A real-time feature-based markerless tumor tracking method using X-ray image sequence for radiotherapy

Yusuke Yoshida, Kei Ichiji, Xiaoyong Zhang, Noriyasu Homma, Yoshihiro Takai, Makoto Yoshizawa

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

In this paper, we present a real-time markerless tumor tracking method for radiotherapy treatment. The proposed method is a feature-based tracking method using X-ray image sequence. In the proposed method, feature points of a tracking target are firstly detected by using the scale-invariant feature transform (SIFT) technique. Then, the feature points are tracked by an optical flow. The proposed method was tested by using clinical X-ray image sequences in comparison with two conventional tracking methods. The tracking error of the proposed method was 0.74±1.18 mm and the computational speed is about 20 frames/s. This result suggests that the proposed method is potential for real-time tumor tracking.

Original languageEnglish
Title of host publication2015 International Workshop on Computational Intelligence for Multimedia Understanding, IWCIM 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467384575
DOIs
Publication statusPublished - 2015 Dec 3
Event2015 International Workshop on Computational Intelligence for Multimedia Understanding, IWCIM 2015 - Prague, Czech Republic
Duration: 2015 Oct 292015 Oct 30

Publication series

Name2015 International Workshop on Computational Intelligence for Multimedia Understanding, IWCIM 2015

Conference

Conference2015 International Workshop on Computational Intelligence for Multimedia Understanding, IWCIM 2015
Country/TerritoryCzech Republic
CityPrague
Period15/10/2915/10/30

Keywords

  • markerless tracking
  • optical flow
  • radiotherapy
  • SIFT

Fingerprint

Dive into the research topics of 'A real-time feature-based markerless tumor tracking method using X-ray image sequence for radiotherapy'. Together they form a unique fingerprint.

Cite this