Prostate cancer is the second most common cancer in American men, after skin cancer, according to the American Cancer Society. And although medical advances have improved prostate cancer diagnosis and treatment, distinguishing between low- and high-risk disease has remained a challenge.
In an attempt to remedy this problem, researchers at Mount Sinai in New York City and the University of Southern California in Los Angeles have been working on a tool that can identify low- and high-risk prostate cancer more accurately. The tool combines machine learning and radiomics, which uses algorithms to extract data from medical images.
Standard methods to assess prostate cancer risk include a sophisticated type of magnetic resonance imaging (MRI), which detects prostate lesions, and the prostate imaging reporting and data system, a scoring system used to classify the lesions. But the scoring system can be interpreted differently by different radiologists and doesn’t distinguish between intermediate and malignant cancer levels, which can lead to unclear results.
The LA and New York researchers suggests in their analysis of the study, published in Scientific Reports, that researchers could use this tool to classify prostate cancer with higher sensitivity and a greater predictive value.
Sourced from: Scientific Reports