Disease Classification and Survival Analysis in Patients with Aortic Stenosis Using Transformer-Based Multi-Modal Artificial Intelligence Techniques

This project provides an annual stipend of £19,237.

Project advert

This studentship is part of Manchester Met’s investment in future thought leaders and offers an opportunity to join the Faculty of Science and Engineering’s growing doctoral research community focused on impactful research.

Aortic valve stenosis (AS) causes significant morbidity and mortality, with severe cases increasing the risk of heart failure, syncope, and sudden cardiac death. Echocardiography and CT are key for assessing AS severity, but conventional methods are time-consuming and susceptible to intra- and inter-observer variations. Current AI models use single modality inputs, failing to effectively integrate data from multiple sources due to their heterogeneity.

This project aims to develop a novel solution for accurate AS diagnosis and prognostication by employing transformer-based AI techniques as the disease classifier and survival predictor using data from multiple clinical domains. We partner with clinicians to provide clinical advice and relevance of our model development and validation.

Our outputs will enhance workflow processes and reduce diagnostic variability. Multi-modal AI can improve patient outcomes by enabling earlier detection of AS and better risk stratification for valvular intervention, leading to more personalized treatments. This aligns with our Human-centred Computing research theme, which focuses on creating technologies to enhance human capabilities and improve quality of life.

Project aims and objectives

The proposed research project aims to develop a novel solution for accurate AS diagnosis and prognostication by employing multi-modal AI techniques. The research objectives are to:

• Automate the analysis and reporting of electrocardiography, echocardiography, and CT images to derive biomarkers in AS patients.
• Autonomously classify AS severity and subtype.
• Improve patient outcomes by facilitating risk stratification for interventions such as valve replacement surgery.

The proposed project aligns closely with our faculty’s Human-centred Computing research theme, which focuses on developing technologies that enhance human capabilities and improve quality of life. This project addresses a critical healthcare need while exemplifying human-centred computing principles by enhancing patient care through advanced, user-friendly, and personalized AI technologies.

Specific requirements of the candidate

Successful candidates would have a strong background in computer science, engineering, maths or physics, and preference would be given to those with a good understanding of computer vision and deep learning.

It is essential for them to have a good background knowledge of machine learning and computer programming and a proactive approach to their work.

Funding

This opportunity is open to both home and international students. Please note that only home fees will be covered – eligible international students will need to make up the difference in tuition fee funding.

Successful applicants will be active researchers in our new state-of-the-art £117 million labs and Dalton Building facilities, and will be supported to develop their skills as independent researchers.

How to apply

Interested applicants should contact Prof Moi Hoon Yap ([email protected]) for an informal discussion.

To apply you will need to complete the online application form for a full-time PhD in Computing and Digital Technologies (or download the PGR application form).

You should also complete the PGR thesis proposal form and a Narrative CV addressing the project’s aims and objectives, demonstrating how the skills you have maps to the area of research and why you see this area as being of importance and interest. 

Applicants should ensure their submitted CV clearly demonstrates any experience and work in ML and AI.

If applying online, you will need to upload your statement in the supporting documents section, or email the application form and statement to [email protected].

Closing date: 14 October 2024.

Expected start date: January 2025 for Home students and April 2025 for International students.

Please note that Home fees are covered. Eligible International students will need to make up the difference in tuition fee funding. 

Please quote the reference: SciEng-CS-2024-Aortic-Stenosis