| Presentation | 2021-05-17 [Short Paper] Fundamental study of automatic segmentation of skeletal muscle regions on whole body CT images based on a 3D DeepCNN Kota Nozaki, Xiangong Zhou, Naoki Kamiya, Takeshi Hara, Hiroshi Fujita, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Amyotrophic lateral sclerosis (ALS) is an intractable disease in which voluntary muscles atrophy gradully due to degeneration of motor neurons. A definitive method for ALS diagnosis is required but it still has not been established. The quantitative information of skeletal muscle region such as volume and CT value that can be obtained from CT images may be useful for supporting ALS diagnosis. In this study, as a preliminary step to obtain quantitative information on skeletal muscles, we investigated an automatic method based on 3D Deep CNN for automatically segmatation surface skeletal muscle regions from whole-body CT images. The experimental results demonstrated that accuracies of the segmetanted skeletal muscle regions showed a mean value of 80.5% on Jaccard coefficient, and 88.8% on Dice coefficient by comapring to the human sketches on 21 whole body CT scans. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Amyotrophic lateral sclerosis / whole-body CT image / skeletal muscle / 3D Deep CNN |
| Paper # | MI2021-7 |
| Date of Issue | 2021-05-10 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2021/5/17(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | On-Line |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Image Processing, etc |
| Chair | Yoshiki Kawata(Tokushima Univ.) |
| Vice Chair | Takayuki Kitasaka(Aichi Inst. of Tech.) / Hidekata Hontani(Nagoya Inst. of Tech.) |
| Secretary | Takayuki Kitasaka(Yamaguchi Univ.) / Hidekata Hontani(Univ. of Hyogo) |
| Assistant | Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST) |
| Paper Information | |
| Registration To | Technical Committee on Medical Imaging |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Short Paper] Fundamental study of automatic segmentation of skeletal muscle regions on whole body CT images based on a 3D DeepCNN |
| Sub Title (in English) | |
| Keyword(1) | Amyotrophic lateral sclerosis |
| Keyword(2) | whole-body CT image |
| Keyword(3) | skeletal muscle |
| Keyword(4) | 3D Deep CNN |
| 1st Author's Name | Kota Nozaki |
| 1st Author's Affiliation | Gifu University(Gifu Univ.) |
| 2nd Author's Name | Xiangong Zhou |
| 2nd Author's Affiliation | Gifu University(Gifu Univ.) |
| 3rd Author's Name | Naoki Kamiya |
| 3rd Author's Affiliation | Aichi Prefectual University(Aichi Prefectual Univ.) |
| 4th Author's Name | Takeshi Hara |
| 4th Author's Affiliation | Gifu University(Gifu Univ.) |
| 5th Author's Name | Hiroshi Fujita |
| 5th Author's Affiliation | Gifu University(Gifu Univ.) |
| Date | 2021-05-17 |
| Paper # | MI2021-7 |
| Volume (vol) | vol.121 |
| Number (no) | MI-21 |
| Page | pp.pp.20-22(MI), |
| #Pages | 3 |
| Date of Issue | 2021-05-10 (MI) |