MICA: Developing Micro-Community Analytics for Histology Landscapes (MiCAHiL)

The current 'gold standard' for diagnosis and grading of many diseases (including most solid tumours) is largely based on an expert histopathologist's visual microscopic assessment of an extremely thin (only a few micrometers thick) section of the suspicious tissue specimen glued to a glass slide. This practice has remained more or less the same for several decades, and results in subjective and variable diagnosis. However, the recent uptake of digital slide scanners by some diagnostic pathology laboratories in the UK marks a new revolution in pathology practice in the NHS trusts, with our local NHS trust being the first one in the country to use digitally scanned images of tissue slides for routine diagnostics. The digital slide scanner produces a multi-gigapixel whole-slide image (WSI) for each histology slide, with each image containing rich information about tens of thousands of different kinds of cells and their spatial relationships with each other.

This project aims to introduce a novel paradigm for analytics and computerised profiling of tissue microenvironment. We will develop sophisticated tools for image analytics in order to reveal spatial trends and patterns associated with disease sub-groups (for example, patient groups whose cancer is likely to advance more aggressively) and deploy those tools for clinical validation at our local NHS trust. This will be made possible by further advancing recent developments made in our group, such as those allowing us to recognise individual cells of different kinds in the WSIs consequently enabling us to paint a colourful picture of the tissue microenvironment which we term as the 'histology landscape'. Understanding and analysing the tissue microenvironment is not only crucial to assessing the grade and aggressiveness of disease and for predicting its course, it can also help us better understand how genomic alterations manifest themselves as structural changes in the tissue microenvironment. We will develop tools and techniques to extract patterns and trends found in the spatial structure and the 'social' interplay of different cells or colonies of cells found in the complex histology landscapes. Our goal is to establish the effective use of image analytics for understanding the histology landscape in a quantitative and systematic manner, facilitating the discovery of image-based markers of disease progression and survival that are intuitive, biologically meaningful, and clinically relevant - eventually leading to optimal selection of treatment option(s) customised to individual patients.

This project will analyse real image data and associated clinical and genomics data from patient cohorts for colorectal cancer as a case study. The research staff on this project will work closely with clinical collaborators to ensure the biological significance and clinical relevance of spatial trends and patterns found in the data. In collaboration with our industrial partner Intel, we will test and demonstrate the effectiveness of our methods in a clinical setting potentially leading to better healthcare provision for patients and potential cost savings for the NHS.

The recent arrival of digital slide scanners into diagnostic pathology laboratories in the UK marks a new revolution in pathology practice in the NHS trusts. Tissue microenvironment in a high-resolution image scanned from a tissue slide presents itself as a 'histology landscape' containing rich information about tens of thousands of cells, communities of cells, and their spatial relationships with each other. In this project, we will develop multi-scale community analytics methods for histology landscapes in order to reveal intuitive, biologically meaningful, and clinically relevant spatial trends and patterns involving various types of cells and communities of cells. We will use colorectal cancer as a case study, while creating methods with wider applicability to other diseases. Novel analytics methods developed in this project offer several advantages: First, accurate, large-scale quantification of the cell types and their spatial distribution including recognition of concept-driven or empirically derived diagnostic motifs at both cellular and community levels will allow more precise prognostic and therapeutic stratification than is currently possible by conventional analysis relying on the human eye. Second, recognition and quantification of social interactions between various different cell populations is likely to lead to novel prognostic data with relevance to personalised medicine. And finally, for diseases with heavy genetic influence such as cancer, a combination of results of image analytics and molecular level changes in the DNA of tumour cells can enable us to understand the downstream effects of genomic alterations on spatial tumour microenvironment, i.e. how such alterations manifest themselves in terms of tumour morphology, micro-architecture, and social networks of cell communities.

This project is anticipated to contribute to the strategic development of the Methodology Research Programme portfolio of MRC, by adding to the portfolio the next generation of algorithms for analytics of digital pathology images (a relatively novel imaging modality) with the goal of improving diagnosis and selection optimal treatment option(s) thereby resulting in better healthcare provision for patients and potential cost savings for the NHS. Major and direct beneficiaries of this project include the MRC/EPSRC Molecular Pathology Nodes (MPNs), the recently established Digital Pathology Centre of Excellence (DP-CoE) at the University Hospitals Coventry & Warwickshire (UHCW) NHS Trust - which is envisaged to act as a role model for other histopathology labs in the UK NHS and beyond - and Digital Pathology (DP) software vendors.

1. Molecular Pathology Nodes: With the increasing uptake of DP, it is envisaged that pathology labs in the developed world will embrace DP within the next few years. This is perhaps why DP is one of the cornerstones of the MPNs. We will work closely with Nottingham MPN (NMPN) and provide access to our image analytics methods for research purposes, contributing in particular to WS3 and WS4 (led by co-I Ilyas) of the NMPN. Our methods will allow the NMPN to build mathematical models required to integrate multi-platform biomarker data from multiple sources, including the digital pathology image data, and will contribute towards understanding the histological and molecular bases of variable outcomes and treatment responses consequently resulting in better patient stratification. Analytics methods developed in this project will be made available to researchers at the Glasgow MPN (GMPN) and will contribute towards the GMPN achieving its goal of building complex informatics using effective methods for the analysis of large datasets (including digitised whole-slide images of tissue slides) that emerge from molecular research.

2. UHCW DP-CoE: With the objectives of improving patient care and making more efficient use of hospital resources through the intelligent use of computer-aided diagnostics, UHCW has recently invested £1.5m in its Digital Pathology unit and has recently become the first hospital in the UK to digitise its histopathology for routine diagnostics. As part of WP4, we will incorporate some of our clinically ready-for-trial software into standard workflow of the UHCW Pathology Department. These are truly ideal circumstances for rapidly translating high quality academic research into practical and visible results, consequently resulting in improved diagnosis and care for cancer patients.

3. Clinical Pathologists: The project will develop sophisticated tools and techniques for advanced histology morphometrics. As part of the project, the technologies will be deployed to the pathologist workstation for large-scale validation on real clinical data, allowing the histopathologist to employ automated spatial features and patterns for computer-assisted diagnosis, grading, and prognostics of cancer in the long run. The last workpackage (WP4) provides a direct path for such exploration and validation.

4. Digital Pathology (DP) Software Vendors: Technologies developed in this project (WP1-3) will be licensed to DP software vendors for commercial exploitation with the help of Warwick Ventures, a tech-transfer arm of Warwick, subject to appropriate IP protection. Warwick Ventures is already working with the PI on the exploitation of IP developed in his lab and negotiations are currently under way with several DP software vendors for the purposes of commercial exploitation.