guided neurosurgery |
| url | http://journal.frontiersin.org/Journal/10.3389/fninf.2014.00033/full |
| work_keys_str_mv | AT yixuneliu anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT yixuneliu anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT andriyekot anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT fotisedrakopoulos anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT chengjuneyao anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT andreyefedorov anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT andreyefedorov anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT andineteenquobahrie anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT oliviereclatz anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT nikospchrisochoides anitkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT yixuneliu itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT yixuneliu itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT andriyekot itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT fotisedrakopoulos itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT chengjuneyao itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT andreyefedorov itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT andreyefedorov itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT andineteenquobahrie itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT oliviereclatz itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery AT nikospchrisochoides itkimplementationofaphysicsbasednonrigidregistrationmethodforbraindeformationinimageguidedneurosurgery |