| Presentation | 2005-01-21 Estimation of born-outline model from CT-images using statistical learning Jun NAKASHIMA, Nobumoto YAMANE, Yoshitaka MORIKAWA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently, in the medical treatment for joint diseases, a treatment method that replaces custom-made artificial joints is developed. The custom-made joint is designed by expert engineers estimating born solid-model from CT-images, so that huge amount of time and cost for the estimation prevent the treatment be widely applied. The major problem of this estimation is that the uncertain factors caused by cartilage and other tissues have correlation with born tissue image, and it makes the estimation inaccurate in conventional methods. In the proposed method, the adaptive Wiener filter that remove the uncertainty is designed by statistical learning, using training images obtained from previously treated cases. Although genuine born images and their CT-images are required for the estimation, the solid-model image that is estimated by the experts is used as substitute for the genuine born images. A simulation result shows that the proposed method is effective for the uncertainty removal. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | CT-image / born-outline / artificial implant / statistical learning / GMM / Wiener filter / MMSE-estimate |
| Paper # | MI2004-67 |
| Date of Issue |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2005/1/14(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Medical Imaging (MI) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Estimation of born-outline model from CT-images using statistical learning |
| Sub Title (in English) | |
| Keyword(1) | CT-image |
| Keyword(2) | born-outline |
| Keyword(3) | artificial implant |
| Keyword(4) | statistical learning |
| Keyword(5) | GMM |
| Keyword(6) | Wiener filter |
| Keyword(7) | MMSE-estimate |
| 1st Author's Name | Jun NAKASHIMA |
| 1st Author's Affiliation | Department of Communication Network Engineering, Okayama University() |
| 2nd Author's Name | Nobumoto YAMANE |
| 2nd Author's Affiliation | Department of Communication Network Engineering, Okayama University |
| 3rd Author's Name | Yoshitaka MORIKAWA |
| 3rd Author's Affiliation | Department of Communication Network Engineering, Okayama University |
| Date | 2005-01-21 |
| Paper # | MI2004-67 |
| Volume (vol) | vol.104 |
| Number (no) | 579 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |