On the Usage of GPUs for Efficient Motion Estimation in Medical Image Sequences
Images are ubiquitous in biomedical applications from basic research to clinical practice. With the rapid increase in resolution, dimensionality of the images and the need for real-time performance in many applications, computational requirements demand proper exploitation of multicore architectures...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2011-01-01
|
| Series: | International Journal of Biomedical Imaging |
| Online Access: | http://dx.doi.org/10.1155/2011/137604 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832558174315479040 |
|---|---|
| author | Jeyarajan Thiyagalingam Daniel Goodman Julia A. Schnabel Anne Trefethen Vicente Grau |
| author_facet | Jeyarajan Thiyagalingam Daniel Goodman Julia A. Schnabel Anne Trefethen Vicente Grau |
| author_sort | Jeyarajan Thiyagalingam |
| collection | DOAJ |
| description | Images are ubiquitous in biomedical applications from basic research to clinical practice. With the rapid increase in resolution, dimensionality of the images and the need for real-time performance in many applications, computational requirements demand proper exploitation of multicore architectures. Towards this, GPU-specific implementations of image analysis algorithms are particularly promising. In this paper, we investigate the mapping of an enhanced motion estimation algorithm to novel GPU-specific architectures, the resulting challenges and benefits therein. Using a database of three-dimensional image sequences, we show that the mapping leads to substantial performance gains, up to a factor of 60, and can provide near-real-time experience. We also show how architectural peculiarities of these devices can be best exploited in the benefit of algorithms, most specifically for addressing the challenges related to their access patterns and different memory configurations. Finally, we evaluate the performance of the algorithm on three different GPU architectures and perform a comprehensive analysis of the results. |
| format | Article |
| id | doaj-art-59e386df84314453a9ad6a2c87aca784 |
| institution | Kabale University |
| issn | 1687-4188 1687-4196 |
| language | English |
| publishDate | 2011-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Biomedical Imaging |
| spelling | doaj-art-59e386df84314453a9ad6a2c87aca7842025-02-03T01:32:56ZengWileyInternational Journal of Biomedical Imaging1687-41881687-41962011-01-01201110.1155/2011/137604137604On the Usage of GPUs for Efficient Motion Estimation in Medical Image SequencesJeyarajan Thiyagalingam0Daniel Goodman1Julia A. Schnabel2Anne Trefethen3Vicente Grau4Oxford e-Research Centre, University of Oxford, Oxford OX1 3QG, UKOxford e-Research Centre, University of Oxford, Oxford OX1 3QG, UKInstitute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, UKOxford e-Research Centre, University of Oxford, Oxford OX1 3QG, UKOxford e-Research Centre, University of Oxford, Oxford OX1 3QG, UKImages are ubiquitous in biomedical applications from basic research to clinical practice. With the rapid increase in resolution, dimensionality of the images and the need for real-time performance in many applications, computational requirements demand proper exploitation of multicore architectures. Towards this, GPU-specific implementations of image analysis algorithms are particularly promising. In this paper, we investigate the mapping of an enhanced motion estimation algorithm to novel GPU-specific architectures, the resulting challenges and benefits therein. Using a database of three-dimensional image sequences, we show that the mapping leads to substantial performance gains, up to a factor of 60, and can provide near-real-time experience. We also show how architectural peculiarities of these devices can be best exploited in the benefit of algorithms, most specifically for addressing the challenges related to their access patterns and different memory configurations. Finally, we evaluate the performance of the algorithm on three different GPU architectures and perform a comprehensive analysis of the results.http://dx.doi.org/10.1155/2011/137604 |
| spellingShingle | Jeyarajan Thiyagalingam Daniel Goodman Julia A. Schnabel Anne Trefethen Vicente Grau On the Usage of GPUs for Efficient Motion Estimation in Medical Image Sequences International Journal of Biomedical Imaging |
| title | On the Usage of GPUs for Efficient Motion Estimation in Medical Image Sequences |
| title_full | On the Usage of GPUs for Efficient Motion Estimation in Medical Image Sequences |
| title_fullStr | On the Usage of GPUs for Efficient Motion Estimation in Medical Image Sequences |
| title_full_unstemmed | On the Usage of GPUs for Efficient Motion Estimation in Medical Image Sequences |
| title_short | On the Usage of GPUs for Efficient Motion Estimation in Medical Image Sequences |
| title_sort | on the usage of gpus for efficient motion estimation in medical image sequences |
| url | http://dx.doi.org/10.1155/2011/137604 |
| work_keys_str_mv | AT jeyarajanthiyagalingam ontheusageofgpusforefficientmotionestimationinmedicalimagesequences AT danielgoodman ontheusageofgpusforefficientmotionestimationinmedicalimagesequences AT juliaaschnabel ontheusageofgpusforefficientmotionestimationinmedicalimagesequences AT annetrefethen ontheusageofgpusforefficientmotionestimationinmedicalimagesequences AT vicentegrau ontheusageofgpusforefficientmotionestimationinmedicalimagesequences |