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

Study investigating targeted drug delivery by focused ultrasound for pancreatic cancer opens

University of Oxford researchers have begun recruitment to a study looking at whether chemotherapy medication can reach pancreatic tumours more effectively if encapsulated within a heat-sensitive shell and triggered with focused ultrasound.
Image from an endoscopy video with the detected artefacts highlighted with coloured boxes.

AI endoscopy enables 3D surface measurements of pre-cancerous conditions in oesophagus

Clinicians and engineers in Oxford have begun using artificial intelligence alongside endoscopy to get more accurate readings of the pre-cancerous condition Barrett’s oesophagus and so determine patients most at risk of developing cancer.

Eoghan Mullholland awarded colorectal cancer fellowship

As part of UK Pride month, we are spotlighting the work of cancer researcher and University LGBTQ+ Representative Dr Eoghan Mulholland

Artificial intelligence tool for streamlining pathology workflow

A multidisciplinary team in Oxford has developed an algorithm for automated requesting of additional investigation in diagnostically uncertain prostate biopsies.

New prostate cancer risk tool

A new calculator has been developed by Professors Julia Hippisley-Cox and Carol Coupland to help GPs prioritise patients at high risk of prostate cancer.

New study investigates how growth factors in our gut could initiate cancer

Dr Francesco Boccellato is investigating the mechanisms of tissue regulation in the healthy stomach and in a 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
An animation showing a dial with green, amber and red risk levels for myeloma

New clinical prediction tools for myeloma

Dr Constantinos Koshiaris has developed clinical prediction models for use in primary care with the aim of accelerating myeloma diagnoses.
Doctor looking at skin

Higher testosterone levels in men linked to greater melanoma risk

New research from Dr Eleanor Watts at the Nuffield Department of Population Health has found this association for the first time

Novel imaging device enters first round of development funding programme

Anna Vella is designing CAPULET: a device to increase the accuracy in delivering particle beam radiotherapy in cancer treatment