fbpx

AI (Artificial Intelligence) Based Prediction Tool for Prostate Cancer Shows Unmatched Accuracy

The current system for assessing prostate cancer risk is based on 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 classification of lesions found on the mpMRI.  While it has helped in standardizing and considerably streamlining the process, the subjective [...]

The current system for assessing prostate cancer risk is based on 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 classification of lesions found on the mpMRI.  While it has helped in standardizing and considerably streamlining the process, the subjective grading does not distinguish clearly between intermediate and malignant cancer levels (scores 3, 4, and 5), often resulting in differences in interpretation among specialists.

Now, a team of researchers from the Icahn School of Medicine at Mount Sinai and Keck School of Medicine at the University of Southern California (USC) has developed a novel machine-learning framework that analyzes cases with more precision than ever before.

By rigorously and systematically combining machine learning with radiomics, our goal is to provide radiologists and clinical personnel with a sound prediction tool that can eventually translate to more effective and personalized patient care”, explained Gaurav Pandey, Ph.D., Assistant Professor of Genetics and Genomic Sciences.

The project combines AI and radiomics, a medical study field that uses algorithms to extract large amounts of quantitative characteristics from medical images.  These in fact contain latent information regarding tumor behavior that can go unnoticed to human examination.  This predictive framework can rigorously and systematically assess different identifying methods and select the best-performing one.  The approach allows doctors to classify patients’ prostate cancer with high sensitivity and an even higher predictive value.

At the moment, prostate cancer is one of the most common forms of malignancy and the American Cancer Institute estimates about 174,000 new cases each year.  To put that into perspective, during their lifetime, about 1 in 9 men will be diagnosed with this disease. With early detection and better classification, doctors can offer improved targeted treatments that have a higher chance of success.

The pathway to predicting prostate cancer progression with high accuracy is ever improving, and we believe our objective framework is a much-needed advancement”, noted Dr.  Pandey.

HOPE RISES With Us!

Receive your FREE eBook on 'Latest Cancer Research Articles' over email TODAY!
We would like to send you cancer relevant emails occasionally! Thanks