Analysis of parameters' effects in semi-automated knee cartilage segmentation model: Data from the osteoarthritis initiative
Unlike automated segmentation, the accuracy of semi-automated segmentation is affected by pertinent parameters such as observer, type of methods and type of cartilage. In this paper, we investigated the effect of these parameters on segmentation results. Based on Dice similarity index obtained from...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
American Institute of Physics Inc.
2016
|
| Subjects: |
| _version_ | 1796862005081014272 |
|---|---|
| author | Gan, H. S. Karim, A. H. A. Sayuti, K. A. Tan, T. S. Kadir, M. R. A. |
| author_facet | Gan, H. S. Karim, A. H. A. Sayuti, K. A. Tan, T. S. Kadir, M. R. A. |
| author_sort | Gan, H. S. |
| collection | ePrints |
| description | Unlike automated segmentation, the accuracy of semi-automated segmentation is affected by pertinent parameters such as observer, type of methods and type of cartilage. In this paper, we investigated the effect of these parameters on segmentation results. Based on Dice similarity index obtained from fifteen normal and ten diseased magnetic resonance images, a parameter estimation model was constructed to study the impact of each parameter. Then, we conducted deviance test to verify the effect's significance. Our result showed that implementation of the proposed segmentation model would introduce positive effect (+0.12) on reproducibility compared to conventional random walks model. Furthermore, we have found intriguing results indicating cartilage normality has diminished effect on reproducibility and tibial cartilage's result could be influenced by external factors as well. Lastly, our findings highlighted on the necessity of refinement for semi-automated segmentation. |
| first_indexed | 2024-03-05T20:05:00Z |
| format | Conference or Workshop Item |
| id | utm.eprints-73003 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T20:05:00Z |
| publishDate | 2016 |
| publisher | American Institute of Physics Inc. |
| record_format | dspace |
| spelling | utm.eprints-730032017-11-21T08:17:09Z http://eprints.utm.my/73003/ Analysis of parameters' effects in semi-automated knee cartilage segmentation model: Data from the osteoarthritis initiative Gan, H. S. Karim, A. H. A. Sayuti, K. A. Tan, T. S. Kadir, M. R. A. TP Chemical technology Unlike automated segmentation, the accuracy of semi-automated segmentation is affected by pertinent parameters such as observer, type of methods and type of cartilage. In this paper, we investigated the effect of these parameters on segmentation results. Based on Dice similarity index obtained from fifteen normal and ten diseased magnetic resonance images, a parameter estimation model was constructed to study the impact of each parameter. Then, we conducted deviance test to verify the effect's significance. Our result showed that implementation of the proposed segmentation model would introduce positive effect (+0.12) on reproducibility compared to conventional random walks model. Furthermore, we have found intriguing results indicating cartilage normality has diminished effect on reproducibility and tibial cartilage's result could be influenced by external factors as well. Lastly, our findings highlighted on the necessity of refinement for semi-automated segmentation. American Institute of Physics Inc. 2016 Conference or Workshop Item PeerReviewed Gan, H. S. and Karim, A. H. A. and Sayuti, K. A. and Tan, T. S. and Kadir, M. R. A. (2016) Analysis of parameters' effects in semi-automated knee cartilage segmentation model: Data from the osteoarthritis initiative. In: 2nd International Conference on Mathematics, Engineering and Industrial Applications 2016, ICOMEIA 2016, 10 August 2016 through 12 August 2016, Songkhla; Thailand. https://www.scopus.com/inward/record.uri?eid=2-s2.0-84997285878&doi=10.1063%2f1.4965172&partnerID=40&md5=a70e52a3efce4dc31f4e4200d3b34729 |
| spellingShingle | TP Chemical technology Gan, H. S. Karim, A. H. A. Sayuti, K. A. Tan, T. S. Kadir, M. R. A. Analysis of parameters' effects in semi-automated knee cartilage segmentation model: Data from the osteoarthritis initiative |
| title | Analysis of parameters' effects in semi-automated knee cartilage segmentation model: Data from the osteoarthritis initiative |
| title_full | Analysis of parameters' effects in semi-automated knee cartilage segmentation model: Data from the osteoarthritis initiative |
| title_fullStr | Analysis of parameters' effects in semi-automated knee cartilage segmentation model: Data from the osteoarthritis initiative |
| title_full_unstemmed | Analysis of parameters' effects in semi-automated knee cartilage segmentation model: Data from the osteoarthritis initiative |
| title_short | Analysis of parameters' effects in semi-automated knee cartilage segmentation model: Data from the osteoarthritis initiative |
| title_sort | analysis of parameters effects in semi automated knee cartilage segmentation model data from the osteoarthritis initiative |
| topic | TP Chemical technology |
| work_keys_str_mv | AT ganhs analysisofparameterseffectsinsemiautomatedkneecartilagesegmentationmodeldatafromtheosteoarthritisinitiative AT karimaha analysisofparameterseffectsinsemiautomatedkneecartilagesegmentationmodeldatafromtheosteoarthritisinitiative AT sayutika analysisofparameterseffectsinsemiautomatedkneecartilagesegmentationmodeldatafromtheosteoarthritisinitiative AT tants analysisofparameterseffectsinsemiautomatedkneecartilagesegmentationmodeldatafromtheosteoarthritisinitiative AT kadirmra analysisofparameterseffectsinsemiautomatedkneecartilagesegmentationmodeldatafromtheosteoarthritisinitiative |