It does so with nearly the same level of accuracy as experienced radiologists, said researchers at the University of California, Los Angeles (UCLA) in the US.
In tests, FocalNet was 80.5 per cent accurate in reading MRIs, while radiologists with at least 10 years of experience were 83.9 percent accurate, according to the study published in the journal IEEE Transactions on Medical Imaging.
Radiologists use MRI to detect and assess the aggressiveness of malignant prostate tumours.
However, it typically takes practicing on thousands of scans to learn how to accurately determine whether a tumour is cancerous or benign and to accurately estimate the grade of the cancer.
In addition, many hospitals do not have the resources to implement the highly specialised training required for detecting cancer from MRIs.
FocalNet is an artificial neural network that uses an algorithm that comprises more than a million trainable variables.
The team trained the system by having it analyse MRI scans of 417 men with prostate cancer.
Scans were fed into the system so that it could learn to assess and classify tumours in a consistent way and have it compare the results to the actual pathology specimen.
Researchers compared the AI system’s results with readings by radiologists who had more than 10 years of experience.
The research suggests that an AI system could save time and potentially provide diagnostic guidance to less-experienced radiologists.