The Programme is organised into two themes. Research theme one will develop new computer vision algorithms to enable efficient search and description of vast image and video datasets - for example of the entire video archive of the BBC. Our vision is that anything visual should be searchable for, in the manner of a Google search of the web: by specifying a query, and having results returned immediately, irrespective of the size of the data. Such enabling capabilities will have widespread application both for general image/video search - consider how Google's web search has opened up new areas - and also for designing customized solutions for searching. A second aspect of theme 1 is to automatically extract detailed descriptions of the visual content. The aim here is to achieve human like performance and beyond, for example in recognizing configurations of parts and spatial layout, counting and delineating objects, or recognizing human actions and inter-actions in videos, significantly superseding the current limitations of computer vision systems, and enabling new and far reaching applications. The new algorithms will learn automatically, building on recent breakthroughs in large scale discriminative and deep machine learning. They will be capable of weakly-supervised learning, for example from images and videos downloaded from the internet, and require very little human supervision. The second theme addresses transfer and translation. This also has two aspects. The first is to apply the new computer vision methodologies to `non-natural' sensors and devices, such as ultrasound imaging and X-ray, which have different characteristics (noise, dimension, invariances) to the standard RGB channels of data captured by `natural' cameras (iphones, TV cameras). The second aspect of this theme is to seek impact in a variety of other disciplines and industry which today greatly under-utilise the power of the latest computer vision ideas. We will target these disciplines to enable them to leapfrog the divide between what they use (or do not use) today which is dominated by manual review and highly interactive analysis frame-by-frame, to a new era where automated efficient sorting, detection and mensuration of very large datasets becomes the norm. In short, our goal is to ensure that the newly developed methods are used by academic researchers in other areas, and turned into products for societal and economic benefit. To this end open source software, datasets, and demonstrators will be disseminated on the project website. The ubiquity of digital imaging means that every UK citizen may potentially benefit from the Programme research in different ways. One example is an enhanced iplayer that can search for where particular characters appear in a programme, or intelligently fast forward to the next `hugging' sequence. A second is wider deployment of lower cost imaging solutions in healthcare delivery. A third, also motivated by healthcare, is through the employment of new machine learning methods for validating targets for drug discovery based on microscopy images

The United Kingdom has a strong history of having developed imaging techniques and technologies that allow us to visualize a range of biomedical phenomena, from being able to visualise molecules inside individual cells, to being able to take pictures non invasively inside patients. Examples of this include the pioneering work done by Sir Godfrey Hounsfield (Nobel Prize winner and co-inventor of the Computed Tomography scanner), and Sir Peter Mansfield of Nottingham University (Nobel Prize winner and co-inventor of magnetic resonance imaging). A recent report from two of the UK Research Councils showed that the UK still has a world-leading research profile in this area, but also showed that there was a shortage of trained UK individuals who are experts in medical imaging. This means that our research institutions and industries struggle to employ suitably qualified individuals, and either have to employ non-UK nationals or cannot undertake the work they wish to. The aim of this Centre for Doctoral Training is therefore to address the need for more trained imaging scientists by linking together two of the UK's top research-intensive universities to deliver a rigorous training programme in this area. In particular, and in response to the needs expressed both by our industry colleagues and by our NHS colleagues, we will put in place a doctoral training programme that gives students an understanding of the full landscape of medical imaging (e.g. different types of imaging, different scales of imaging from cellular imaging up to whole human imaging, and different ways of analyzing the resulting images). Since these will mostly be students with a background in the physical sciences (physics, engineering and mathematics) we will also provide them with a training in the basic biology of cells, and in the range of diseases in which medical imaging can make a difference. Following a first year of training the students will work in specialist research laboratories in Oxford and Nottingham (with some students working between the two institutions). Both universities have world-renowned scientists and excellent facilities to host research projects for the students, culminating in each student receiving a doctoral degree from either Nottingham or Oxford. The range of research and opportunities available to these students is very large, with researchers in both institutions working at all scales of medical imaging (single cells to whole humans), and on various diseases, including cancer, brain disorders, and heart disorders. As major partners we will work with colleagues from industry so that our students gain experience in working in an industry environment, and so that some of the projects they work on are ones that are proposed by industry. This partnership will also help us produce trained experts who have an appreciation for the way that industry operates, and an understanding of how research ideas can be commercialized so that they become a source of income to the nation. We believe that by having a rigorous doctoral training programme like this we will ensure that the UK is well placed to compete academically and industrially in the future. We also believe that there will be benefits to the NHS, since our graduates will develop imaging techniques that will refine the way the NHS treats us, thus saving money and making the treatments that we receive more relevant to us as individuals.

As quality of life constantly improves, the average lifespan will continue to increase. Underlining this improvement is the vast amount of the UK government's support to NHS (£133.5 billion in year 2011/12) and the UK pharmaceutical industry's R&D large investment (4.9 billion to R&D in year 2011/12). The expectation of quality healthcare is inevitably high from all stakeholders. Fortunately recent advances in science and technology have enabled us to work towards personalised medicine and preventative care. This approach calls for a collective effort of researchers from a vast spectrum of specialised subjects. Advances in science and engineering is often accompanied by major development of mathematical sciences, as the latter underpin all other sciences. The UoL Centre will consist of a large and multidisciplinary team of applied and pure mathematicians, and statisticians together with healthcare researchers, clinicians and industrialists, collaborating with 15 HEIs and 40 NHS trusts plus other industrial partners and including our strongest groups: MRC Centre in Drug Safety Science, Centre for Cell imaging (CCI for live 3D and 4D imaging), Centre for Mathematical Imaging Techniques (unique in UK), Liverpool Biomedical EM unit, MRC Regenerative Medicine Hub, NIHR Health Protection Research Units, MRC Hub for Trials Methodology Research. Several research themes are highlighted below: Firstly, an improved understanding of the interaction dynamics of cells and tissues is crucial to developing effective future cures for cancer. Much of the current work is in 2D, with restrictive assumptions and without access to real data for modelling. We shall use the unparalleled real data of cell interactions in a 3D setting, generated at UoL's CCI. The real-life images obtained will have low contrast and noise and they will be analysed and enhanced by our imaging team through developing accurate and high resolution imaging models. The main imaging tools needed are segmentation methods (identifying objects such as cells and tissues regions in terms of sizes, shapes and precise boundaries). We shall propose and study a class of new 3D models, using our imaging data and analysis tools, to investigate and predict the spatial-temporal dynamics. Secondly, better models of how drugs are delivered to cells in tissues will improve personalised predictions of drug toxicity. We shall combine novel-imaging data of drug penetration into 3D experimental model systems with multi-scale mathematical models which scale-up from the level of cells to these model systems, with the ultimate aim of making better in-vitro to in-vivo predictions. Thirdly, there exist many competing models and software for imaging processing. However, for real images that have noise and are of low contrast, few methods are robust and accurate. To improve the modelling, applied and pure mathematicians team up to consider using more sophisticated tools of hyperbolic geometry and Riemann surfaces and fractional calculus to meet the demand for accuracy, and, applied mathematicians and statisticians will team up to design better data fidelity terms to model image discrepancies. Fourthly, resistance to current antibiotics means that previously treatable diseases are becoming deadly again. To understand and mitigate this, a better understanding is needed for how this resistance builds up across the human interaction networks and how it depends on antibiotic prescribing practices. To understand these scenarios, the mathematics competition in heterogeneous environments needs to be better understood. Our team links mathematical experts in analysing dynamical systems with experts in antimicrobial resistance and GPs to determine strategies that will mitigate or slow the development of anti-microbial resistance. Our research themes are aligned with, and will add value to, existing and current UoL and Research Council strategic investments, activities and future plans.

Building upon our existing flagship industry-linked EPSRC & MRC CDT in Systems Approaches to Biomedical Science (SABS), the new EPSRC CDT in Sustainable Approaches to Biomedical Science: Responsible and Reproducible Research - SABS:R^3 - will train a further five cohorts, each of 15 students, in cutting-edge systems approaches to biomedical research and, uniquely within the UK, in advanced practices in software engineering. Our renewed goal is to bring about a transformation of the research culture in computational biomedical science. Computational methods are now at the heart of biomedical research. From the simulation of the behaviour of complex systems, through the design and automation of laboratory experiments, to the analysis of both small and large-scale data, well-engineered software has proved capable of transforming biomedical science. Biomedical science is therefore dependent as never before on research software. Industries reliant on this continued innovation in biomedical science play a critical role in the UK economy. The biopharmaceutical and medical technology industrial sectors alone generate an annual turnover of over £63 billion and employ 233,000 scientists and staff. In his foreword to the 2017 Life Sciences Industrial Strategy, Sir John Bell noted that, "The global life sciences industry is expected to reach >$2 trillion in gross value by 2023... there are few, if any, sectors more important to support as part of the industrial strategy." The report identifies the need to provide training in skills in "informatics, computational, mathematical and statistics areas" as being of major concern for the life sciences industry. Over the last 9 years, the existing SABS CDT has been working with its consortium of now 22 industrial and institutional partners to meet these training needs. Over this same period, continued advances in information technology have accelerated the shift in the biomedical research landscape in an increasingly quantitative and predictive direction. As a result, computational and hence software-driven approaches now underpin all aspects of the research pipeline. In spite of this central importance, the development of research software is typically a by-product of the research process, with the research publication being the primary output. Research software is typically not made available to the research community, or even to peer reviewers, and therefore cannot be verified. Vast amounts of research time is lost (usually by PhD students with no formal training in software development) in re-implementing already-existing solutions from the literature. Even if successful, the re-implemented software is again not released to the community, and the cycle repeats. No consideration is made of the huge benefits of model verification, re-use, extension, and maintainability, nor of the implications for the reproducibility of the published research. Progress in biomedical science is thus impeded, with knock-on effects into clinical translation and knowledge transfer into industry. There is therefore an urgent need for a radically different approach. The SABS:R^3 CDT will build on the existing SABS Programme to equip a new generation of biomedical research scientists with not only the knowledge and methods necessary to take a quantitative and interdisciplinary approach, but also with advanced software engineering skills. By embedding this strong focus on sustainable and open computational methods, together with responsible and reproducible approaches, into all aspects of the new programme, our computationally-literate scientists will be equipped to act as ambassadors to bring about a transformation of biomedical research.

Medical imaging has made major contributions to healthcare, by providing noninvasive diagnostics, guidance, and unparalleled monitoring of treatment and understanding of disease. A suite of multimodal imaging modalities is nowadays available, and scanner hardware technology continues to advance, with high-field, hybrid, real-time and hand-held imaging further pushing on technological boundaries; furthermore, new developments of contrast agents and radioactive tracers open exciting new avenues in designing more targeted molecular imaging probes. Conventionally, the individual imaging components of probes and contrast mechanisms, acquisition and reconstruction, and analysis and interpretation are addressed separately. This however, is creating unnecessary silos between otherwise highly synergistic disciplines, which our current EPSRC CDT in Medical Imaging at King's College London and Imperial College London has already started to successfully challenge. Our new CDT will push this even further by bridging the different imaging disciplines and clinical applications, with the interdisciplinary research based on complementary collaborations and new research directions that would not have been possible five years ago. Through a comprehensive, integrated training programme in Smart Medical Imaging we will train the next generation of medical imaging researchers that is needed to reach the full potential of medical imaging through so-called "smart" imaging technologies. To achieve this ambitious goal we have developed four new Scientific Themes which are synergistically interlinked: AI-enabled Imaging, Smart Imaging Probes, Emerging Imaging and Affordable Imaging. This is complemented by a dedicated 1+3 training programme, with a new MRes in Healthcare Technologies at King's as the foundation year, strong industry links in form of industry placements, careers mentoring and workshops, entrepreneurship training, and opportunities in engaging with international training programmes and academic labs to become part of a wider cohort. Cohort building, Responsible Research & Innovation, Equality, Diversity & Inclusion, and Public Engagement will be firmly embedded in this programme. Students graduating from this CDT will have acquired a broad set of scientific and transferable skills that will enable them to work across the different medical imaging sub-disciplines, gaining a high employability over wider sectors.