Research ProjectCardiovascular magnetic resonance imaging (CMR) is widely regarded as the gold-standard imaging modality for evaluating cardiac structure, function, and viability. However, CMR remains an expensive imaging modality limiting its widespread use worldwide. Furthermore, current clinical scanners operate at high field strengths (1.5T and above) which makes imaging of specific patient population (such as patients with implanted cardiac devices) very challenging and often associated to a high rate of non-diagnostic images.New affordable low-field MRI scanners operating at much lower magnetic field (0.55T) have been recently developed and offers unprecedented opportunities to increase the accessibility of CMR. Furthermore, these scanners have reduced susceptibility artefact from implanted devices, thus offering an opportunity to also increase access and diagnostic value of CMR in that corresponding patient population. Unfortunately, low-field CMR remains associated with low signal-to-noise ratio and resolution due to associated scanner hardware. Advanced reconstruction techniques have been proposed to improve image reconstruction but remain associated with long computational time, preventing their clinical use. Therefore, there is a need to develop fast image reconstruction techniques which address these limitations.The aim of this PhD is to develop novel image reconstruction techniques using deep learning for improved CMR at low field strength and to evaluate their potential in phantom, healthy subjects and patients.·       Aim 1/Year 1: Development of a deep learning-based image reconstruction to generate high quality images as obtained from computationally intensive image reconstruction.·       Aim 2/Year 2: Development of an extended deep learning-based image reconstruction integrating multi-contrast and temporal information. ·       Aim 3/Year 3: Development of deep learning-based super-resolution reconstruction to enhance image spatial resolution. ·       Aim 4/Year 4: Clinical evaluation of the proposed technology in patients undergoing low-field CMR at our institution.Learning experience: The student will develop a range of inter-disciplinary skills including in AI/deep learning, MRI physics, medical imaging acquisition/reconstruction, computer programming, and cardiology. EnvironmentThe applicant will join an internationally leading programme in cardiac MRI at KCL and will be co-supervised by Dr. Sebastien Roujol (MR-physics and engineering) and Dr. Tevfik Ismail (Cardiologist). This work will be conducted in close collaboration with Siemens, our industrial partner on this project. The postholder will be located within the School of Biomedical Engineering & Imaging Sciences at King’s College London (KCL), which is located within St Thomas Hospital in the heart of London. The applicant will join an interdisciplinary environment with a strong expertise in development and clinical translation of novel cardiac MRI techniques. FundingThis project is proposed as part of the MRC-DTP programme at KCL, which offers a number of fully funded PhD studentships: either as one-year MRes followed by a PhD (‘1+3’) or a 4 year PhD (‘0+4’) for a start in September 2025.Who Should Apply?Applications are invited from worldwide candidates with interest in multi-disciplinary research and training in medical imaging and AI, and a degree in any engineering subject such as computer science, medical physics, biomedical engineering or equivalent. We welcome applicants from communities underrepresented in academia.How to Apply?To be considered for this project, applicants will need to apply to the MRC DTP programme first (follow this direct link) and be admitted. The deadline for application to this is 29 October 2024.