PhD Research Studentship in Biomedical Image Analysis

3.5-year D.Phil. studentship 

Project: Automated Analysis of X-ray Angiogram Images Using Deep Learning for Real-time Interventions

Supervisors: Dr Abhirup Banerjee and Prof Vicente Grau

Invasive x-ray coronary angiography is integral to the diagnosis and treatment of coronary arterial diseases. It provides high spatial and temporal resolution images of lumen structure in real-time to enable percutaneous coronary intervention and hence, is considered as gold standard during cardiac surgery settings. However, its interpretation in the cardiac catheterisation laboratory (cath. lab.) presently relies on sequential evaluation of multiple 2D image projections, limiting the assessment of lesion severity, visualisation of true vessel geometry, and quantitative image analysis.

In the last few years, AI and deep learning-based methods have revolutionised the medical image analysis. However, their effectiveness has not yet been demonstrated in x-ray angiograms. This project aims to bridge the gap and deliver novel automated AI-based system to generate 4D (3D+time) coronary vascular tree in real-time based only on 2D angiogram sequences. The candidate will contribute towards the development of novel deep learning-based methods for segmentation, tracking, motion estimation, and reconstruction (3D and 4D) of the coronary arterial tree in real-time, which will, in turn, enable automated identification of the coronary blockages, measurement of severity, and blood flow estimation. The primary objective of this project is to deliver an optimal patient-care system based only on standard 2D x-ray angiograms, which would potentially transform the present workflow of subjective interpretations and invasive measurements in cath. lab. environments.

This project offers the exciting opportunity to solve a critical healthcare problem during real-time cardiac surgery. It involves elements of Biomedical Engineering, AI, Machine Learning, Statistics, Mathematics (3D Geometry), Computer Science, and so forth.

Eligibility

This studentship is funded through the UK Engineering and Physical Sciences Research Council (EPSRC) Doctoral Training Partnership and is open to Home students (full award – home fees plus stipend). Full details of the eligibility requirements can be found on the UK Research and Innovation website.

There is very limited flexibility to support international students. If you are an international student and want to apply for this studentship please contact the supervisor to see whether the flexibility might be available for you.

Award Value

Course fees are covered at the level set for Home students (c. £8960 p.a.). The stipend (tax-free maintenance grant) is a minimum of c. £18,198 p.a. for the first year, and at least this amount for two and a half more years.

Candidate Requirements

Prospective candidates will be judged according to how well they meet the following criteria:

• A first-class or high 2.1 (or equivalent) honours degree in Engineering, Computer Science, Statistics, or Related Fields.
• Excellent English written and spoken communication skills.

The following skills are also desirable:

• Programming experience, especially in Python, Matlab, etc.
• Knowledge of the Machine Learning and Deep Learning Models, such as Convolutional Neural Networks, U-Net, GAN, Transformers, etc.

Application Procedure

Informal enquiries are encouraged and should be addressed to Dr Abhirup Banerjee (abhirup.banerjee@eng.ox.ac.uk).

Candidates must submit a graduate application form and are expected to meet the graduate admissions criteria. Details are available on the course page of the University website.

Please quote 23ENGBI_AB in all correspondence and in your graduate application.

Application deadline: noon on 9 December 2022

Start date: October 2023

Advert information