Non-invasive histology for cancer diagnosis with diffusion MRI and machine learning

Brief description of the context of the research including potential impact

Cancer diagnosis is often inaccurate, and the resulting treatment ineffective far too often. The current gold standard for identifying cancer types and informing treatment is histology, but this is an invasive procedure where tissue is extracted with a biopsy needle. This can have side effects and also only targets a small area, making it possible to miss vital tumour regions and require repetition. In addition, biopsies are limited to very small samples and also miss the possibility of metastases.

Medical imaging has many potential advantages when it comes to cancer diagnosis. It is in vivo, can be non-invasive and allows non-localised view of the whole organ or region of interest. However, current imaging techniques lack the discriminatory power and the sensitivity of histology. The objective of this project is to use computational modelling and machine learning to develop tools to support noninvasive imaging techniques capable of estimating the same cellular characteristics as histology. The project will focus on utilizing Magnetic Resonance Imaging (MRI). In particular we will develop models based on the Vascular Extracellular and Restricted DIffusion for Cytometry in Tumours (VERDICT)-MRI framework that allows analysis of tumour microstructure.

The method is currently part of clinical trials for prostate cancer diagnosis. VERDICT was successful in delineating benign from cancer lesions and also achieved discrimination of Gleason scores. Previous work used traditional model fitting, which has several drawbacks. This work will explore deep learning algorithms to improve the fitting as well as the modelling of the tumour microstructure. Initially, the project will leverage existing prostate MRI datasets with histological diagnosis. This will enable us to explore difficult clinical problems, such as false positive results when diagnosing prostate cancer. Subsequently we will explore modelling of other cancers such as breast and rectal.

Aims and Objectives
-The specific objectives are to:

1. Use machine learning to achieve robust tissue parameter estimation for comprehensive tumour characterization with existing models.
2. Develop new computational models of water diffusion and relaxation in cancerous and benign tissue by investigating histology and tumour biology.
3. Compare and evaluate the new methods against conventional MRI, histology and with simulations.
4. Use machine learning to exploit standard clinical MRI to synthesize VERDICT-type data to enable extraction of microstructural indices.

Novelty of Research Methodology

1. Develop new deep learning methods to enable complex model fitting and utilise these tools for clinical studies.
2. Develop novel models of cancer microstructure to enhance prostate cancer diagnosis using diffusion MRI.
3. Create new non-invasive microstructural imaging techniques for other cancers, such as breast and rectal.

Alignment to EPSRC's strategies and research areas

This project aligns firstly with the EPSRC strategy for enabling earlier and more effective diagnosis of physical and mental health conditions, to inform treatment planning. This is done by the aim of this project to improve cancer diagnosis methods as they currently stand. The project also aligns with the strategy for automated extraction and/or integration of existing and additional information from clinical data/images (e.g. via machine learning and/or mathematical science techniques), by aiming to improve the parameter fitting aspect using deep learning methods.

Any companies or collaborators involved

Prof. Shonit Punwani, Dr. Saurabh Singh, Dr Andrew Plumb (Div. Medicine UCL, UCLH), Dr. Bernard Siow (Crick Institute)

The critical mass of scientists and engineers that i4health will produce will ensure the UK's continued standing as a world-leader in medical imaging and healthcare technology research. In addition to continued academic excellence, they will further support a future culture of industry and entrepreneurship in healthcare technologies driven by highly trained engineers with deep understanding of the key factors involved in delivering effective translatable and marketable technology. They will achieve this through high quality engineering and imaging science, a broad view of other relevant technological areas, the ability to pinpoint clinical gaps and needs, consideration of clinical user requirements, and patient considerations. Our graduates will provide the drive, determination and enthusiasm to build future UK industry in this vital area via start-ups and spin-outs adding to the burgeoning community of healthcare-related SMEs in London and the rest of the UK. The training in entrepreneurship, coupled with the vibrant environment we are developing for this topic via unique linkage of Engineering and Medicine at UCL, is specifically designed to foster such outcomes. These same innovative leaders will bolster the UK's presence in medical multinationals - pharmaceutical companies, scanner manufacturers, etc. - and ensure the UK's competitiveness as a location for future R&D and medical engineering. They will also provide an invaluable source of expertise for the future NHS and other healthcare-delivery services enabling rapid translation and uptake of the latest imaging and healthcare technologies at the clinical front line. The ultimate impact will be on people and patients, both in the UK and internationally, who will benefit from the increased knowledge of health and disease, as well as better treatment and healthcare management provided by the future technologies our trainees will produce.

In addition to impact in healthcare research, development, and capability, the CDT will have major impact on the students we will attract and train. We will provide our talented cohorts of students with the skills required to lead academic research in this area, to lead industrial development and to make a significant impact as advocates of the science and engineering of their discipline. The i4health CDT's combination of the highest academic standards of research with excellent in-depth training in core skills will mean that our cohorts of students will be in great demand placing them in a powerful position to sculpt their own careers, have major impact within our discipline, while influencing the international mindset and direction. Strong evidence demonstrates this in our existing cohorts of students through high levels of conference podium talks in the most prestigious venues in our field, conference prizes, high impact publications in both engineering, clinical, and general science journals, as well as post-PhD fellowships and career progression. The content and training innovations we propose in i4health will ensure this continues and expands over the next decade.