Interpretability of Self-supervised Learning in Ultrasound Video

Today, there has been great progress in designing deep learning models for medical imaging applications, but current understanding of how and why models work lags behind. Further the need for data to be manually annotated has limited progress in medical imaging, where available human expertise can be scarce. Manual annotation of anatomy in hundreds of hours of medical ultrasound video is one such case. Self-supervised learning is one recent approach to address the latter.
The doctoral research will explore the design and evaluation of deep-learning based self-supervised learning methods for medical ultrasound video placed in the context of automated analysis tasks such as plane finding, and image-guidance. Novelty will be in terms of the proposed single and multi-modal algorithms. The doctoral research will also investigate interpretability of the methods which is an important emerging area of AI research, relevant to benchmarking algorithms (understanding and justifying algorithm design), and translation (determining acceptability of methods by end users and whether there are constraints on use). The latter work will be conducted in collaboration with clinical partners. This project falls within the EPSRC healthcare technologies and ICT research areas.
Co-supervisors: Professor Alison Noble (Engineering Science), Dr Jianbo Jiao (Engineering Science);

Clinical collaborator: Professor Aris Papageorghiou (Nuffield Dept. Women's and Reproductive Health, U. Oxford).

In the same way that bioinformatics has transformed genomic research and clinical practice, health data science will have a dramatic and lasting impact upon the broader fields of medical research, population health, and healthcare delivery. The beneficiaries of the proposed training programme, and of the research that it delivers and enables, will include academia, industry, healthcare, and the broader UK economy.

Academia: Graduates of the training programme will be well placed to start their post-doctoral careers in leading academic institutions, engaging in high-impact multi-disciplinary research, helping to build training and research capacity, sharing their experience within the wider academic community.

Industry: Partner organisations will benefit from close collaboration with leading researchers, from the joint exploration of research priorities, and from the commercialisation of arising intellectual property. Other organisations will benefit from the availability of highly-qualified graduates with skills in big health data analytics.

Healthcare: Healthcare organisations and patients will benefit from the results of enabled and accelerated health research, leading to new treatments and technologies, and an improved ability to identify and evaluate potential improvements in practice through the analysis of real-world health data.

Economy: The life sciences sector is a key component of the UK economy. The programme will provide partner companies with direct access to leading-edge research. Graduates of the programme will be well-qualified to contribute to economic growth - supporting health research and the development of new products and services - and will be able to inform policy and decision making at organisational, regional, and national levels.