Exploring advanced FDG PET-CT imaging feature analysis for more accurate diagnosis and outcome prediction in suspected large vessel vasculitis

The aim of this project is to discover and validate predictive parameters extracted from FDG PET-CT images of patients with and without LVV that will allow the development of a radiomic model that can determine the prognosis of LVV patients effectively.

Objectives:
- Collate outcome data for a large single centre cohort of patients with baseline FDG PET-CT data
- Use advanced feature analysis and machine learning to develop putative diagnostic and predictive imaging biomarkers in test and validation cohorts derived from FDG PET-CT images of patients with and without GCA from dataset from a single centre
- Correlate outcomes with extracted parameters to determine which parameters have the best performance characteristics
- Validate test performance within a multi-centre FDG PET-CT imaging cohort allowing for harmonisation of the process across different scanners. Data pooling facilitated as part of an established GCA multi-centre trial in the UK (TARGET Consortium, MRC)
- Explore the potential of this process in (a) other forms of LVV, and (b) MRA and CTA imaging

The facilities used for this project will include:
- Deep learning software to build a radiomic model
- Image analysis software (LifeX)
- Baseline FDG PET-CT data from the 2011-2017 Leeds LVV cohort
- FDG PET-CT from patients who were tested but not diagnosed with LVV
- FDG PET-CT data from other centres to validate the model
- MRA & CTA data taken during the treatment of the 2011-2017 Leeds LVV cohort

The analysis of medical images requires developing an understanding of interactions between modality / modalities and disease. While PET-CT, MRA and CTA imaging of LVV is well established, not all the data provided by these scans will have been analysed; the relevant extracted features could provide valuable insights into the characteristics of the disease that have not been discovered through routine / traditional clinical approaches.

The radiomic features (the parameters extracted) relevant to LVV prognosis are currently unknown but could include:
- the heterogeneity of the vessel (textural analysis)
- size, shape and location of inflammation
- relationship with neighbouring tissues (requires statistical analysis considering parameters such as energy and entropy)
- intensity of signal
- density of tissue
- parameters that may be unique to the illness and not established previously

Once the parameters are determined, their relationship to the disease and its phenotype may be established.

The features will be vulnerable to image quality of the data and image processing methods such as over smoothing in the case of textural analysis. Therefore the methods will require optimisation and will not necessarily be directly transferable from previous work.

Once the parameters have been established, we will create a novel radiomic model that can: (a) determine predictive biomarkers in a given image and (b) make patient outcome predictions. For these purposes, we will utilise deep learning with the help of a convolutional artificial neural network. The multiple layers of this network will serve a purpose, ranging from data extraction, through to the evaluation of a given feature. The image will cascade through the layers being weighted by the criteria and the model will make a judgement about the accuracy and precision of the prognosis. The model will need to be trained to recognise the predictive biomarkers with a large data set to minimise incorrect predictions.

As the project will be co-supervised by clinicians at the forefront of LVV research, it will be designed to be clinically relevant and useful.

Regenerative Medicine been defined as "an interdisciplinary approach, spanning tissue
engineering, stem cell biology, gene therapy, cellular therapeutics, biomaterials (scaffolds and matrices),nanoscience, bioengineering and chemical biology that seeks to repair or replace damaged or diseased human cells or tissues to restore normal function, (UK Strategy for Regenerative Medicine). CDT TERM will focus on acellular therapies, scaffolds,autologous cells and regenerative devices, which can be delivered to patients as class three device interventions, thus reducing the time and cost of translation and which provide an opportunity to deliver economic growth and benefits to health in the next decade. The primary beneficiaries of CDT TERM are patients, the health service, UK industry, as well as the academic community and the students themselves. Recognising that the impact and benefit from CDT TERM will arise in the future, the statements describing impact below are supported by evidence of actual impact from our existing research and training.

Patients will benefit from regenerative interventions, which address unmet clinical needs, have improved safety and reliability, have been stratified to meet patients needs and manufactured in a cost effective manner. An example of impact arising from previous students work is a new acellular scaffold for young adult heart valve repair, which has demonstrated improved clinical outcomes at five years.

The Health Service will benefit from collaborations on research, development and evaluation of technologies, through existing partnerships with National Health Service Blood and Transplant NHSBT and the Leeds Biomedical Musculoskeletal Research Unit LMBRU. NHSBT will benefit through collaborative projects, through technology transfer, through enhancement of manufacturing processes, through pre-clinical evaluation of products and supply of trained personnel. We currently collaborate on heart valves, skin, ligaments and arteries, have licensed patents on acellular bioprocesses, and support product and process developments with pre-clinical testing and simulation. LMBRU and NHS clinicians will benefits from our collaborative research and training environment and access to our research expertise, facilities and students. Existing collaborative projects include, delivery devices for minimally manipulated stem cells and applied imaging for early OA.

Industry will benefit from supply of highly trained multidisciplinary engineers and scientists, from collaborative research and development projects, from creation and translation of IP, creation of spinout companies and through access to unique equipment, facilities and expertise. We have demonstrated: successful spin outs in form of Tissue Regenix and Credentis; successful commercialisation of a novel biological scaffolds for vascular patch repair; sustainable long term R and D and successful licensing of technology with DePuy; collaborative research with Invibio, partnering with Simulation Solutions to develop new pre-clinical simulation systems, which been adopted by regulatory agencies such as China FDA. Our graduates and researchers are employed by our industry partners.

The academic community will benefit through collaborative research and access to our facilities. We have funded collaborations with over 30 academic institutions in UK and internationally. The CDT TERM will support these collaborations and the academic partners will support student research and training. The CDT students will benefit from enhanced integrated multidisciplinary training and research, a cohort experience focused on research innovation and translation, access to our research partners, industry and clinicians. Feedback from existing students has identified the benefit of the multidisciplinary experience, the depth and breadth of excellence in our research base, the outstanding facilities and the added value of the cohort training.