| Presentation | 2019-01-22 Deep learning-based segmentation of head anatomical structures using multi-modal images Takaaki Sugino, Holger R. Roth, Masahiro Oda, Taichi kin, Kensaku Mori, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper proposes a fully convolutional network-based method for segmenting head anatomical structures from multi-modal images to construct a database of elaborate head anatomical models for practical neurosurgery simulation. In this study, to ease difficulties in creating annotated data for FCN training, we aim to construct a method to achieve accurate segmentation of head anatomical structures, using FCN designed to obtain multi-scale image features effective for multi-class segmentation, from less training data. On the bases of multi-modal images of 5 brain aneurysm cases, we validated the performance of the proposed method about segmentation of head anatomical structures from training on sparse annotation data. From the validation results, we found that the proposed method could achieve the segmentation accuracy of more than 80 % even from training on 10 % of all images for network training. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Segmentation / deep learning / head anatomical structures / sparse annotation |
| Paper # | MI2018-77 |
| 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) | Deep learning-based segmentation of head anatomical structures using multi-modal images |
| Sub Title (in English) | Segmentation accuracy validation for training on a small amount of image data |
| Keyword(1) | Segmentation |
| Keyword(2) | deep learning |
| Keyword(3) | head anatomical structures |
| Keyword(4) | sparse annotation |
| 1st Author's Name | Takaaki Sugino |
| 1st Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 2nd Author's Name | Holger R. Roth |
| 2nd Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 3rd Author's Name | Masahiro Oda |
| 3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
| 4th Author's Name | Taichi kin |
| 4th Author's Affiliation | The University of Tokyo(Univ. of Tokyo) |
| 5th Author's Name | Kensaku Mori |
| 5th Author's Affiliation | Nagoya University(Nagoya Univ.) |
| Date | 2019-01-22 |
| Paper # | MI2018-77 |
| Volume (vol) | vol.118 |
| Number (no) | MI-412 |
| Page | pp.pp.65-70(MI), |
| #Pages | 6 |
| Date of Issue | 2019-01-15 (MI) |