| Presentation | 2019-01-22 [Short Paper] Differences of Segmentation Results by Three Training Data for Cartilage Extraction in Knee MR Images Using Deep Learning Ryoma Aoki, Takeshi Hara, Taiki Nozaki, Masaki Matsusako, Xiangrong Zhou, Hiroshi Fujita, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Accurate grasp of cartilage area is important for diagnosis and treatment related to arthropathy diseases. In recent years, the importance of the quantitative evaluation index of the cartilage state has been noted in the diagnosis related to knee articular cartilage. The purpose of this research is to develop an automatic extraction method of cartilage region using deep learning. FCN-32s, FCN-16s and FCN-8s were used for learning from each teacher data of 20 normal MR images in which 2 doctors drew a cartilage area, and comparison was made by t-test with interobserver and intraobserver correspondence. As a result, it was suggested that there was a significant difference in learning result, and comparison of cartilage region extraction accuracy could be done. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Knee MR image / cartilage / segmentation / FCN |
| Paper # | MI2018-76 |
| Date of Issue | 2019-01-15 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2019/1/22(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Image Engineering, Analysis, Recognition, etc. |
| Chair | Kensaku Mori(Nagoya Univ.) |
| Vice Chair | Yoshiki Kawata(Tokushima Univ.) / Yuichi Kimura(Kinki Univ.) |
| Secretary | Yoshiki Kawata(Aichi Inst. of Tech.) / Yuichi Kimura(Nagoya Inst. of Tech.) |
| Assistant | Ryo Haraguchi(Univ. of Hyogo) / Yasushi Hirano(Yamaguchi Univ.) |
| Paper Information | |
| Registration To | Medical Imaging |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Short Paper] Differences of Segmentation Results by Three Training Data for Cartilage Extraction in Knee MR Images Using Deep Learning |
| Sub Title (in English) | |
| Keyword(1) | Knee MR image |
| Keyword(2) | cartilage |
| Keyword(3) | segmentation |
| Keyword(4) | FCN |
| Keyword(5) | |
| 1st Author's Name | Ryoma Aoki |
| 1st Author's Affiliation | Gifu University(Gifu Univ) |
| 2nd Author's Name | Takeshi Hara |
| 2nd Author's Affiliation | Gifu University(Gifu Univ) |
| 3rd Author's Name | Taiki Nozaki |
| 3rd Author's Affiliation | Department of Radiology,St.Luke's International Hospitai(Dept.of Radiol.,St.Luke's Hosp.) |
| 4th Author's Name | Masaki Matsusako |
| 4th Author's Affiliation | Department of Radiology,St.Luke's International Hospitai(Dept.of Radiol.,St.Luke's Hosp.) |
| 5th Author's Name | Xiangrong Zhou |
| 5th Author's Affiliation | Gifu University(Gifu Univ) |
| 6th Author's Name | Hiroshi Fujita |
| 6th Author's Affiliation | Gifu University(Gifu Univ) |
| Date | 2019-01-22 |
| Paper # | MI2018-76 |
| Volume (vol) | vol.118 |
| Number (no) | MI-412 |
| Page | pp.pp.63-64(MI), |
| #Pages | 2 |
| Date of Issue | 2019-01-15 (MI) |