| Presentation | 2021-03-17 Study on automated anatomical labeling of abdominal arteries using Spectral-based Convolutional Graph Neural Networks Yuta Hibi, Yuichiro Hayashi, Takayuki Kitasaka, Hayato Itoh, Masahiro Oda, Kazunari Misawa, Kensaku Mori, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this study, we report an automated anatomical labeling method of abdominal arteries using Spectral-based Convolutional Graph Neural Networks. In laparoscopic surgery, which is widely performed today, it is difficult to understand the vascular structure due to the narrow field of laparoscope camera. Therefore, computer assistance is desired to help understanding of grasping vascular structure on surgeons by presenting the results of automated anatomical labeling of abdominal arteries. The use of a wide range of vascular features is important for learning vascular structures, and propose automated anatomical labeling of abdominal arteries by ChebNet that can handle a wide range of graph convolution. A maximum F value of 93.1% was achieved by introducing a weighted softmax cross entropy loss to reduce the imbalance in the data set. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | blood vessel / CT volume / anatomical names recognition / blood vessel structures analysis |
| Paper # | MI2020-89 |
| Date of Issue | 2021-03-08 (MI) |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2021/3/15(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Medical Imaging |
| 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) | Study on automated anatomical labeling of abdominal arteries using Spectral-based Convolutional Graph Neural Networks |
| Sub Title (in English) | |
| Keyword(1) | blood vessel |
| Keyword(2) | CT volume |
| Keyword(3) | anatomical names recognition |
| Keyword(4) | blood vessel structures analysis |
| 1st Author's Name | Yuta Hibi |
| 1st Author's Affiliation | Nagoya University(Nagoya Univ) |
| 2nd Author's Name | Yuichiro Hayashi |
| 2nd Author's Affiliation | Nagoya University(Nagoya Univ) |
| 3rd Author's Name | Takayuki Kitasaka |
| 3rd Author's Affiliation | Aichi Institute of Technology(Aichi Institute of Tech) |
| 4th Author's Name | Hayato Itoh |
| 4th Author's Affiliation | Nagoya University(Nagoya Univ) |
| 5th Author's Name | Masahiro Oda |
| 5th Author's Affiliation | Nagoya University(Nagoya Univ) |
| 6th Author's Name | Kazunari Misawa |
| 6th Author's Affiliation | Aichi Cancer Center Hospital(Aichi Cancer Center Hospital) |
| 7th Author's Name | Kensaku Mori |
| 7th Author's Affiliation | Nagoya University/National Institute of Informatics(Nagoya University/NII) |
| Date | 2021-03-17 |
| Paper # | MI2020-89 |
| Volume (vol) | vol.120 |
| Number (no) | MI-431 |
| Page | pp.pp.176-181(MI), |
| #Pages | 6 |
| Date of Issue | 2021-03-08 (MI) |