A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core system
This paper presents the sequential and parallel data decomposition strategies implemented on a Particle Swarm Optimization (PSO) algorithm based Artificial Neural Network (PSO-ANN) weights optimization for image reconstruction. The application system is developed for the reconstruction of two-dimens...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2017-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914817300370 |
| _version_ | 1818288761350389760 |
|---|---|
| author | Subramanian Kartheeswaran Daniel Dharmaraj Christopher Durairaj |
| author_facet | Subramanian Kartheeswaran Daniel Dharmaraj Christopher Durairaj |
| author_sort | Subramanian Kartheeswaran |
| collection | DOAJ |
| description | This paper presents the sequential and parallel data decomposition strategies implemented on a Particle Swarm Optimization (PSO) algorithm based Artificial Neural Network (PSO-ANN) weights optimization for image reconstruction. The application system is developed for the reconstruction of two-dimensional spatial standard Computed Tomography (CT) phantom images. It is running on a multi-core computer by varying the number of cores. The feed forward ANN initializes the weight between the âidealâ images that are reconstructed using filtered back projection (FBP) technique and the corresponding projection data of CT phantom. In an earlier work, ANN training time is too long. Hence, we propose that the ANN exemplar datasets are decomposed into subsets. Using these subsets, artificial sub neural nets (subnets) are initialized and each subnet initial weights are optimized using PSO. Consequently, it was observed that the sequential approach of the proposed method consumes more training time. Hence the parallel strategy is attempted to reduce the computational training time. The parallel approach is further explored for image reconstruction from ânoisyâ and âlimited-angleâ datasets also. Keywords: Image reconstruction, Filtered back projection, Artificial neural networks, Particle swarm optimization, Multi-core processors |
| first_indexed | 2024-12-13T02:01:31Z |
| format | Article |
| id | doaj.art-b74b8b7b46214f3b832aad78c534c120 |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-12-13T02:01:31Z |
| publishDate | 2017-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-b74b8b7b46214f3b832aad78c534c1202022-12-22T00:03:15ZengElsevierInformatics in Medicine Unlocked2352-91482017-01-0182131A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core systemSubramanian Kartheeswaran0Daniel Dharmaraj Christopher Durairaj1Correspondance to: Assistant Professor, M.C.A Department, Kalasalingam University, Krishnankoil - 626126, Tamil Nadu, India; Research Centre in Computer Science, V.H.N.S.N College (Autonomous), Virudhunagar 626001, Tamil Nadu, IndiaResearch Centre in Computer Science, V.H.N.S.N College (Autonomous), Virudhunagar 626001, Tamil Nadu, IndiaThis paper presents the sequential and parallel data decomposition strategies implemented on a Particle Swarm Optimization (PSO) algorithm based Artificial Neural Network (PSO-ANN) weights optimization for image reconstruction. The application system is developed for the reconstruction of two-dimensional spatial standard Computed Tomography (CT) phantom images. It is running on a multi-core computer by varying the number of cores. The feed forward ANN initializes the weight between the âidealâ images that are reconstructed using filtered back projection (FBP) technique and the corresponding projection data of CT phantom. In an earlier work, ANN training time is too long. Hence, we propose that the ANN exemplar datasets are decomposed into subsets. Using these subsets, artificial sub neural nets (subnets) are initialized and each subnet initial weights are optimized using PSO. Consequently, it was observed that the sequential approach of the proposed method consumes more training time. Hence the parallel strategy is attempted to reduce the computational training time. The parallel approach is further explored for image reconstruction from ânoisyâ and âlimited-angleâ datasets also. Keywords: Image reconstruction, Filtered back projection, Artificial neural networks, Particle swarm optimization, Multi-core processorshttp://www.sciencedirect.com/science/article/pii/S2352914817300370 |
| spellingShingle | Subramanian Kartheeswaran Daniel Dharmaraj Christopher Durairaj A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core system Informatics in Medicine Unlocked |
| title | A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core system |
| title_full | A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core system |
| title_fullStr | A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core system |
| title_full_unstemmed | A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core system |
| title_short | A data-parallelism approach for PSO-ANN based medical image reconstruction on a multi-core system |
| title_sort | data parallelism approach for pso ann based medical image reconstruction on a multi core system |
| url | http://www.sciencedirect.com/science/article/pii/S2352914817300370 |
| work_keys_str_mv | AT subramaniankartheeswaran adataparallelismapproachforpsoannbasedmedicalimagereconstructiononamulticoresystem AT danieldharmarajchristopherdurairaj adataparallelismapproachforpsoannbasedmedicalimagereconstructiononamulticoresystem AT subramaniankartheeswaran dataparallelismapproachforpsoannbasedmedicalimagereconstructiononamulticoresystem AT danieldharmarajchristopherdurairaj dataparallelismapproachforpsoannbasedmedicalimagereconstructiononamulticoresystem |