Researchers have developed a diagnostic tool that can diagnose prostate cancer before patients have any symptoms. All of this is possible by using artificial intelligence to analyze CT scans in seconds.
We all get sick from time to time. But in general, it is better to prevent it in the first place or catch it early to increase the chances of the disease coming back with relatively fewer problems. In men, this could be prostate cancer, which requires regular checkups to see if anything is wrong.
Diagnosis of Prostate cancer is the most common and the leading cause of cancer death in men in Australia.
An artificial intelligence (AI) program developed at RMIT University can now detect disease early. It’s allowing to be detecting incidentally through routine computed tomography (CT) imaging. The technology, developed in collaboration with doctors at St. Hospital. Vincent in Melbourne analyzed CT scans for signs of prostate cancer, which even a trained human eye can treat. CT scans are not suitable for regular cancer screening due to high doses of radiation. But AI solutions can be used for cancer screening when men examine the abdomen or pelvis for other problems.
Researchers at RMIT University and St. Vincent’s Hospital in Melbourne, Australia have developed an AI that they claim can detect prostate cancer in patients before symptoms appear. This is done via CT scans, which are not normally used to screen for cancer due to the high levels of radiation, but the researchers trained their AI to look for clues in these scans.
To detect signs of prostate cancer, the researchers looked at various scans of asymptomatic patients with and without cancer. They then teach the AI how to look for diseases based on these scans and where to look, meaning no scans are needed. Over time, AI improves its accuracy with each scan, where it is able to detect even the smallest deviations.
One of the researchers, drug. Ruwan Tennakoon, said: “We trained our software to see what the human eye cannot see to detect prostate cancer by chance. It’s like training bloodhounds – we can teach AI to see things we can’t see with our own eyes, just as dogs can smell things that human noses can’t. “