Presentation | 2020-01-29 Surgical tool segmentation from laparoscopic images using laparoscopic image syntheses and deep learning Takuya Ozawa, Yuichiro Hayashi, Hirohisa Oda, Masahiro Oda, Takayuki Kitasaka, Nobuyoshi Takeshita, Masaaki Ito, Kensaku Mori, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper proposes a surgical tool segmentation method from laparoscopic images using image synthesis and deep learning. Forceps and anatomical structure recognition in laparoscopic movies is applicable to develop various surgical assistance and surgical process analysis systems. In the analysis of laparoscopic movies using deep learning, it is difficult to collect massive training data of forceps which are used infrequently during surgery. Recognition accuracy of them may be reduced by lack of training data. This paper solves the problem by generating training data using image synthesis. A pairs of synthetic laparoscopic images and segmentation data is automatically generated by superimposing the 3D forceps models on the actual laparoscopic movies. A deep learning model of forceps segmentation is trained using both the synthetic and the manual segmentation datasets. We applied the trained model to extract forceps in laparoscopic movies. The result showed that recognition accuracy of forceps used infrequently during surgery was improved by using the proposed training data. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Laparoscopic video / Surgical tool segmentation / Image synthesis |
Paper # | MI2019-94 |
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) | Surgical tool segmentation from laparoscopic images using laparoscopic image syntheses and deep learning |
Sub Title (in English) | |
Keyword(1) | Laparoscopic video |
Keyword(2) | Surgical tool segmentation |
Keyword(3) | Image synthesis |
1st Author's Name | Takuya Ozawa |
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 | Hirohisa Oda |
3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
4th Author's Name | Masahiro Oda |
4th Author's Affiliation | Nagoya University(Nagoya Univ.) |
5th Author's Name | Takayuki Kitasaka |
5th Author's Affiliation | Aichi Institute of Technology(Aich Ins. of Tech.) |
6th Author's Name | Nobuyoshi Takeshita |
6th Author's Affiliation | National Cancer Center Hospital East(NCC East) |
7th Author's Name | Masaaki Ito |
7th Author's Affiliation | National Cancer Center Hospital East(NCC East) |
8th Author's Name | Kensaku Mori |
8th Author's Affiliation | Nagoya University(Nagoya Univ.) |
Date | 2020-01-29 |
Paper # | MI2019-94 |
Volume (vol) | vol.119 |
Number (no) | MI-399 |
Page | pp.pp.129-134(MI), |
#Pages | 6 |
Date of Issue | 2020-01-22 (MI) |