New Delhi: A you have a model Developed to detect prostate cancer found that their performance was “no different from that of the experienced.” radiologistA team, including researchers from the Mayo Clinic in Minnesota, US, said that as a “potential assistant” to a radiologist, the model could help improve diagnosis from magnetic resonance imaging (MRI) scans through increased detection with fewer false positives.
For the clinical diagnosis of prostate cancer, radiologists often use multiparametric magnetic resonance imagingwhich produces a more detailed image of the prostate gland than a standard one.
Results are expressed as a PI-RADS (Prostate Imaging Reporting and Data System) score, where a higher score means a greater chance of clinically significant cancer Be present.
However, grading tissue lesions or abnormalities using the PI-RADS score has limitations, the study authors said.
“Prostate MRI interpretation is difficult. More experienced radiologists tend to have better diagnostic performance,” said Naoki Takahashi of the Department of Radiology at Mayo Clinic and senior author of the study published in the journal Radiology.
To develop the model, the researchers trained a convolutional neural network (CNN), a type of artificial intelligence (AI) used primarily for image recognition and processing, to predict clinically significant prostate cancer from a multiparametric MRI scan.
The performance of the model was compared to that of abdominal radiologists in a group of patients who had undergone MRI but without known clinically significant prostate cancer.
“In a retrospective study of 5,215 patients (5,735 examinations) who underwent multiparametric MRI for prostate cancer evaluation, the performance of the (AI-based) model in detecting clinically significant prostate cancer was no different from that of experienced radiologists,” the authors wrote.
They said the model could be used as an adjunct to radiologists to improve prostate cancer detection.
“I don’t think we can use this model as a stand-alone diagnostic tool. Instead, the model’s prediction can be used as an adjunct to our decision-making process,” Takahashi said.
A Lancet commission on prostate cancer projected that between 2020 and 2040, cases worldwide could more than double and deaths could rise by 85 percent. Low- and middle-income countries are expected to bear most of the burden of the increase, it said.
The commission called for evidence-based interventions, including early detection and diagnosis, to help save lives and prevent health problems resulting from prostate cancer in the years to come.
