Artificial intelligence might be able to help doctors detect the prostate cancers most likely to be life-threatening to men, a new study suggests.

An AI program successfully identified and outlined 85% of the most aggressive prostate tumors seen on MRI scans of more than 700 patients, researchers said.

The larger tumors found by the AI were more likely to withstand cancer treatment and spread to other parts of the body, researchers found.

And for patients treated with radiation, the AI-assessed tumor size predicted the risk of cancer spread better than traditional risk calculations, results showed.

“Al-determined tumor volume has the potential to advance precision medicine for patients with prostate cancer by improving our ability to understand the aggressiveness of a patient’s cancer and therefore recommend the most optimal treatment,”  said lead researcher Dr. David Yang, a radiation oncologist with Brigham and Women’s Hospital in Boston.

For the study, researchers trained an AI model based on MRI images of prostate cancer tumors from 732 patients undergoing treatment.

The AI was able to locate and measure about 85% of very high-risk prostate tumors.

Size estimates generated by the AI also showed promise as a means of predicting a patient’s cancer progression, researchers said.

Larger tumors came with a higher risk that cancer would recur or spread to other parts of the body, both in patients treated surgically and with radiation.

“The AI measurement itself can tell us something additional in terms of patient outcomes,” said senior researcher Dr. Martin King, a radiation oncologist with Brigham and Women’s. “For patients, this can really tell them something about what are the chances of cure, and the likelihood that their cancer will reoccur or metastasize in the future.”

The AI also could help guide radiation oncologists, by pinpointing the tumor for more targeted treatment.

It also provided a much faster snapshot of predicting prostate cancer aggressiveness, researchers said. Current methods take two weeks or longer to judge how fast a cancer will grow or spread; with AI-informed testing, patients might be able to start treatment sooner.

However, researchers noted that the AI needs further testing.

“We want to validate our findings, using other institutions and patient cohorts with different disease characteristics, to make sure that this approach is generalizable to all patients,” Yang said in a hospital news release.

The new study was published Oct. 29 in the journal Radiology.

More information

The American Cancer Society has more about prostate cancer.

SOURCE: Mass General Brigham, news release, Oct. 29, 2024

Source: HealthDay