Automatic Tool Detection in X-Ray Images for Robotic Assisted Joint Fracture Surgery

YingLiang Ma, Giulio Dagnino, Sanja Dogramadzi

Research output: Contribution to conferencePaper

Abstract

Long-bone fractures such as femur fractures are very
common in trauma centers. Robotic assisted fracture surgery
(RAFS) can facilitate the minimally invasive surgery which
reduces scarring, infection risk and long hospital stays. One
important step in RAFS is to establish the coordinate system
link between patient joint (rigidly connected with the robotic
system) and an external tracking system. As X-ray
fluoroscopic images are routinely used during the procedure,
an automatic method is proposed to detect and localize
landmarks on the tracking tool using live X-ray image. The
proposed method uses combination of block detection,
geometric model matching and principle component
analysis. A successful rate of 91.3% is achieved after testing
on 650 X-ray images and accuracy is within 0.5 mm.
Original languageEnglish
Publication statusPublished - 2017
EventIEEE International Conference on Internet of Things - Exeter, United Kingdom
Duration: 21 Jun 201723 Jun 2017
Conference number: 10

Conference

ConferenceIEEE International Conference on Internet of Things
Abbreviated titleiThings 2017
CountryUnited Kingdom
CityExeter
Period21/06/1723/06/17

Fingerprint Dive into the research topics of 'Automatic Tool Detection in X-Ray Images for Robotic Assisted Joint Fracture Surgery'. Together they form a unique fingerprint.

  • Cite this

    Ma, Y., Dagnino, G., & Dogramadzi, S. (2017). Automatic Tool Detection in X-Ray Images for Robotic Assisted Joint Fracture Surgery. Paper presented at IEEE International Conference on Internet of Things, Exeter, United Kingdom.