| Presentation | 2020-01-30 2D Deep CNN for automated multi organ segmentation from CT images by using consecutive slices feature maps Hiroki Isakari, Xiangrong Zhou, Takeshi Hara, Hiroshi Fujita, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The development of a computer-aided diagnosis system is expected to reduce the burden on the radiologist in clinical practice and to reduce the variation in diagnosis. Therefore, it is indispensable for the computer to recognize and extract the three-dimensional human anatomy. However, in the organ extraction method using deep learning, the 3D CT image is converted into a 2D cross section or 3D patch image as preprocessing due to the limitation of hardware processing capacity, and deep learning uses only part of the human body information, sometimes not. In this study, we proposed a method for constructing an organ region extraction model using the continuity of 2D cross-sectional images. The proposed method was applied to the problem of region extraction of 21 organs from CT images taken in four human body areas. As a result, it was confirmed that the average agreement rate between the extracted result and the organ in the correct area was 87.1%. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | 3D-CT images / multiple organ region extraction / anatomical structure / convolutional neural network |
| Paper # | MI2019-113 |
| Date of Issue | 2020-01-22 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2020/1/29(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | OKINAWAKEN SEINENKAIKAN |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Image Engineering, Analysis, Recognition, 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) | 2D Deep CNN for automated multi organ segmentation from CT images by using consecutive slices feature maps |
| Sub Title (in English) | |
| Keyword(1) | 3D-CT images |
| Keyword(2) | multiple organ region extraction |
| Keyword(3) | anatomical structure |
| Keyword(4) | convolutional neural network |
| 1st Author's Name | Hiroki Isakari |
| 1st Author's Affiliation | Gifu University(Gifu Univ.) |
| 2nd Author's Name | Xiangrong Zhou |
| 2nd Author's Affiliation | Gifu University(Gifu Univ.) |
| 3rd Author's Name | Takeshi Hara |
| 3rd Author's Affiliation | Gifu University(Gifu Univ.) |
| 4th Author's Name | Hiroshi Fujita |
| 4th Author's Affiliation | Gifu University(Gifu Univ.) |
| Date | 2020-01-30 |
| Paper # | MI2019-113 |
| Volume (vol) | vol.119 |
| Number (no) | MI-399 |
| Page | pp.pp.203-205(MI), |
| #Pages | 3 |
| Date of Issue | 2020-01-22 (MI) |