Researchers use artificial intelligence to help tailor bowel cancer treatment

In a study by the S:CORT (Stratification in COloRecTal cancer) consortium, researchers led by Jens Rittscher (Dept. of Engineering Science, University of Oxford) and Viktor Koelzer (Dept. of Pathology and Molecular Pathology, University of Zurich) have used advanced machine learning approaches to study bowel cancer samples using digital images to establish the cancer subtype. This offers hope of more personalised treatment for bowel cancer patients.

Previous research has shown there are four distinct bowel cancer subtypes. Bowel cancers are grouped into subtypes by common patterns of gene expression – that is which genes are switched on or off. Clinicians hope to use this information in deciding which treatments are likely to work best. Currently, bowel cancer subtype is established through RNA analysis, which is not widely used due to high costs and the need for specialist knowledge to interpret the data.

The S:CORT team have trained a computational model to analyse digital images of bowel cancer samples, looking at how cells and structures in the sample are organised and working out the subtype. This is less expensive than sequencing and can use samples routinely taken in the clinic. In their new research paper, the team found the programme was able to accurately predict subtype from standard and readily available imaging data. They suggest this is a technique that could be used for other cancers and disease types in future.

“This research shows that, with the help of computer analysis, it is possible to detect complex biological patterns from the way cancer looks under the microscope using routine ways to prepare tissue slides. This has great potential for providing information on how the cancer will behave in the individual and use in the future to guide treatment decisions.” Tim Maughan, leader of the S:CORT consortium.

Dr Lisa Wilde, Director of Research and External Affairs, Bowel Cancer UK, comments: “This is an exciting step forward in the development of a clinical test that could help personalise treatment for bowel cancer patients.  We know that the use of AI has great promise for improving the diagnosis and treatment of cancer. We are also delighted that this work is tackling research gaps identified in our Critical Gap in Colorectal Cancer Research project.”

Find out more about our research below

New Oxford technology assesses cancer patient vulnerability to COVID-19

New research from Prof Julia Hippisley-Cox has resulted in thousands of cancer patients being given prioritised access to the COVID-19 vaccine.

Understanding how cancer arises from infected tissue

Dr Francesco Boccellato is investigating the mechanisms behind the pre-cancerous condition known as atrophic gastritis. This may help to identify those who may have cancer, as well as find new ways to prevent cancer from progressing

Bowel cancer patients going undiagnosed due to COVID distruption

A new study led by the University of Oxford has found that since the first coronavirus lockdown the number of people diagnosed with bowel cancer in England has fallen sharply, with a deficit persisting up to October 2020

Bioengineering the human gut

An interdisciplinary collaboration generates an advanced model of the human gastrointestinal tract with broad applications for disease research and regenerative medicine
Image from an endoscopy video with the detected artefacts highlighted with coloured boxes.

Using AI to improve the quality of endoscopy videos

A multidisciplinary team of researchers has developed a deep-learning framework for improving endoscopy to aid cancer detection.

The search for pancreatic cancer biomarkers

Nuffield Department of Population Health researchers are using the China Kadoorie Biobank to identify potential protein biomarkers in the blood that could be used to predict the presence or development of pancreatic cancer

Early stage ‘red flag’ symptoms for pancreatic cancer

The ADEPTS study uses the QResearch database to better understand what ‘red flag’ symptoms may be associated with pancreatic cancer, in the hopes of promoting earlier diagnosis from primary care.

Understanding breast cancer risk in Chinese populations

Researchers from the Clinical Trial Service Unit and Epidemiological Studies Unit (CTSU) are utilising the China Kadoorie Biobank to better understand how breast cancer risk factors may differ between individuals from Western and Eastern populations

Using big data in breast cancer research

The Cancer Epidemiology Unit has been using the largest epidemiological data set of its kind to unlock the secrets of breast cancer, what can be done to prevent it, and which women are most likely to develop it