The most accurate prostate progression prediction technology to date has been developed by researchers from the Icahn School of Medicine at Mount Sinai and the Keck School of Medicine at the University of Southern California.
Existing methods of prostate cancer detection include multiparametric magnetic resonance imaging (MRI) and the Prostate Imaging Reporting and Data System Version 2, a five-point scoring scale that categorizes tumors found on the multiparametric MRI. Because they are subjective, both of these methods are not always accurate. Furthermore, they do not differentiate between moderate and malignant stages of prostate cancer, leading to discrepancies in management between various oncologists.
The new technology uses machine learning in conjunction with radiomics, a field of study involving use of data-characterization algorithms to extract large amounts of quantifiable features, such as texture, size, and shape, from medical images. Together, these methods are sensitive enough to accurately categorize prostate tumors and predict prostate cancer prognosis.
"By rigorously and systemically 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," remarked Gaurav Pandey, PhD, Assistant Professor of Genetics and Genomic Sciences at the Icahn School of Medicine at Mount Sinai and senior corresponding author of the study. "This pathway to predicting prostate cancer progression with high accuracy is ever improving, and we believe our objective framework is a much-needed advancement."
This new technology will be used in the future to more accurately predict progression of prostate cancer and allow clinicians to precisely establish patients' prognosis, thereby determining the most effective treatment for their patients.
For More Information
Varghese B, Chen F, Hwang D, et al (2019). Objective risk stratification of prostate cancer using machine learning and radiomics applied to multiparametric magnetic resonance images. Sci Rep, 9:1570. DOI:10.1038/s41598-018-38381-x
Image courtesy of Homieg340