HPC:Main: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
add new references |
||
| Line 1: | Line 1: | ||
==References== | |||
* [https://crtc.cs.odu.edu/pub/papers/journal_40.pdf Non-Rigid Registration for brain MRI: faster and cheaper ] | |||
:'''Abstract''' : We study the problem of Non-Rigid Registration (NRR) for intra-operative recovery of brain shift during image-guided neurosurgery. Time-critical nature of the tumour resection procedure presents a major obstacle to the routine clinical use of many available NRR approaches. In this paper, we utilise the resources of a single multicore workstation with an advanced graphics card to parallelise and evaluate an end-to-end implementation of a clinically validated NRR method. The results on clinical brain MRI data show the parallel NRR can reach real-time clinical requirement. | |||
* [https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3985035/ An ITK implementation of a physics-based non-rigid registration method for brain deformation in image-guided neurosurgery ] | |||
:'''Abstract''' : 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. | |||
Latest revision as of 00:31, 29 May 2017
References
- Abstract : We study the problem of Non-Rigid Registration (NRR) for intra-operative recovery of brain shift during image-guided neurosurgery. Time-critical nature of the tumour resection procedure presents a major obstacle to the routine clinical use of many available NRR approaches. In this paper, we utilise the resources of a single multicore workstation with an advanced graphics card to parallelise and evaluate an end-to-end implementation of a clinically validated NRR method. The results on clinical brain MRI data show the parallel NRR can reach real-time clinical requirement.
- Abstract : 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.