Presentation | 2021-08-27 A Study of a Pose Estimation Method of Ultrasound Probe Using RNN Kanta Miura, Koichi Ito, Takafumi Aoki, Jun Ohmiya, Satoshi Kondo, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose an ultrasound (US) probe pose estimation method using deep learning for 3D US image reconstruction. The proposed method employs a novel neural network consisting of a convolutional neural network (CNN) and a recurrent neural network (RNN). The features extracted from the US image sequence using CNN are input to RNN to estimate the relative and absolute pose of the US probe. We create an US image sequence dataset with ground-truth probe position measured by a motion capture system to evaluate the accuracy of the proposed method. Through a set of experiments, we demonstrate that the proposed method exhibits the efficient performance on probe pose estimation and 3D US image reconstruction compared with the conventional method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | ultrasound / volume reconstruction / RNN / CNN / pose estimation |
Paper # | MI2021-22 |
Date of Issue | 2021-08-20 (MI) |
Conference Information | |
Committee | MI |
---|---|
Conference Date | 2021/8/27(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Medical imaging |
Chair | Hidekata Hontani(Nagoya Inst. of Tech.) |
Vice Chair | Hideaki Haneishi(Chiba Univ.) / Takayuki Kitasaka(Aichi Inst. of Tech.) |
Secretary | Hideaki Haneishi(Yamaguchi Univ.) / Takayuki Kitasaka(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) | A Study of a Pose Estimation Method of Ultrasound Probe Using RNN |
Sub Title (in English) | |
Keyword(1) | ultrasound |
Keyword(2) | volume reconstruction |
Keyword(3) | RNN |
Keyword(4) | CNN |
Keyword(5) | pose estimation |
1st Author's Name | Kanta Miura |
1st Author's Affiliation | Tohoku University(Tohoku Univ.) |
2nd Author's Name | Koichi Ito |
2nd Author's Affiliation | Tohoku University(Tohoku Univ.) |
3rd Author's Name | Takafumi Aoki |
3rd Author's Affiliation | Tohoku University(Tohoku Univ.) |
4th Author's Name | Jun Ohmiya |
4th Author's Affiliation | KONICA MINOLTA, INC.(KONICA MINOLTA) |
5th Author's Name | Satoshi Kondo |
5th Author's Affiliation | KONICA MINOLTA, INC.(KONICA MINOLTA) |
Date | 2021-08-27 |
Paper # | MI2021-22 |
Volume (vol) | vol.121 |
Number (no) | MI-164 |
Page | pp.pp.2-7(MI), |
#Pages | 6 |
Date of Issue | 2021-08-20 (MI) |