European researchers developed AI robot for colonoscopies of the large intestine but could be applied to other tests such as pancreatic endoscopy, gastroscopy and bronchoscopy.
The scientists, from the British University of Leeds, who published the paper in the journal Nature Machine Intelligence, said that by simplifying colonoscopies, robotic systems can increase the frequency of these tests in the future, which will facilitate early detection of the colon.
Today around 19 million colonoscopies are carried out each year in Europe and the USA, a figure that is expected to increase by 16% over the next decade. Both the diagnosis and prevention of colorectal cancer – the third most common form of cancer in the world – depend to a decisive extent on colonoscopies.
How the new robot works for colonoscopies
Traditional colonoscopies are relatively expensive, can become painful and require specialized operators of the semi-flexible endoscope, which is inserted from the anus. More recently, new techniques have been developed that make use of magnetic endoscopes, which are guided by a magnet outside the body, which in turn can be precisely controlled by a robotic arm, which allows complex movements within the body to be performed. However, this method is complex and also requires a great deal of expertise from the operator of the robotic arm and magnet.
- Robot against coronavirus in Singapore shopping mall
- Greek company brings first disinfection robot to market
- Gold medal for Greek Plaisiobots Team at the robotics competition
The new semi-automatic robotic system depends on simple initial motion commands given by the operator. Then, the robotic endoscope featuring a camera with computational vision on its edge, artificial intelligence (machine learning) and image analysis algorithms moves itself through the gut with the help of a magnet outside the body. Testing of the “smart” system in artificial intestines and experimental animals (pigs) has shown that it is 100% reliable and more manageable than today’s conventional colonoscopy.
Although a doctor should have the supervision of robotic colonoscopy to make the necessary clinical decisions on a case-by-case basis during the diagnostic examination, the manipulation of the endoscope is left to the robot. Testing of the system on five healthy volunteers is expected to begin by the end of 2021. If successful, at a later stage the system will be tested in patients with inflammatory bowel disease.