Scientists at Showa University in Yokohama, Japan see 94% accuracy from the AI system.
Cancer detection speeds could be improved to just a matter of seconds with the use of artificial intelligence, suggests new research from scientists in Japan.
Trials of computer programmes found that they were able to distinguish between harmless growths and potentially dangerous tumours quickly and with high levels of accuracy, at around 94% when looking at endoscopy images.
The AI system used assessed 306 colorectal polyps – growths in the bowel – in the hope of identifying whether they are cancerous or not. The tests with 250 men and women found that the AI system took less than a second to analyse each magnified image and to decide whether it was malignant or not.
Dr Claire Knight, from Cancer Research UK, told The Telegraph: “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 over-treatment 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 of people first before we understand it’s potential.”
Working by matching each growth against a database of over 30,000 images, as part of the machine learning process, the results from the scientists at Showa University in Yokohama, Japan, have been seen as positive but there have been cautions that the system has not received regulatory approval.
Study leader Dr Yuichi Mori 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.
“This allows the complete resection of adenomatous (cancerous) polyps and prevents unnecessary polypectomy (removal) of non-neoplastic polyps.
“We believe these results are acceptable for clinical application and our immediate goal is to obtain regulatory approval for the diagnostic system.”
Bowel cancer is the fourth most common in the UK, and breakthroughs could help to reduce the number of surgeries required for the more than 40,000 that are diagnosed with it annually.
The trial highlights the growing hope that technology can be used throughout the healthcare sector to not only digitise records, but to improve patient care, processes, and improve detection and treatment of diseases such as cancer.
Research from OpenText found that UK consumers are already seeing the advantages of the technology with 33% believing that a robot would reach a decision on their condition much faster, in addition to 25% believing an AI system would be more accurate in its diagnosis.
Mark Barrenechea, CEO at OpenText, said: “Thanks to parallel processing, big data, cloud technology, and advanced algorithms, Artificial Intelligence (AI) and machine learning are becoming more powerful. The Digital Revolution will drive an increasing reliance on self-service technology, machine to machine (M2M) communication and AI, and there is no denying that every job in every industry will be impacted. The opportunity for innovation and change is limitless.”