| Presentation | 2018-03-13 Application of U-Net to spine image extraction in CT image Mikoto Kamata, Masayuki Kikuchi, Hayaru Shouno, Isao Hayashi, Kunihiko Fukushima, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this study, we aimed at automatic extraction of spinal parts in CT images using deep learning as a foothold for automatically generating 3D mesh model of spine from CT image of patient. We used 10 spinal data which were learned and tested on U-Net for the segmentation of spine region. The percentage of correct answers that the learned spine was tested was 98.5%, and the similarity between teacher image and segmented spine image measure by Dice coefficient of having tested the unedited spinal column was 82.7%. In order to improve this similarity value, it will be effective to adjust the parameters of U-Net and to conduct 3D learning as well. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | U-Net / Medical image processing / segmentation |
| Paper # | NC2017-81 |
| Date of Issue | 2018-03-06 (NC) |
| Conference Information | |
| Committee | MBE / NC |
|---|---|
| Conference Date | 2018/3/13(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Kikai-Shinko-Kaikan Bldg. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | ME, general |
| Chair | Kazuki Nakajima(Univ. of Toyama) / Masafumi Hagiwara(Keio Univ.) |
| Vice Chair | Masaki Kyoso(TCU) / Yutaka Hirata(Chubu Univ.) |
| Secretary | Masaki Kyoso(Toyama Pref. Univ.) / Yutaka Hirata(Kindai Univ.) |
| Assistant | Kim Juhyon(Univ. of Toyama) / Takumi Kobayashi(YNU) / Yoshihisa Shinozawa(Keio Univ.) / Keiichiro Inagaki(Chubu Univ.) |
| Paper Information | |
| Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing |
|---|---|
| Language | JPN-ONLY |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Application of U-Net to spine image extraction in CT image |
| Sub Title (in English) | |
| Keyword(1) | U-Net |
| Keyword(2) | Medical image processing |
| Keyword(3) | segmentation |
| 1st Author's Name | Mikoto Kamata |
| 1st Author's Affiliation | Tokyo University of Technology(Tokyo Univ.of Tech.) |
| 2nd Author's Name | Masayuki Kikuchi |
| 2nd Author's Affiliation | Tokyo University of Technology(Tokyo Univ.of Tech.) |
| 3rd Author's Name | Hayaru Shouno |
| 3rd Author's Affiliation | University of Electro-Communications(Univ. of Electro-Communications.) |
| 4th Author's Name | Isao Hayashi |
| 4th Author's Affiliation | Kansai University(Kansai Univ.) |
| 5th Author's Name | Kunihiko Fukushima |
| 5th Author's Affiliation | Fuzzy Logic Systems Institute(Fuzzy Logic Systems Inst.) |
| Date | 2018-03-13 |
| Paper # | NC2017-81 |
| Volume (vol) | vol.117 |
| Number (no) | NC-508 |
| Page | pp.pp.81-84(NC), |
| #Pages | 4 |
| Date of Issue | 2018-03-06 (NC) |