Object Detecting and Tracking in Medical X-ray Images

Eligibility: UK/EU graduates only with the required entry requirements

Award Details: Non funded

Duration: Full-Time – between 3 and 3.5 years.

Application deadline: 8 November 2019

Interview dates: Will be confirmed to shortlisted candidates

Start date: January 2020 (May 2020 entry may also be considered- subject to discussion and agreement)

Informal enquiries are essential before application; contact Ying Liang to discuss this opportunity.


Introduction

Coventry University is inviting applications from suitably-qualified graduates for a self funded PhD studentship

This project is to develop a real-time detection method for catheters and guidewires in medical X-ray images, which will be used in image guidance application for cardiac catheterization intervention.

The Project

Real-time detecting and tracking surgical instruments in X-ray images is an important task for guiding minimally invasive cardiac surgeries. As blood vessels and heart tissues are hardly visible under X-ray, to overcome this problem, 3D roadmaps can be overlaid onto X-ray images to add anatomical information. 3D roadmaps are the anatomical models which can be generated from computed tomography (CT) or images magnetic resonance (MR) images.  However, the accuracy of 3D roadmap guiding systems relies on two issues: 1) respiratory and cardiac motion compensation, and 2) registration between the 2D X-ray images and the 3D roadmap. Detecting and tracking surgical instruments, such as catheters and guidewires, provides more information to help increasing the accuracy and dealing with both issues.

The standard machine learning algorithms and image processing methods need to be adapted and re-designed to effectively localize surgical instruments in X-ray images, as medical X-ray images are very different compared to natural images. The proposer has developed a new concept of embedding machine learning methods into image filter algorithms, which could dramatically improve the accuracy and efficiency of real-time detection and tracking methods for surgical instruments.

Funding

For the academic year 2019/20, English-resident UK and EU students, or EU students moving to England for a PhD, who are not in receipt of Research Council funding or other direct government funding can apply  for a loan to help cover the cost of their PhD tuition fees. Further details can be found here.

Benefits

The successful candidate will receive comprehensive research training including technical, personal and professional skills.

All researchers at Coventry University (from PhD to Professor) are part of the Doctoral College and Centre for Research Capability and Development, which provides support with high-quality training and career development activities. 

Candidate specification

Entry criteria for applicants to PHD 

  • A minimum of a 2:1 first degree in a relevant discipline/subject area with a minimum 60% mark in the project element or equivalent with a minimum 60% overall module average. 
    PLUS 
    the potential to engage in innovative research and to complete the PhD within a 3.5 years
  • a minimum of English language proficiency (IELTS overall minimum score of 7.0 with a minimum of 6.5 in each component)

The ideal candidate should have experience in programming languages such as C/C++.  Experience with developing image-processing tools using the OpenCV environment or similar open-source software is a plus.

For further details please see out guide to making an application.

To find out more about the project please contact Dr Ma

All applications require full supporting documentation, a covering letter, plus a 2000-word supporting statement showing how the applicant’s expertise and interests are relevant to the project. 

Apply to Coventry University