Researchers use artificial intelligence to help tailor bowel cancer treatment
A leading group of researchers have developed a new way to study bowel cancer samples using digital images. This means that patients could be better matched to the best treatment for them.
Previous research has shown that there are four distinct subtypes of bowel cancer. These subtypes group bowel cancers by common features such as specific gene changes. Clinicians hope to be able to use this information to help decide which treatments are likely to work best for which patients.
At the moment, sophisticated technology which looks at changes in genes that make up bowel cancer (known as gene-sequencing technology) is used to work out which of these four types of bowel cancer a patient might have. This process is expensive and needs specialist knowledge to understand the large amounts of data that is produced. This means it’s not very widely used at the moment.
In a study by the S:CORT (which stands for stratification in colorectal cancer) consortium, researchers jointly led by Prof. Jens Rittscher (Dept. of Engineering Science, University of Oxford) and Prof. Viktor Koelzer (Dept. of Pathology and Molecular Pathology, University of Zurich) have used advanced machine learning to overcome some of these problems.
They have trained a computational model to analyse digital images of bowel cancer samples. The programme looks at how the cells and structures in the sample are organised and then works out which of the four subtypes the bowel cancer belongs to.
Tim Maughan, leader of the S:CORT consortium comments: “this research shows that, with the help of computer analysis, it is possible to detect complex biological patterns from the way the 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 this in the future to guide treatment decisions”.
This is less expensive than the gene sequencing technologies and can use samples that are already being taken in the clinic. In their new research paper, the team found that the imaging programme was able to accurately predict the subtype of the bowel cancer. The researchers suggest this is a technique that could not only be used for bowel cancer, but also other cancers and disease types in the future.
Dr Lisa Wilde, Director of Research and External Affairs, said: “This is an exciting step forward in the development of a clinical test that could help personalise treatment for patients with bowel cancer. We know that the use of artificial intelligence has great promise for improving the diagnosis and treatment of cancer.
We are also delighted that this research is tackling research gaps identified in our Critical Gap in Colorectal Cancer Research project. We look forward to seeing how this work is further developed and implemented.”