Researchers at RMIT University in Melbourne, Australia, created an AI system that can identify prostate cancer during routine CT scans. It is typically difficult to spot prostate cancer in CT images, and the radiation makes CT unsuitable as a screening modality. However, if men are undergoing abdominal or pelvic scans for other reasons, this latest system can help spot prostate cancer and let clinicians initiate early treatment. Prostate cancer remains a significant cause of cancer mortality in men. In Australia, where this technology was developed, prostate cancer is responsible for approximately 12% of male cancer deaths. While prostate cancers typically grow fairly slowly, they often go unnoticed for years, which is unfortunate as early treatment is a significant factor in positive outcomes. While men over a certain age are encouraged to undergo routine prostate exams with their doctor, many skip such visits, leading to undiagnosed cancer that can grow unchecked for years. While nothing can replace a prostate exam with a clinician, incidental discovery of prostate cancer could significantly help many men that would otherwise be oblivious to the reality within. The Aussie researchers trained their AI software to identify prostate cancer in CT scans using a dataset of scans of asymptomatic men with and without prostate cancer. Identifying prostate cancer in a CT scan is typically tricky, even for highly trained human observers, but the AI system handled it well. “We’ve trained our software to see what the human eye can’t, with the aim of spotting prostate cancer through incidental detection,” said Ruwan Tennakoon , a researcher involved in the study. “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.” So far, the system has been able to rapidly identify subtle signs of cancerous growth, and outperformed radiologists who viewed the same images. “Australia doesn’t have a screening program for prostate cancer but armed with this technology, we hope to catch cases early in patients who are scanned for other reasons,” said Mark Page, another researcher involved in the study. “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.” Source
