Researchers have discovered a novel machine-learning framework that distinguishes between low and high-risk prostate cancer with more precision than ever before.
The framework is intended to help physicians in particular, and radiologists to more accurately identify treatment options for prostate cancer patients, thereby lessening the chance of unnecessary clinical intervention.
The team of researchers from Icahn School of Medicine at Mount Sinai and Keck School of Medicine, University of Southern California (USC) who made the discovery stated in their report that prostate cancer was one of the leading causes of cancer deaths, second only to lung cancer.
While recent advances in prostate cancer research have saved many lives, objective prediction tools have, until now, remained an unmet need.
Presently, the standard methods used to assess prostate cancer risk are multiparametric magnetic resonance imaging (mpMRI), which detects prostate lesions, and the Prostate Imaging Reporting and Data System, version 2 (PI-RADS v2), a five-point scoring system that classifies lesions found on the mpMRI.
Together, these tools are intended to soundly predict the likelihood of clinically significant prostate cancer. However, PI-RADS v2 scoring is subjective and does not distinguish clearly between intermediate and malignant cancer levels (scores 3, 4, and 5), often leading to differing interpretations among clinicians.
Assistant Professor of Genetics and Genomic Sciences at the School, Gaurav Pandey, said by rigorously and systematically combining machine learning with radiomics, their goal is to provide radiologists and clinical personnel with a sound prediction tool that can eventually translate to more effective and personalised patient care.
The senior corresponding author of the publication, Bino Varghese, also said the pathway to predicting prostate cancer progression with high accuracy is ever improving, and they believed their objective framework is a much-needed advancement.