We are searching data for your request:
Upon completion, a link will appear to access the found materials.
Artificial intelligence significantly improves colorectal cancer screening
Colon cancer is the second most common diagnosis of all cancers in Germany and the second most common cause of death. Timely detection can significantly improve the chances of recovery from this type of cancer or even prevent this disease. Artificial intelligence (AI) can also help.
According to experts, colonoscopy (colonoscopy) is the most important and meaningful examination for the early detection and diagnosis of colorectal cancer. This method can be significantly enhanced by artificial intelligence. According to a message, an AI-based system at Freiburg University Hospital detects up to ten percent more colon cancer precursors during colonoscopy.
Improved chances of recovery through timely detection
According to the Federal Ministry of Health, more than 60,000 people develop colon cancer every year. "Timely detection can significantly improve the chances of recovery from colorectal cancer or even prevent this disease," says the ministry's website.
As explained on the "ONKO Internet portal" of the German Cancer Society, it is assumed that 90 percent of all colon cancer patients can be cured if diagnosed early.
In addition to the tactile examination and the stool test, the intestinal level contributes to the clarification.
Discover more precancerous stages with artificial intelligence
Endoscopy specialists from the University Hospital of Freiburg are now relying on artificial intelligence (AI) to reliably detect even more and smaller precancerous stages in a colonoscopy. The system analyzes the live video images during colonoscopy and marks suspicious spots on the monitor with a green rectangle.
Studies show that doctors find about ten percent more precancerous stages than without AI support. At the University Clinic in Freiburg, all preventive colonoscopies have been carried out using the new system since the beginning of the year. According to the information, more than 50 people have already been successfully examined.
PD Dr. Arthur Schmidt, head of interdisciplinary endoscopy at the Clinic for Internal Medicine II at the Freiburg University Medical Center, explained that with the support of artificial intelligence, patients can be offered even greater safety in colorectal cancer prevention.
The system can also help very experienced medical professionals to more reliably identify abnormal tissue structures. "This enables us to detect and remove very small preliminary stages even more reliably," explained Schmidt.
The final judgment and decision lies with the person
As explained in the communication, the system was trained on the basis of several thousand pictures of suspected cancer precursors using the so-called deep learning procedure. The software developed its own search patterns with which the success rate for recognizing these tissues was particularly high.
Because the optical markings are superimposed on the colonoscopic image immediately during the examination, there is no training period for the doctors.
“While the human eye always focuses on one point in the image, the AI always has the entire image in view. Ultimately, of course, we humans judge and decide whether something needs to be removed, ”says Schmidt.
One of the most effective cancer screening tools ever
The University Medical Center Freiburg points out that colonoscopy is paid every ten years by health insurance companies from the age of 55.
For people with an increased risk of illness, for example with cases of colon cancer in the family, an earlier examination may also be useful.
Colonoscopy examines the condition of the colon. For this purpose, a special endoscope is introduced, which delivers a moving and illuminated image from inside the body.
If suspicious tissue is detected, it can be cut directly with a wire loop and sent to the laboratory for further investigation. (ad)
Author and source information
This text corresponds to the specifications of the medical literature, medical guidelines and current studies and has been checked by medical doctors.