Highly Accelerated Magnetic Resonance Angiography using Deep Learning
LEAD SUPERVISOR: Professor Thomas Okell, Nuffield Department of Clinical Neurosciences
Co-supervisor: Professor Peter Jezzard, Nuffield Department of Clinical Neurosciences
Co-supervisor: Professor Mark Chiew, Nuffield Department of Clinical Neurosciences
Commercial partner: Siemens Healthcare Ltd (part of Siemens Healthineers), Camberley
Imaging of the blood vessels (angiography) is particularly important in the brain, where disturbances in blood supply and haemorrhage have severe consequences. Angiograms allow the visualisation of both blood supply disruption (atherosclerosis, embolism) and vascular abnormalities (aneurysms, arteriovenous malformations). However, conventional angiographic techniques have limited spatiotemporal resolution, require the injection of a contrast agent and use ionising radiation, resulting in some risks to the patient and limiting their use in paediatric or longitudinal examinations.
Certain magnetic resonance imaging (MRI)-based methods do not have these drawbacks: for example, time-of-flight (TOF) and arterial spin labelling (ASL) angiography. ASL is less well established than TOF, but improves vessel visibility and allows dynamic, vessel-selective angiograms to be obtained. This enables separate visualisation of arterial and venous signals as well as identification of feeding arteries to lesions. However, both methods suffer from long scan times, particularly when high spatial resolution and whole-head coverage are required, making them difficult to fit into busy clinical protocols and increasing the likelihood of image corruption due to patient motion.
In this project, highly accelerated angiographic methods will be developed that combine undersampling in the raw signal (k-space) domain with novel image reconstruction methods based on physics-informed supervised deep learning. We anticipate that the very specific branching structure of vessels within the brain can be well represented by deep convolutional networks, allowing rapid scans with high spatial resolution and whole-head coverage without the artefacts and long processing times associated with conventional (parallel imaging or compressed sensing) undersampled reconstructions.
This will involve: optimising unrolled neural network architectures in combination with undersampling patterns; training and testing on large, retrospectively undersampled TOF datasets; fine-tuning for ASL angiography; and application to prospectively undersampled rapid scan data in healthy volunteers and patient cohorts, in collaboration with clinical colleagues. This framework will also be adapted for vessel identification, allowing quantitative analysis of the acquired angiographic data (e.g. branching patterns, vessel tortuosity) and providing crucial information for complementary MRI-based pulse wave velocity measurements of arterial stiffness, thought to be implicated in vascular dementia. If time allows, this approach could also be further extended to accelerate ASL-based tissue perfusion imaging, allowing the downstream effects of vascular disease to also be rapidly evaluated.
This project aligns well with the MRC strategic priorities on new technologies and precision medicine: the much higher quality angiographic images that can be obtained, incorporating vessel-selective and quantitative information, will facilitate optimal treatment selection for individual patients (e.g. planning embolization therapy for a patient with arteriovenous malformation). In addition, the very short scan times of the proposed approach could make it feasible for use in the prevention and early detection of disease (e.g. screening for atherosclerosis in patients with vascular risk factors), another priority area of the MRC.
As well as an exciting research opportunity, this work will help to develop the rapidly growing portfolio of deep learning technologies being developed by Siemens Healthcare, enabling rapid scanning and image reconstruction, ideal for application in busy clinical settings, that they can deploy throughout the world.
Apply using course: DPhil in Clinical Neurosciences