Odin Vision

Background to the study

In the UK, there are 42,000 new cases of colorectal cancer (CRC) and 16,000 deaths each year making it the second leading cause of cancer deaths. Cases of CRC related deaths are forecast to increase by 51% by 2035.This is caused by an aging population and an increase in the number of younger people getting the disease. A 2017 study showed that adults born in the 1990’s are 4 times more likely to get rectal cancer and twice as likely to get colon cancer compared to adults born in the 1950s.

Colonoscopy is an important procedure for finding and removing pre-cancerous/cancerous polyps (abnormal tissue growths). However, colonoscopy is not always effective. Studies have shown that doctor/nurse miss up to 25% of polyps. Higher miss rates lead to increased likelihood of cancer.

Polyps that are found, are removed and sent away to be tested for cancer. This adds on average 3 weeks to patient waiting times, it is inefficient and causes the patient anxiety.

Odin Medical has developed a Computer Assisted Detection and Diagnosis system for colonoscopy. The system acts like a second pair of eyes during the procedure using artificial intelligence (AI) to find/analyse polyps in colonoscopy images. This technology can support doctors to find more polyps and make instant diagnosis leading to better early detection of cancer.   It sends the colonoscopy image from the hospital to a secure cloud/super-computer where they are analysed. The analysis is instantly sent back to the hospital where the doctor can use it to support clinical decision. This makes it cost effective and accessible for all hospitals, small and large. In principal: a comprehensive service, available to all.

How will this study be conducted?

The aim of this project is to demonstrate the benefits of using AI in colonoscopy through a multi-centre randomised controlled trial. These benefits include, better better patient outcomes by improving polyp/cancer detection rates, improved patient experience with instant diagnosis and increased operational efficiency. The project will gather clinical data and perform health economic analyses.

The project has three phases: 1) pre-trial, set up the trial and develop software to collect data 2) trial, perform procedures, collect data and review performance and 3) post-trial, analyse the clinical evidence and build the healthcare economic case for cost savings.

How you can be involved in the Odin project?

A public and patient group has been involved throughout the technical development of the AI system and will continue to be involved.

Read more about the Odin project

Watch Odin on BBC Breakfast

If you’re interested in finding out more about being involved at the co-design stage email sam@bowelresearchuk.org

Read more about our People and Research Together programme.