Radboud university medical center sees promising results with the use of artificial intelligence (AI) during colonoscopy, a visual examination of the large intestine using an endoscope. The technology results in forty percent more detected polyps, which are structures that can eventually develop into cancer.
This is evident from a publication by the Radboud university medical center in The Lancet Digital Health. More than 100,000 Dutch people have a colonoscopy every year, also called a colonoscopy. A doctor uses a camera to look inside the intestine and looks for colon cancer and polyps. Polyps are bulges in the intestinal wall and can be a precursor to colon cancer.
More polyps removed leads to a lower risk of colon cancer
Previous research has already shown that the more polyps the doctor finds and removes during a colonoscopy, the smaller the chance that someone will develop colon cancer later. The research results that Radboud University Medical Center is now presenting show that AI can provide great added value in this regard. The technology appears to increase the number of detected polyps by 40%. This therefore has a direct impact on the chance that someone will develop colon cancer later.
A total of almost 1,000 patients participated in the Radboud University Medical Center research. It has been performed in ten hospitals in various countries. Participants in the study were all eligible for colon cancer screening or had previously had polyps. The patients are divided into two groups. One group received a standard colonoscopy, while the AI watched live in the second group.
Purple square attracts attention
The AI places a purple square on the screen at each suspicious location. The square is intended to attract the attention of the doctor, who then takes a closer look at the suspicious image. The method led to 40% more detected polyps.
Medical researcher Michiel Maas speaks of enormous added value. “A doctor can miss polyps because they are in the picture for too short a time, or because their attention is focused on another spot,” says Maas. “But a computer looks at every pixel in the image and is equally alert every millisecond. That provides enormous added value.”
Research does not take more time
The researchers point out that although the number of polyps detected and removed is higher, colonoscopy does not take more time in practice due to the use of AI.
The number of false positives has also not increased. Examination of the removed tissue shows that the extra removed polyps are just as often of a dangerous type as the excised polyps during a standard colonoscopy.
Developed by Magentiq Eye
The AI used by the researchers at Radboud university medical center was developed by the company Magentiq Eye from Israel. This company has been active since 2014. It focuses on the development of AI for AI-assisted colonoscopy, in which a doctor examines the lining of the colon.
Magentiq Eye’s system – MAGENTIQ-COLO – is compatible with commonly used endoscopy systems, including those from Olympus, Fujinon, Pentax and Sonoscape. The system uses a digital video signal from the endoscopy system and applies a deep learning algorithm to it in real time. The AI searches the images for abnormalities that could indicate a polyp.
Magentiq Eye brings these suspicious images to the doctor’s attention. If desired, this can be displayed on the main screen of the system, but also on a separate screen. It not only shows the suspicious location, but also shows, among other things, an estimate of the size and characteristics of the polyp in the image. During the examination, the system provides additional information to the doctor, who can use it for his analysis. At the end of the procedure, the recorded video with or without suspicious spots marked can be exported and saved. Finally, MAGENTIQ-COLO automatically draws up a report on the findings.
Deployment still limited
MAGENTIQ-COLO is commercially available, but is only used to a limited extent. Maas: “This system costs money, and the reimbursement of medical research with the help of AI is still in the development phase.”
Follow-up studies are planned. The researchers want to demonstrate, among other things, to what extent MAGENTIQ-COLO is able to determine whether a polyp is dangerous based on external characteristics and size. Professor and gastroenterologist Peter Siersema: “If we can determine this during the examination, we can leave innocent polyps in place. So you don’t have to have it analyzed at Pathology. Ultimately, this reduces the risk of complications and costs.”
Author: Wouter Hoeffnagel
Beeld: Julio César Velásquez Mejía via Pixabay
2024-02-26 03:24:08
#Radboud #university #medical #center #detects #polyps #colonoscopy #Manufacturing #Industry #News