MRI to Histology mapping using Deep Learning

1. Context of the research including potential impact

Prostate cancer (PCa) is the second most commonly diagnosed cancer and the fifth leading cause of cancer death among men worldwide. Moreover, the burden of PCa is expected to rise due to population aging and economic growth. Early diagnosis and treatment are critical to reduce mortality rate.
The current gold standard for cancer diagnosis is histological analysis of a biopsy sample. This method has several limitations: i) It is invasive, with side effects and risks, such as infection, bleeding and urinary retention. ii) The sample analysed is small, so cancer can be missed or under/overestimated. iii) The grading system, e.g. the Gleason score for PCa, is subjective and inconsistent. In contrast, MRI is a non-invasive technique that can scan whole organs and can support an objective grading system.
MRI has been extensively studied as a tool for diagnosis of PCa. To standardise acquisition, interpretation and reporting of prostate multi-parametric MRI (mpMRI) examinations, a set of guidelines has been developed: The Prostate Imaging Reporting and Data System (PI-RADS). It is important to note that while the use of mp-MRI before prostate biopsy is strongly recommended, it is not yet suitable for use as an initial screening tool. mpMRI has low specificity and would create a large amount of false-positive results in very low-risk patients.
mpMRI typically consists of T2-weighted (T2W), diffusion weighted (DWI) and contrast enhanced (DCE) images. DWI is relevant in cancer detection because it detects water movement at length scales beyond the image resolution and can be used to deduce physiological parameters of the tissue. Model-based approaches aim to separate the effects of different parameters on diffusion. An example is the VERDICT (Vascular, Extracellular and Restricted Diffusion for Cytometry in Tumors) model, which assumes that the diffusion contributions can be categorised into three primary components: vascular, extracellular-extravascular space, and intracellular water. VERDICT MRI has been shown to help differentiate PCa from healthy tissue and to provide more microstructural feature information than images derived from similar models.

2. Aims and objectives

The main goal in this project is to develop a novel framework based on machine learning methods that enables in-vivo MRI to become the primary diagnostic and prognostic tool for PCa in clinical practice. This would have a meaningful impact on PCa patients: it would enable highly targeted therapy and reduce the need for biopsies. Being able to identify patients with good prognosis could avoid unnecessary prostatectomies, reducing side-effects and minimising healthcare costs.

3. Novelty of the research methodology
- Novel dataset: the project will levera
ge large prostate MRI datasets that belong to on-going clinical trials at UCLH, as well as a unique set of matched annotated MRI with histological prostatectomy data.
- Novel methods: the project will develop new techniques based on machine learning to leverage the unique dataset. It will aim to provide state-of-the-art results for diagnosis and prognosis of PCa from MR images.

4. Alignment to ESPRC's strategies and research areas

This project aligns with the ESPRC's strategy for medical imaging. In particular, it fits into two high priority areas:
- Earlier diagnosis: by providing accurate diagnosis from initial mpMRI
- Automated extraction and integration: by using machine learning techniques to obtain additional information from mpMRI

5. Any companies or collaborators involved

None

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.