Presentation | 2007-03-16 An improved method for identifying bronchial branch names using branching features in bronchoscopy guidance system Riyoko SHINOHARA, Daisuke DEGUCHI, Takayuki KITASAKA, Kensaku MORI, Yasuhito SUENAGA, Hirotsugu TAKABATAKE, Masaki MORI, Hiroshi NATORI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper describes an improved method for identifying bronchial branch names in bronchoscopy guidance system. In the previous method, we generated eigenspace from learning images that are virtual bronchoscopic(VB) images, and identified branches by selecting the image that is similar to a real bronchoscopic(RB) image. In the proposed method, we try to improve branch identification accuracy using branching information that is analyzed from both R.B and VB images. First, we classify learning images by the number of branching branches and construct the eigenspace for each branching number. Then the image that is similar to an RB image is selected from learning images that have the same number of branching branches as the RB image. In addition, we limit VB image by angle of branching braches in the image. We applied the proposed method to three pairs of 3D CT images and RB videos. The experimental results showed that we can improve branch identification accuracy of RB images by 11.7%. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | bronchoscope / virtual endoscopy / navigation / eigenspace / segmentation |
Paper # | PRMU2006-281 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2007/3/9(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | An improved method for identifying bronchial branch names using branching features in bronchoscopy guidance system |
Sub Title (in English) | |
Keyword(1) | bronchoscope |
Keyword(2) | virtual endoscopy |
Keyword(3) | navigation |
Keyword(4) | eigenspace |
Keyword(5) | segmentation |
1st Author's Name | Riyoko SHINOHARA |
1st Author's Affiliation | Graduate School of Information Science, Nagoya University() |
2nd Author's Name | Daisuke DEGUCHI |
2nd Author's Affiliation | Graduate School of Information Science, Nagoya University |
3rd Author's Name | Takayuki KITASAKA |
3rd Author's Affiliation | Graduate School of Information Science, Nagoya University |
4th Author's Name | Kensaku MORI |
4th Author's Affiliation | Graduate School of Information Science, Nagoya University |
5th Author's Name | Yasuhito SUENAGA |
5th Author's Affiliation | Graduate School of Information Science, Nagoya University |
6th Author's Name | Hirotsugu TAKABATAKE |
6th Author's Affiliation | Minami-sanjo Hospital |
7th Author's Name | Masaki MORI |
7th Author's Affiliation | Sapporo-Kosei General Hospital |
8th Author's Name | Hiroshi NATORI |
8th Author's Affiliation | Keiwakai Nishioka Hospital |
Date | 2007-03-16 |
Paper # | PRMU2006-281 |
Volume (vol) | vol.106 |
Number (no) | 606 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |