Computational Pathology and Integrative Genomics Group

The group works to reconstruct two-dimensional or three-dimensional tumour models from images of tumour sections. Previously led by Professor Yinyin Yuan, it is now led by Professor Janet Shipley as interim.

Our group is investigating cancer tissue ecosystems and how selective pressures can promote cancer development.

Deciphering Tumour Microenvironement

A pathologic-genomic approach

Pathological analysis of tumour architecture and cell morphology dates back to the 19th century. Now, morden image-analysis tools promises objective and quantitative insights into hundreds of tumours.

By drawing on the rich information from pathological images and combining it with molecular data from next generation sequencing, we hope to offer more powerful approaches to study the microenvironment and its implications to cancer progression.

Building an automated classifier for histopathological images, enables us to identify heterogeneous cell populations in patient tumours and quantify their spatial proximity to each other.

Quantitative scores of cell spatial patterns

The cell spatial patterns can be summarised using methods from spatial statistics and pattern recognition techniques to provide quantitative scores.

These quantitative scores of cell patterns can reveal various metrics that would be impossible to conclude by eye, for example, the degree of clustering and the spatial interactions between different cells.

Discovery of functional roles of normal cells

One of the central dogma in cancer biology is the functional roles of heterogenous types of cells in cancer progression.

With quantitative readout from the images, we can correlate the abundance and spatial patterns of cells with patient outcome. For example, by summarising the abundance of lymphocytes in the ER-negative breast cancer, we are able to stratify patients into different outcome groups, where the patients with high numbers of lymphoctyes have significantly better prognosis than patients with few lymphocytes.

Integrating images with molecular signal

Combining molecular signal from the same samples, the image-based quantitative scores can either complement molecular data, or offer completely new observations from this entirely different angle.

The Computational Pathology and Integrative Genomics Team sits within the Centre for Evolution and Cancer and the Centre for Molecular Pathology. The scientists within this team are investigating cancer tissue ecosystems and how selective pressures can promote cancer development. Understanding how tumours adapt to their microenvironment is key to appreciating how they grow and spread, and could direct interventions to alter or stop the selective pressures helping to drive their growth.

As cancer cells all evolve dynamically within the habitats of our tissues on which they retain some dependence, therapeutic regulation of the ecosystem may be a viable alternative to the current notion of trying to kill cancer cells directly - a bit like draining the swamps to get rid of mosquitoes as one way of eradicating malaria.

Such approaches might provide a Darwinian bypass that uses selective pressure on the tumour ecosystem to avoid the problems that drug resistance can bring. In fact doctors can already target the ecosystem, with anti-hormonal therapies (such as tamoxifen for breast cancer), anti-inflammatories (such as aspirin for gastrointestinal cancer), and anti-angiogenesis therapies (that stop new blood vessel formation) are already being used for this.

The team focusses on developing computational approaches to combine statistical modelling with automated image analysis of tumours. The scientists are looking at the different regions within a genetically variable (heterogeneous) tumour and analysing them as if they are different ecological systems.

The team trains powerful computers to automatically identify cancer cells in pathology samples from the clinic. By drawing on the rich information contained in these images, and combining it with the data describing the DNA sequences of the cancer cells, so the team can construct two and three dimensional images of tumour sections. This enables them to explore the complexities of the tumour microenvironment and to develop new tools to diagnose patients or to predict how they might respond to a treatment, and to explore the consequences of how different regions and populations of cells within the tumour interact.

Professor Janet Shipley

Group Leader:

Sarcoma Molecular Pathology, Computational Pathology and Integrative Genomics Professor Janet Shipley

Professor Janet Shipley is investigating ways to improve the treatment of patients with sarcomas that have a poor outcome.

See profile

Recent discoveries from this group

24/02/25

Researchers have developed an artificial intelligence-based model that can help pathologists grade certain lung cancer tumours and predict patients’ outcomes. It does this by assessing the growth patterns in tumour samples, which can vary significantly among patients.

In a recent study, the grading achieved using the model, which is called ANORAK (pyrAmid pooliNg crOss stReam Attention networK), was predictive of disease-free survival (DFS). DFS is the length of time between treatment for lung adenocarcinoma – the most common type of non-small cell lung cancer (NSCLC) – and the return of signs or symptoms.

In the longer term, this model could help clinicians determine how best to treat each of their patients based on the likely progression of their cancer. Improved decision-making at the treatment stage could lead to better outcomes overall in this type of lung cancer. With recently introduced cancer screening programmes significantly increasing the identification of early-stage lung cancer, improving these treatment decisions is more urgent than ever before.

ANORAK was primarily created by scientists at The Institute of Cancer Research, London, with the work funded by a Cancer Research UK Career Establishment Award. The paper has been published in the journal Nature Cancer.

Challenges in tumour grading in lung adenocarcinoma

Lung adenocarcinoma will typically adopt one of six types of growth pattern, with a single tumour often combining multiple types. A global grading system known as the International Association for the Study of Lung Cancer (IASLC) system proposes that these growth patterns predict the extent to which a patient is at risk of disease progression or recurrence.

The combination of distinct pattern types that may appear within a tumour can make it difficult for pathologists to determine a person's outlook, as can the fact that the appearance of each type of pattern varies across a spectrum. The difficulties encountered in defining and quantifying the broad range of growth patterns means that different pathologists may not make the same decision when it comes to grading a tumour.

The risk of suboptimal or inconsistent grading by pathologists is that it leads to inadequate or inappropriate treatment for some patients, potentially putting them at risk of poorer outcomes.

Developing the deep learning model ANORAK

Although previous studies have applied deep learning models to the classification of growth patterns in lung adenocarcinoma, these models have not taken into account the detailed morphological structure of the patterns. What is more, they have not been able to provide automated IASLC grading.

In this study, the researchers developed an AI method, ANORAK, that was able to distinguish between the six types of lung adenocarcinoma growth pattern by assessing them at the pixel level. They applied it to 5,540 tumour samples on diagnostic slides, which came from a total of 1,372 people with the disease. The model was able to improve patient risk stratification, with patients identified as having IASLC grade 1 or 2 tumours having significantly longer DFS than those identified as having IASLC grade 3 tumours.

To further validate the ANORAK model, the team compared the information it provided with manual grading information from three pathologists. The AI grading was comparable with the pathologist grading across the board, even slightly outperforming it for one cohort of patients.

By referring to previous studies, the researchers were also able to show that the extent to which the AI and manual gradings agreed on the predominant growth pattern in a tumour was consistent with the level of agreement between different pathologists. Overall, the team concluded that AI grading added prognostic value, particularly in early-stage lung adenocarcinoma, where treatment decisions can be difficult.

In the second part of the study, the researchers considered four specific scenarios that pathologists might find particularly challenging. These included cases with four or more diagnostic slides per tumour and cases with highly diversified growth patterns. The ANORAK model performed well in each of the four scenarios, leading the team to conclude that their method could help pathologists grade growth patterns even when the case is more demanding than usual.

Finally, the researchers focused on the most common of the six growth patterns: the acinar pattern. Using ANORAK, they were able to achieve a better understanding of the shapes and structures of the acinar pattern. They also determined correlations between various acinar subtypes and different tumour characteristics, including some associated with a poor outlook.

Some achievements are only possible using AI

First author Dr Xiaoxi Pan, then a Postdoctoral Training Fellow in the Computational Pathology and Integrative Genomics Group at the Institute of Cancer Research (ICR), said:

“Diagnostic inaccuracies and variability among pathologists are longstanding issues in lung adenocarcinoma. Our study is the first to implement the IASLC grading system with an AI-powered tool and validate the prognostic values on two distinct cohorts.

“Our AI method enables the precise and automated quantification of unique growth patterns within a tumour, thereby inferring the predominant pattern and grading. It has also identified previously undiscovered morphological and spatial features of certain tissues that were not achievable using existing algorithms or human observations.”

Second author Dr Khalid Abdul Jabbar, who was a postdoc in the same group at the ICR at the time, said:

“We were delighted that our AI method not only matched but also consistently enhanced the prognostic value of grading in early-stage tumours, including in challenging scenarios. Its capability to identify high-risk tumours could aid the selection of patients for additional treatment in a reproducible manner, free from variability among observers.

“Additionally, in the research setting, it has the potential to integrate with genetic data, which could lead to new biotechnical tools and deeper insights into tumour evolution.”

The researchers have already planned further studies to incorporate genetic data into their work, with the aim of better understanding how tumours progress and how this is influenced by the cells and tissues surrounding them. The team will also be trialling ANORAK in larger groups of people with early-stage lung adenocarcinoma to provide further evidence of its effectiveness.