New diagnostic tool spots prostate cancer before symptoms show
Scientists at RMIT University and St Vincent’s Hospital in Melbourne, Australia, have developed an artificial intelligence (AI) programme for the early detection of prostate cancer. The programme analyses computerised tomography (CT) for tell-tale signs of the disease, and even outperforms trained radiologists to detect cancerous growths in seconds.
“We’ve trained our software to see what the human eye can’t, with the aim of spotting prostate cancer through incidental detection,” said Dr. Ruwan Tennakoon, from RMIT. “It’s like training a sniffer dog – we can teach the AI to see things that we can’t with our own eyes, in the same way a dog can smell things human noses can’t.”
Read also: Prostate cancer drug more effective with low-fat breakfast
Although CT imaging is not suitable for regular or direct cancer screening because of the high radiation doses involved, the trained AI software could be run at the same time as an abdomen or pelvis CT cancer screening to check for other issues. It simply looked for features of the disease in a variety of scans and performed better than radiologists who viewed the same images, detecting cancerous growths much quicker. The AI additionally learnt to read images from different machines to spot even the smallest irregularities.
The scientists are therefore hopeful that the technology would be adapted to a variety of diagnostic equipment, such as MRI machines.
Prostate cancer is the leading cause of death by cancer in Australian men – responsible for an estimated 12% of male cancer deaths in 2020. Prostate cancer may be slow-growing but early diagnosis is key to successful treatment. Most men unfortunately avoid diagnosis tests until it is too late.
“Australia doesn’t have a [dedicated] screening program for prostate cancer but armed with this technology, we hope to catch cases early in patients who are scanned for other reasons,” explained Dr. Mark Page, Head of CT in Diagnostic Imaging at St Vincent’s Hospital.
“For example, emergency patients who have CT scans could be simultaneously screened for prostate cancer. If we can detect it earlier and refer them to specialist care faster, this could make a significant difference to their prognosis.”
Category: Features, Technology & Devices
