Home » Health » New technique to better diagnose prostate cancer

New technique to better diagnose prostate cancer

A team of Montreal researchers has developed a new and better way to detect prostate cancer, by combining two existing techniques.

The scientific team at the Research Center of the Center hospitalier de l’Université de Montréal (CRCHUM) and Polytechnique Montréal first used Raman microspectroscopy imaging, a method of observing and characterizing molecular composition. This technique “uses light rays to make the molecules of a sample vibrate and collect information on the chemical bonds that compose it”, we read in a press release presenting the ins and outs of the study.

Then machine learning, a facet of artificial intelligence that uses algorithms to analyze data and draw conclusions, comes into play. The Raman spectra obtained in the first step are then used “to train algorithms to automatically recognize and classify specific signatures of healthy tissue, intracanal carcinoma of the prostate and other forms of prostate cancer ”.

“These predictive models were then tested on data from the other two hospitals,” it says. With promising results to say the least: they correctly detect the presence or absence of intracanal carcinoma of the prostate in nearly 9 out of 10 cases. ”

Currently, in hospitals, to identify for example intracanal carcinoma of the prostate, an aggressive variant of prostate cancer diagnosed in 20% of patients who die of prostate cancer each year, pathologists rely on a simple visual observation of the tissues removed, for lack of anything better.

The Dre Dominique Trudel and Frédéric Leblond, researchers at the CRCHUM, as well as the postdoctoral researcher Andrée-Anne Grosset, therefore believe that they have found “a tool of the future”, that is “a way of improving the identification of patients at risk and the diagnosis of the most aggressive forms of this cancer ”.

Their study has just been published in the specialized journal PLOS Medicine.

For the purpose of this study, tissue samples from 483 patients (median age 62) from the Center hospitalier de l’Université de Montréal, the Center universitaire de Québec and the University Health Network in Toronto were analyzed.

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.