Position Overview

KU is seeking a highly motivated Post-doctoral Fellow to work on an internally funded project to investigate the development of an AI-based automated framework for accurate coronary tree segmentation and stenosis detection & grading in Coronary Computed Tomography Angiography (CCTA), with the aim of enhancing cardiovascular disease diagnosis. The project will focus on coronary artery segmentation and quantitative shape analysis.

The successful candidate will be responsible for the design and implementation of machine/deep learning algorithms for coronary artery segmentation and vessel shape modelling and representation. A variety of approaches will be pursued, including Graph Neural Networks, Transformers and Contrastive learning for segmentation, and generalized cylinder modelling for vascular shape analysis.

Position Requirements

• Conduct research on the development of vessel segmentation and quantitative shape analysis in CCTA images.
• Support the development of a CCTA image database from online repositories and our clinical partner and the setup of associated software functionalities to meet end-user requirements.
• Design and implement deep learning methods for acquisition-independent coronary vessel segmentation with minimal or no user intervention in the presence of intensity inhomogeneities and geometric artifacts.
• Design and implement a computational framework for quantitative vascular shape analysis providing vessel anatomical information, e.g., diameter, length, bi/trifurcation angles.
• Demonstrate expertise in the use of high-level programming languages (e.g., MATLAB, Python), and be competent in developing software applications for deployment in GPUs/HPC, etc.
• Write independently, as directed by the project supervisor, publications for submission to Q1 journals and premier computer science conferences.
• Take responsibility for reporting technical progress to the project investigator, periodically and in a timely manner.
• Carry out a specified research program under the direction of the project investigator.
• Collaborate and work in a collegial manner with the project team members.
• Function autonomously, ethically, and responsibly.
• Adhere to the University\'s information security and confidentiality policies and procedures, and report breaches or other security risks accordingly
• Perform any other tasks assigned by the Line Manager.

Qualifications

Candidate Profile

Essential Criteria

• PhD from a reputable university in Computer Science, Engineering or related discipline
• Experience in some of the following areas: Cardiovascular Imaging, Deep Learning, Image Segmentation
• Demonstrable background/experience in machine/deep learning and the broader field of AI. Experience in contrastive/self-supervised learning, graph neural networks is an advantage.
• Demonstrable ability to develop software in MATLAB/Python, including running applications in GPUs and/or HPC. Familiarity with at least one Machine Learning framework which can support application development, e.g., Pytorch, Tensorflow, Transformers, etc.
• Experience in writing scientific or review papers.
• A willingness to contribute to a collaborative and supportive team culture.
• Strong English language communication skills (verbal and written).
• Ability to work both independently and as part of a team.
• The proven ability to work on multiple tasks with competing demands and deadlines.
• Ability to train and mentor students and support fellow researchers.
• Highly developed reasoning and problem-solving skills.

Desired Criteria

• PhD gained from a top 200 QS or THE ranked University
• At least 1 year of relevant experience as a Post-doctoral researcher in academia or in industry.
• High impact first-author publications in top 10% journals in the relevant field

Should you require further assistance or if you face any issue with the online application, please feel to contact the Recruitment Team ( ).

Primary Location: Abu Dhabi UAE
Job: Post Doctoral Fellow
Schedule: Regular
Shift: Standard
Job Type: Full-time

Times Higher Education