Deep Learning for Joint Reconstruction for PET-MR

1 Brief description of the context of the research including potential impact

The combination of PET with MRI is now a commercially realised modality. A conventional approach to image reconstruction is to acquire a densely sampled MRI dataset reconstructed with penalised inverse Fourier transform and to use the structural information as a prior for PET reconstruction. This one-sided reconstruction has a mathematical framework that is quite mature. On the other hand, joint reconstruction, where underlying structural and statistical correspondence is used for the reconstruction of both modalities, is still in the early stages of development. Joint reconstruction has the potential of further accelerating data acquisition, as well as reducing doses for PET, whilst maintaining or improving image quality. Deep learning will be leveraged as it allows a powerful representation of priors. The priors will be trained to enforce complimentary information between the modalities. Accelerating acquisition can increase patient throughput and decreasing dosage can reduce potential for harm. Improvements to image quality could allow for more accurate diagnosis, improving patient outcome.

2 Aims and Objectives

The aim will be to develop practical learned reconstruction algorithms for joint multi-modal PET-MR imaging problems that are robust and efficient. The objectives include investigating a wider set of MRI acquisition protocols with strong under sampling. Developing iterative deep learning joint reconstruction methods. Testing methods on phantoms and clinical data with demonstrable improvement in performance efficiency and accuracy.

3 Novelty of Research Methodology

Deep Learning has become a dominant technique in many image processing tasks including image reconstruction. Joint reconstruction leveraging deep learning for prior representation will constitute a novel approach. The problems of very large datasets, small training sets and network generalisability and interpretability will be addressed.

4 Alignment to EPSRC's strategies and research areas

The theme that this project is aligned to is: Healthcare technologies. Within this theme the strategic grand challenge aligned to the project is optimising treatment. Where the success of mathematically and computationally tractable joint reconstruction can serve to optimise treatment. Potentially allowing for higher patient throughput, lower dosages, and more accurate diagnoses. Joint reconstruction falls under the novel computational and mathematical sciences as a cross-cutting capability. The research area that is aligned with the theme and the project is Medical imaging (including medical image and vision computing). This project focuses on the following "areas of high priority": enabling earlier and more effective diagnosis of physical and mental health conditions, to inform treatment planning; and automated extraction and/or integration of existing and additional information from clinical data/images (e.g. via machine learning and/or mathematical science techniques).

5 Any companies or collaborators involved

N/A

The critical mass of scientists and engineers that i4health will produce will ensure the UK's continued standing as a world-leader in medical imaging and healthcare technology research. In addition to continued academic excellence, they will further support a future culture of industry and entrepreneurship in healthcare technologies driven by highly trained engineers with deep understanding of the key factors involved in delivering effective translatable and marketable technology. They will achieve this through high quality engineering and imaging science, a broad view of other relevant technological areas, the ability to pinpoint clinical gaps and needs, consideration of clinical user requirements, and patient considerations. Our graduates will provide the drive, determination and enthusiasm to build future UK industry in this vital area via start-ups and spin-outs adding to the burgeoning community of healthcare-related SMEs in London and the rest of the UK. The training in entrepreneurship, coupled with the vibrant environment we are developing for this topic via unique linkage of Engineering and Medicine at UCL, is specifically designed to foster such outcomes. These same innovative leaders will bolster the UK's presence in medical multinationals - pharmaceutical companies, scanner manufacturers, etc. - and ensure the UK's competitiveness as a location for future R&D and medical engineering. They will also provide an invaluable source of expertise for the future NHS and other healthcare-delivery services enabling rapid translation and uptake of the latest imaging and healthcare technologies at the clinical front line. The ultimate impact will be on people and patients, both in the UK and internationally, who will benefit from the increased knowledge of health and disease, as well as better treatment and healthcare management provided by the future technologies our trainees will produce.

In addition to impact in healthcare research, development, and capability, the CDT will have major impact on the students we will attract and train. We will provide our talented cohorts of students with the skills required to lead academic research in this area, to lead industrial development and to make a significant impact as advocates of the science and engineering of their discipline. The i4health CDT's combination of the highest academic standards of research with excellent in-depth training in core skills will mean that our cohorts of students will be in great demand placing them in a powerful position to sculpt their own careers, have major impact within our discipline, while influencing the international mindset and direction. Strong evidence demonstrates this in our existing cohorts of students through high levels of conference podium talks in the most prestigious venues in our field, conference prizes, high impact publications in both engineering, clinical, and general science journals, as well as post-PhD fellowships and career progression. The content and training innovations we propose in i4health will ensure this continues and expands over the next decade.