| Presentation | 2019-01-23 Segmentation for diffuse lung disease opacities on CT images using U-Net and residual U-Net Kanako Murakami, Shoji Kido, Yasushi Hirano, Shingo Mabu, Kenji Kondo, Jun Ozawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Segmentation is important for diagnosis of diffuse lung diseases (DLD) as same as classification. In recent years, a lot of segmentation methods of medical images using U-Net are suggested in computer-aided diagnosis (CAD). Contours of cases such as ground-glass opacity (GGO) and emphysema (EMP) are vague in DLD opacities. Segmentation is difficult for such DLD opacities. In this study, we evaluated detection methods of DLD areas using U-Net and residual U-Net. Dice value of six DLD patterns using U-Net was 0.800±0.101, and dice value using residual U-Net was 0.854±0.065. Dice values of honeycombing (HCM) and EMP using U-Net were 0.768±0.090 and 0.679±0.183. Dice values of HCM and EMP using residual U-Net were 0.871±0.045 and 0.831±0.109. It is shown to be useful for cases those contours are vague. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | U-Net / residual U-Net / Diffuse Lung Disease |
| Paper # | MI2018-102 |
| 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) | Segmentation for diffuse lung disease opacities on CT images using U-Net and residual U-Net |
| Sub Title (in English) | |
| Keyword(1) | U-Net |
| Keyword(2) | residual U-Net |
| Keyword(3) | Diffuse Lung Disease |
| 1st Author's Name | Kanako Murakami |
| 1st Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
| 2nd Author's Name | Shoji Kido |
| 2nd Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
| 3rd Author's Name | Yasushi Hirano |
| 3rd Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
| 4th Author's Name | Shingo Mabu |
| 4th Author's Affiliation | Yamaguchi University(Yamaguchi Univ.) |
| 5th Author's Name | Kenji Kondo |
| 5th Author's Affiliation | Advanced Industrial Science and Technology/Panasonic Corporation(AIST/Panasonic) |
| 6th Author's Name | Jun Ozawa |
| 6th Author's Affiliation | Advanced Industrial Science and Technology(AIST) |
| Date | 2019-01-23 |
| Paper # | MI2018-102 |
| Volume (vol) | vol.118 |
| Number (no) | MI-412 |
| Page | pp.pp.175-179(MI), |
| #Pages | 5 |
| Date of Issue | 2019-01-15 (MI) |