Multimodal mapping of individual level cytoarchitectural anatomy in vivo

Project Summary:

I aim to develop a framework to map cytoarchitectural brain anatomy from multimodal quantitative MRI (qMRI). Multimodal qMRI maps (including diffusion and connectivity measures, high resolution R1, R2*, proton density, magnetisation transfer, and susceptibility) will be used to automatically derive anatomical labels. Jointly modelling this multimodal data, whilst accounting for image resolution differences, will better characterise microstructural tissue properties, allowing objective mapping of anatomical regions. Furthermore, the qMRI maps can be used to simulate a range of different contrasts. Combined with the qMRI-derived labels, this would enable machine learning systems to be trained for application to conventional MRI. The broader objective is to better characterise the link between anatomy and individual variation in neurological conditions such as Parkinson's disease.

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

The human brain is composed of multiple processing units with distinct functions. Whilst these tend to occur in similar areas, their precise location and size are highly variable among individuals and are imprecisely mapped using conventional MRI. This work will develop a bottom-up generative modelling approach to tissue segmentation using qMRI and DWI, where the biophysical MR properties are used to define anatomical regions that cannot conventionally be seen using 3T MRI.

To broaden the utility of these approaches, CNNs will be used to reproduce the quantitative maps and empirically defined segmentations on more easily acquired image modalities. The aim is to open these methods, that provide a much greater sensitivity to detect anatomical changes, to a wider range of existing datasets such as the >40,000 MRIs contained in the UK Biobank.

Aims and Objectives

The specific objectives are to:
- Improve estimation of qMRI parameters (R1, R2*, PD, and MT).
- Replicate pre-existing anatomical clustering methods using qMRI and tractography to identify limitations.
- Test whether additional quantitative maps (e.g., quantitative susceptibility imaging or various diffusion metrics) improve within-modality segmentation.
- Develop a segmentation approach that may be jointly applied to qMRI and DWI.
- Apply U-Nets to predict the optimised segmentations (c) from a range of MRI images simulated from qMRI parameters and assess its effectiveness.
- Apply the best performing method to a large cohort with Parkinson's disease to predict clinical outcomes.

Novelty of Research Methodology

Previous work has mapped brainstem using qMRI and DWI separately. Each technique samples different brain-tissue properties but pooling across modalities poses challenges because images have different resolutions. The goal is to build on these techniques to develop a flexible methodology that combines all available MRI data to improve the segmentation of cytoarchitectural regions. A further aim is to use synthesised MRI (from quantitative parameter maps), along with derived segmentations, to train a CNN that can segment the same structures from conventional MRI scans.

Alignment to EPSRC's strategies and research areas

This work aims to support the development of future therapies with a particular focus on translation applications for healthy aging, specifically:
- Improved precision medicine by better understanding, and modelling, individual-level clinical variability.
- Histological MRI approaches to identify anatomical subtypes of disease, particularly in neurodegenerative conditions, allowing more targeted medical therapies and earlier diagnoses.
- Non-invasive ways to improve safety in neurosurgery e.g., better stereotactic neurosurgical targeting in deep brain stimulation.

Any companies or collaborators involved

None

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.