HeartPad: Real-Time Visual Guidance for Cardiac Ultrasound

Steven Ford, Gabriel Kiss, Ivan Viola, Stefan Brukner and Hans Torp

INPROCEEDINGS, Proceedings of Workshop at SIGGRAPH ASIA 2012, November, 2012

• paper

Abstract

Medical ultrasound is a challenging modality when it comes to image interpretation. The goal we address in this work is to assist the ultrasound examiner and partially alleviate the burden of interpretation. We propose to address this goal with visualization that provides clear cues on the orientation and the correspondence between anatomy and the data being imaged. Our system analyzes the stream of 3D ultrasound data and in real-time identifies distinct features that are basis for a dynamically deformed mesh model of the heart. The heart mesh is composited with the original ultrasound data to create the data-to-anatomy correspondence. The visualization is broadcasted over the internet allowing, among other opportunities, a direct visualization on the patient on a tablet computer. The examiner interacts with the transducer and with the visualization parameters on the tablet. Our system has been characterized by domain specialist as useful in medical training and for navigating occasional ultrasound users.

Published

Proceedings of Workshop at SIGGRAPH ASIA 2012

• Series: WASA 2012
• Date: November 2012

Media

BibTeX

@inproceedings{Ford12HeartPad,
 author = {Steven Ford and Gabriel Kiss and Ivan Viola and Stefan Brukner and
  Hans Torp},
 title = {HeartPad: Real-Time Visual Guidance for Cardiac Ultrasound},
 booktitle = {Proceedings of Workshop at SIGGRAPH ASIA 2012},
 series = {WASA 2012},
 year = {2012},
 month = {November},
 address = {Fusionopolis, Singapore},
 abstract = {Medical ultrasound is a challenging modality when it comes to image
  interpretation. The goal we address in this work is to assist
  the ultrasound examiner and partially alleviate the burden of interpretation.
  We propose to address this goal with visualization that
  provides clear cues on the orientation and the correspondence between
  anatomy and the data being imaged. Our system analyzes the
  stream of 3D ultrasound data and in real-time identifies distinct features
  that are basis for a dynamically deformed mesh model of the
  heart. The heart mesh is composited with the original ultrasound
  data to create the data-to-anatomy correspondence. The visualization
  is broadcasted over the internet allowing, among other opportunities,
  a direct visualization on the patient on a tablet computer.
  The examiner interacts with the transducer and with the visualization
  parameters on the tablet. Our system has been characterized by
  domain specialist as useful in medical training and for navigating
  occasional ultrasound users.},


}