A computer vision based ultrasound operator skill evaluation

Chen, Zizui (2017) A computer vision based ultrasound operator skill evaluation. Masters thesis, Memorial University of Newfoundland.

[img] [English] PDF - Accepted Version
Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.

Download (1MB)


The aim of this thesis is to research inexpensive and automatic methods for analysing sonogra- phers skill level, which reduces cost and improves objectivity. The current approach of teaching physicians to generate good quality ultrasound images is expensive and subjective, also takes significant time and resources, because it requires experienced instructors to guide and assess trainees in person. In this thesis, a distributed data collection system for synchronising and collecting data from multiple different sensors, including Microsoft Kinect 2 and ultrasound machine, was designed. Then hand movements are extracted from ultrasound images with an intensity-based image registration algorithm. The extracted movements data are analysed to find different patterns between novice and expert sonographers. A multi-sensor fusion algorithm is used in this thesis to extend the field of view of Microsoft Kinect 2, as well as overcome the cluttered environments and obstacles in clinics. Hand tracking is performed in the registered large point clouds with a semi-automatic colour-based segmentation algorithm.

Item Type: Thesis (Masters)
URI: http://research.library.mun.ca/id/eprint/13046
Item ID: 13046
Additional Information: Includes bibliographical references (pages 64-73).
Department(s): Science, Faculty of > Computer Science
Date: November 2017
Date Type: Submission
Library of Congress Subject Heading: Computer vision in medicine; Medical technologists -- Rating of; Diagnostic ultrasonic imaging -- Practice

Actions (login required)

View Item View Item


Downloads per month over the past year

View more statistics