By continuing to browse our site you agree to our use of cookies, revised Privacy Policy and Terms of Use. You can change your cookie settings through your browser.
CHOOSE YOUR LANGUAGE
CHOOSE YOUR LANGUAGE
互联网新闻信息许可证10120180008
Disinformation report hotline: 010-85061466
Artificial intelligence can now speed up tumor surgeries, cutting down on operating times. That's the conclusion of a team of Austrian and American scientists who have developed the AI tool FastGlioma, which recognizes cancer cells within 10 seconds.
Normally, tumor surgeries are lengthy. Pathologists carefully check every piece of extracted tissue for cancer cells... taking around 30 minutes for each sample.
The increasing duration of brain surgery also increases the risk of complications for patients. It is therefore crucial to arrive at reliable assessments more quickly or as promptly as possible.
In Vienna, the waiting time in the operating room (OR) is now much shorter.
"I take the sample directly in the OR and use our AI tool to get a diagnosis within some seconds," neurosurgeon Barbara Kiesel told CGTN at Vienna General Hospital. FastGlioma analyses the tissue in real time - during the surgery.
"I'm sure that this technique will be widely used in the next years - in several medical disciplines and also several hospitals worldwide," says Georg Widhalm, who runs the Vienna team of the international FastGlioma project together with neurosurgeon colleague Lisa Körner.
The results are promising: the machine was able to detect the spread of tumors with 92 percent accuracy.
Determining where a tumor ends and healthy tissue begins is particularly important in the brain. If too much is removed, this can impair central processes such as the ability to speak or move – but if cancer cells remain, this increases the likelihood of the disease returning early with a correspondingly reduced survival rate.
FastGlioma is a refined version of a previous AI tool. By training the new software with around four million images, collaborating scientists in Austria, Michigan, California and New York further reduced the machine's processing time.
"We expect this to improve the prognosis of brain tumor patients in the future," say the Viennese co-developers. The new findings show the great potential that AI has in the care of cancer patients as a whole, the researchers wrote in the journal Nature.
Given the world's growing and aging population, hospitals are starting to rely on AI and surgical robots to deal with the rising caseload. The prediction: once AI is perfected and built into platforms, most surgeries will be entirely performed by machines.
In the United Kingdom, for instance, the number of robot-assisted surgeries grew more than fivefold in the past decade.
"I think the combination of robotics with AI would also increase the precision of procedures and the safety," Widhalm told CGTN. "So I think that's really a great combination."
Now that the FastGlioma study is completed, the Viennese research team is waiting for EU approval to introduce their newest AI tool as standard operating procedure.