The heart works as a muscular pump, which needs a healthy amount of shortening and lengthening of heart muscle in each region of the heart to maintain good overall pump function. Diseases such as heart attacks, heart failure and heart rhythm disorders, as well as heart damage caused by cancer therapy drugs, are diagnosed and monitored by measuring pump function, including changes in regional heart contraction and motion. Strain is an engineering quantity which measures contraction and relaxation as a relative change in length. Accurate measurement of strain in all regions of the heart is vital to understand mechanisms of disease. Medical imaging methods such as echocardiography and cardiac magnetic resonance imaging are being used to measure regional strain, to help diagnose disease and monitor treatment, and to develop and evaluate computational analyses of heart function. However, current quantification methods are inaccurate and imprecise, since strain is highly sensitive to image artefacts, noise, and low resolution. Worse, strain estimates vary systematically between different imaging modalities and even between different commercial software products. Vendors use "black box" closed source solutions which hamper reproducibility. This leads to different standards and measures being used by different doctors. Subsequently, it is not known which of the many measures available is best for diagnosing heart disease and predicting outcomes. Clearly, a new way of solving this problem is required. This project will develop novel technologies for measuring motion and strain in the heart which are standardized between imaging modalities. We will use "artificial intelligence" neural network methods to automatically process different types of medical imaging examinations to obtain more accurate and precise strain measurements. These networks will be trained to learn how to predict the underlying motion and strain from thousands of image simulations, as well as thousands of patient scans, using a statistical atlas of heart motions. By simulating realistic images with exact high resolution heart motions derived from the statistical atlas, the networks will learn how to handle image artefacts, noise and low resolution in real images. More fundamentally, we will examine how statistical atlasing methods can help us discover which strain measures are best for diagnosing and predicting heart disease. We will then deploy these methods in high-throughput heart imaging clinics at St Thomas' Hospital, Royal Brompton Hospital, and other NHS hospitals. By making open-source tools widely available for doctors, we will test how standardised measurements and reports will work in practice. This will also reduce the costs of patient evaluation, by getting the information we need from commonly-performed scans and avoiding the need for specialized equipment. More accurate and precise evaluation of patients with heart disease will improve patient care, by identifying high risk patients and optimizing treatment dose. In particular, many cancer patients suffer from heart muscle damage caused by their cancer drug therapy. Our tools will enable better identification of which patients are at most risk and may require a change of treatment.

Our EPSRC CDT in Advanced Engineering for Personalised Surgery & Intervention will train a new generation of researchers for diverse engineering careers that deliver patient and economic impact through innovation in surgery & intervention. We will achieve this through cohort training that implements the strategy of the EPSRC by working across sectors (academia, industry, and NHS) to stimulate innovations by generating and exchanging knowledge. Surgery is recognised as an "indivisible, indispensable part of health care" but the NHS struggles to meet its rising demand. More than 10m UK patients underwent a surgical procedure in 2021, with a further 5m patients still requiring treatment due to the COVID-19 backlog. This level of activity, encompassing procedures such as tumour resection, reconstructive surgery, orthopaedics, assisted fertilisation, thrombectomy, and cardiovascular interventions, accounts for a staggering 10% of the healthcare budget, yet it is not always curative. Unfortunately, one third of all country-wide deaths occur within 90 days of surgery. The Department of Health and Social Care urges for "innovation and new technology", echoing the NHS Long Term Plan on digital transformation and personalised care. Our proposed CDT will contribute to this mission and deliver mission-inspired training in the EPSRC's Research Priority "Transforming Health and Healthcare". In addition to patient impact, engineering innovation in surgery and intervention has substantial economic potential. The UK is a leader in the development of such technology and the 3rd biggest contributor to Europe's c.150bn euros MedTech market (2021). The market's growth rate is substantial, e.g., an 11.4% (2021 - 2026) compound annual growth rate is predicted just for the submarket of interventional robotics. The engineering scientists required to enhance the UK's societal, scientific, and economic capacity must be expert researchers with the skills to create innovative solutions to surgical challenges, by carrying out research, for example, on micro-surgical robots for tumour resection, AI-assisted surgical training, novel materials and theranostic agents for "surgery without the knife", and predictive computational models to develop patient-specific surgical procedures. Crucially, they should be comfortable and effective in crossing disciplines while being deeply engaged with surgical teams to co-create technology solutions. They should understand the pathway from bench-to-bedside and possess an entrepreneurial mindset to bring their innovations to the market. Such researchers are currently scarce, making their training a key contributor to the success of the UK Government's "Build Back Better - our plan for growth" and UKRI's "five-year strategy". The cross-discipline collaboration of King's School of Biomedical Engineering & Imaging Sciences (BMEIS, host), Department of Engineering, and King's Health Partners (KHP), our Academic Health Science Centre, will create an engineering focused CDT that embeds students within three acute NHS Trusts. Our CDT brings together 50+ world-class supervisors whose grant portfolio (c.£150m) underpins the full spectrum of the CDT's activity, i.e., Smart Instruments & Active Implants, Surgical Data Science, and Patient-specific Modelling & Simulation. We will offer MRes/PhD training pathway (1+3), and direct PhD training pathway (0+4). All students, regardless of pathway, will benefit from continuous education modules which cover aspects of clinical translation and entrepreneurship (with King's Entrepreneurship Institute), as well as core value modules to foster a positive research culture. Our graduates will acquire an entrepreneurial mindset with skills in data science, fundamental AI, computational modelling, and surgical instrumentation and implants. Career paths will range from creating next generation medical innovators within academia and/or industry to MedTech start-up entrepreneurs.

The challenges for healthcare systems are unprecedented, exacerbated by the burdens of infectious and chronic disease, ageing populations, inequalities, fragmented systems and workforce shortages. The NHS has a severe and growing workforce shortage that will be put under increasing pressure as the demands of our population continue to grow. Digital health technologies have the capacity to mitigate some of these challenges, for example via advanced monitoring technologies, virtual wards and 'hospital-at-home' programmes that will enable earlier diagnosis and personalised treatment strategies; however, this necessitates a new generation of digital health technologists, trained in research at the intersection of engineering, computing, data sciences and healthcare. Our EPSRC centre for doctoral training iN diGital heAlth technoloGiEs (ENGAGE) will address this deficit by creating a new coordinated doctoral training programme, partnering world-leading academic and NHS organisations and industry, such that graduates from the Centre can co-create and ideate, design, develop, evaluate and implement evidence-based digital health technologies. ENGAGE will provide a holistic approach to research and innovation, bringing together cutting-edge research spanning mathematical and data sciences, AI and machine learning, through to materials, sensors and medical devices, human-computer interaction and behavioural science, avoiding traditional disciplinary silos. We have co-designed ENGAGE with a breadth of industry and healthcare partners, identifying four themes for student training and PhD projects: Diagnostic & Prognostic Indications; Treatment & Care Optimization; Disease Tracking, Surveillance & Modelling; Data Security, Interoperability & Sharing. These Themes are underpinned by technology innovations as diverse as wearables and apps for home-monitoring of health and disease, digitally-enabled sensors for public health assessment, real-time patient algorithms and AI models to guide treatment. ENGAGE is a highly collaborative research training programme around a core academic partnership between UCL and Ulster University, providing a cutting-edge set of research expertise and facilities, in addition to embedding student projects in two different health and care systems (NHS in London and HSCNI in Northern Ireland). Further, ENGAGE partners with NHS Trusts via UCL's three Biomedical Research Centres at UCLH, GOSH and Moorfields, as well as the Belfast Health and Social Care Trust in Northern Ireland, providing excellent opportunities for multidisciplinary projects and to understand patient and clinician unmet needs. Students will also benefit from opportunities to share their research with the public via events organised by our universities and partners, including the Science Museum. ENGAGE has embedded partnerships with large industry and SMEs, spanning the breadth of digital health development and real-world application ranging from imaging technologies, through medical device regulation, device-enabled therapeutic monitoring, computational tools and infrastructure, to health apps, allowing co-creation of projects most likely to achieve impact. All partners will be embedded in student training opportunities, from hosting secondments to co-designing research projects and providing training. ENGAGE graduates will be adept at: (1) Identifying unmet need by engaging end-users and co-creating research questions with them; (2) Undertaking discovery research in engineering and physical sciences, bringing together approaches from different disciplines to tackle health challenges; (3) Understanding technology translation to the market via innovation & entrepreneurship; (4) Understanding the translational pipeline for sustainable digital health technologies, including ideation, development, evaluation, trials, regulation, adoption.

Magnetic resonance image (MRI) is the leading diagnostic modality for a wide range of exams due to the lack of ionising radiation and its ability to probe various aspects of the physiology. The use of MRI in UK has seen a large increase in recent years and with the technological advances and an ageing population, this demand is likely to continue to increase year-on-year. However unfortunately the physics of MRI data acquisition process makes it inherently slow, and the sustained increase in demand for MRI and its reduced reliability have also led to patients' longer waits and repeated procedures. It is therefore essential that society finds new ways to improve and optimise towards efficient MR imaging workflows. Recently, artificial intelligence (AI) techniques have opened the possibility to accelerate the MRI acquisition process considerably and have enabled progress beyond the limitations of conventional reconstruction methods. However, there is still a lack of consideration of their trustworthiness and failure management on unseen cases, which limits their translational potential in clinical practice. With the increasing development of deep learning-based techniques for MRI reconstruction, awareness about trustworthiness and uncertainty over deep learning reconstructed scans are becoming necessary and are also critical for downstream diagnostic decision-makings. This project aims to tackle the critical and growing problem of AI trustworthiness for AI-enabled MRI reconstruction. The proposed research will integrate and advance state-of-the-art research in machine learning and medical imaging. It will develop novel Bayesian deep learning approaches to quantify uncertainty for model-driven MRI reconstruction, build original failure prediction mechanisms to evaluate uncertainty, and investigate advanced test-time uncertainty reduction techniques for handling out-of-distribution data. This will conduce to creation of a streamlined pipeline to foster the common uncertainty practices in deep learning-based MRI reconstruction. It will also be evaluated on two clinical applications of accelerated pathological brain MRI and motion-corrupted cardiac MRI reconstruction. The confluence of the development in AI-enabled MRI reconstruction and its translational need opens exciting possibilities that we propose to investigate in this project.

The EPSRC Centre for Doctoral Training in Water Infrastructure & Resilience II (WIRe II) builds upon the highly successful collaboration between three of the UK's centres of excellence in water research (Cranfield, Sheffield and Newcastle Universities). One of the foundations of a thriving civic community and economy is having secure, resilient and sustainable water resources and services that: (i) provide affordable and equitable access to water; (ii) deliver a safe drinking water supply; (iii) provide wastewater services that don't pollute the environment; (iv) ensure there is enough water to meet the increasing demands from multiple sectors; and (v) are net beneficial to the environment, while protecting critical infrastructure from the impacts of climate change. This is placed against a backdrop of increased levels of dissatisfaction and higher expectations from civic communities on their water services, multiple demands on water resources and adaptations required from the impacts of climate change. With the UK population expected to grow from 69 million to 79 million by 2050, water resources have never been under as much pressure. Recent assessments have shown that only 14% of English rivers have good ecological status and no river has good chemical status. Water companies have also been placed under significant public examination from recent well-publicised pollution incidents from storm overflows and restrictions in water, with expectations that the UK will need to save 4billion litres of water per day by 2050. A collaborative and interdisciplinary approach is therefore essential for securing more resilient and sustainable water systems. There is also an urgent demand for improved water management as we move into a more sustainable world - the requirement for suitably skilled specialists with the appropriate interdisciplinary skills has never been higher. In developing the case for WIRe II, we have brought together an important group of civic partners, including the water utilities (with representation from all nations of the UK, covering water and wastewater services for 90% of the UKs population), organisations from the energy sector working on net zero technologies that have significant water demand and/or wastewater streams, regulators and civic groups, consultancies who work across the water-energy nexus, and partnerships with UKCRIC and DAFNI for access to world leading facilities. The CDT will be a significant contributor to addressing a clear skills gap identified by our partners and provide a future blueprint for enhanced training in the sector. We urgently need research to understand whole water systems (catchment, treatment and distribution processes) to achieve stable, safe water delivery to customers and the return of water back to the environment for multiple beneficial purposes. Such complexity requires inter- and trans-disciplinary research and a critical mass of experts and outputs. Three interconnected research themes will be addressed in WIRe II that align with key civic priorities: Safe and sustainable water resources for all; A resource neutral water sector; and Adapting to climate change. The WIRe II training programme has been developed with our partners to ensure we develop talent with the skills, competencies, and creativeness required to meet the changing demands of the sector. Built around the principles of deep vertical and horizontal integration of cohorts, students will progress through the CDT by undertaking a common induction semester, an assessed taught programme, an inspiring transferable skills curriculum and an annual Summer Challenge, alongside opportunities for national and international placements. We have evolved the programme to deliver the transformative science needed to tackle the rapidly changing demands and challenges being faced across our water systems and to develop the future leaders in the water and allied sectors.