Assessing Response to Therapy of Colon Cancer Based on Tissue Morphology

Around 13,000 people are diagnosed each year with rectal cancer in the UK. Common treatments include radiotherapy, but one third of rectal cancer patients have a poor response to conventional radiotherapy. A genetic test developed by Maughan and Domingo shows promise in predicting a patient's response to radiotherapy with 88% accuracy. Although this 33 gene expression score (RSS) has not been published, it has been validated on an extensive patient cohort. Further development will be required before this test can be used in the clinic.Recent research has demonstrated the ability to predict response to therapy or indeed biologically relevant information from morphological features extracted from standard H&E images. Building on recent advances in deep learning I aim to build a histology-based predictor capable of predicting which rectal cancer patients should be treated with radiotherapy. This predictor should mimic RSS, but as it is based on standard H&E images it could be deployed much faster and it would offer the possibility to simplify patient recruitment.
Aim 1 - Develop imRSS: Develop an image-based approach for predicting the RSS gene signature score from histology slides, using attention-based deep learning techniques. Aim 2 Explainability of imRSS: Acceptance and adoption will depend on the interpretability of the newly developed signature. First, I will investigate if any of the identified morphological features can be linked to cancer biology. Secondly, I will determine how several different histology-based signatures (including imRSS, imCMS and microsatellite instability) can be utilised to provide a better interpretation of a patient sample. Aim 3 - Longitudinal clinical study: Using a set of selected patients I will investigate how the histology-based features can be set in context with other clinical information, for example radiology and other laboratory tests. The goal of this aim is to analyse how the newly developed predictor will affect clinical decision making, while considering the challenges and requirements of integrating an AI based digital pathology algorithm into the clinical workflow.
I will be working closely with clinical scientists to evaluate if the developed methodology can be used for patient stratification and patient management. It has the potential to be a cheaper and faster alternative to gene sequencing panels. In the long term, this work can be incorporated into a gastrointestinal pathway to aid clinicians in choosing appropriate treatment for their rectal cancer patients.

In the same way that bioinformatics has transformed genomic research and clinical practice, health data science will have a dramatic and lasting impact upon the broader fields of medical research, population health, and healthcare delivery. The beneficiaries of the proposed training programme, and of the research that it delivers and enables, will include academia, industry, healthcare, and the broader UK economy.

Academia: Graduates of the training programme will be well placed to start their post-doctoral careers in leading academic institutions, engaging in high-impact multi-disciplinary research, helping to build training and research capacity, sharing their experience within the wider academic community.

Industry: Partner organisations will benefit from close collaboration with leading researchers, from the joint exploration of research priorities, and from the commercialisation of arising intellectual property. Other organisations will benefit from the availability of highly-qualified graduates with skills in big health data analytics.

Healthcare: Healthcare organisations and patients will benefit from the results of enabled and accelerated health research, leading to new treatments and technologies, and an improved ability to identify and evaluate potential improvements in practice through the analysis of real-world health data.

Economy: The life sciences sector is a key component of the UK economy. The programme will provide partner companies with direct access to leading-edge research. Graduates of the programme will be well-qualified to contribute to economic growth - supporting health research and the development of new products and services - and will be able to inform policy and decision making at organisational, regional, and national levels.