Bowel cancer breakthrough as AI software used to spot tumours

Trials found that computer programmes were able to distinguish potentially dangerous tumours from harmless growths with high levels of accuracy. Photo / AP file

Artificial intelligence could detect cancer in less than a second, new research suggests.

Trials found that computer programs were able to distinguish potentially dangerous tumours from harmless growths with high levels of accuracy.

The research involved bowel cancer - the fourth most common form of the disease in the UK, with more than 40,000 diagnoses annually.

In a trial, the AI system was able to distinguish tumours from endoscopy images with a 94 per cent accuracy.

Scientists used the software to assess 306 colorectal polyps - growths in the bowel which may or may not be cancerous - in 250 men and women. It took less than a second for the system to analyse each magnified endoscopic image and decide whether or not the polyp was malignant.

The program worked by matching each growth against more than 30,000 images that were used for machine learning.

British experts said the findings from Showa University in Yokohama, Japan, presented at United European Gastroenterology (UEG) Week in Barcelona, were encouraging.

Cautioning that the system has yet to obtain regulatory approval, they said the technology could spare many patients from needless surgery, if further trials succeed.

Dr Claire Knight, from Cancer Research UK, said: "AI and virtual reality are opening up many exciting areas of exploration to increase our understanding and treatment of cancer. The technology in this presentation could help reduce the overtreatment of bowel growths, called polyps, by helping doctors decide if they need removing or can be left alone. But it will need testing in much larger groups... first before we understand its potential."

Judith Brodie, interim chief executive at Beating Bowel Cancer, said: "The results of the study are encouraging. We welcome any development that speeds and supports early diagnosis of bowel cancer and we hope that the potential of AI in this context will be investigated further on the basis of these results."

Dr Yuichi Mori, the study's leader, said: "The most remarkable breakthrough with this system is that artificial intelligence enables real-time optical biopsy of colorectal polyps during colonoscopy, regardless of the endoscopists' skill. We believe these results are acceptable for clinical application and our immediate goal is to obtain regulatory approval for the diagnostic system."