Post Doctoral Fellow in Machine Vision

About us

The evidENT team, which is part of UCL's Ear Institute applies artificial intelligence to address challenges in hearing healthcare. We are a multidisciplinary group of clinicians, data scientists, and researchers working on medical image analysis, machine learning, and audiology. Our recent work has focused on using deep learning to analyse temporal bone CT scans and brain MRI data in patients with hearing disorders.

You will join a collaborative environment where your technical expertise in computer vision will contribute to clinical applications. Our team are now expanding our work to develop automated segmentation tools and diagnostic aids for otologic conditions.

Working with ENT surgeons, audiologists, and AI researchers, you'll have access to datasets including audiograms and corresponding imaging data. Our partnership with the UCLH Biomedical Research Centre and NIHR Hearing Health Informatics Collaborative provides a strong foundation for translational research.

We value technical excellence and a practical approach to improving patient care. If you're interested in applying computer vision techniques to address clinical challenges in hearing health, our team offers the opportunity to work on meaningful projects with direct clinical relevance.

About the role

In this role, you will develop and implement computer vision and deep learning algorithms to analyse CT and MRI data from patients with hearing disorders. You will focus on creating automated segmentation methods for temporal bone structures, designing predictive models for treatment outcomes, and developing diagnostic tools for conditions such as otosclerosis.

The position requires expertise in medical image analysis, proficiency with neural network architectures (particularly CNNs for segmentation tasks), and experience processing 3D medical imaging data. You will collaborate closely with clinicians to ensure your technical work addresses practical clinical needs, while contributing to publications, grant applications, and the development of open-source tools for the hearing healthcare community.

About you

You should have a PhD in computer science, biomedical engineering, or a related field with strong expertise in medical image analysis and deep learning. You are proficient in implementing and optimising convolutional neural networks for medical image segmentation, with demonstrated experience working with 3D imaging data such as CT or MRI scans.

Your technical skills include Python programming and familiarity with deep learning frameworks (PyTorch or TensorFlow), along with a solid understanding of image processing techniques for medical applications.

You have a track record of successfully developing computer vision solutions for challenging segmentation tasks, ideally with experience in handling small anatomical structures or working with limited training data.

You can effectively communicate complex technical concepts to clinical collaborators and can work independently while contributing to the broader research goals of the team.

Customer advert reference: B02-08763

Advert information