A new UCLA study has found that artificial intelligence could help doctors identify prostate cancer patients most likely to benefit from targeted treatment that removes cancer while sparing healthy tissue, according to a UCLA-led study published Tuesday.
Researchers evaluated the new Unfold AI software that uses data from MRIs and biopsies to generate a detailed 3D map of prostate tumors. The study found that the AI technology’s measurements of tumor size — compared with relying solely on tumor grade or prostate-specific antigen levels — significantly improved doctors’ predictions of successful treatment.
“By using AI to measure the size of a man’s prostate tumor more precisely, we can better predict who is likely to be cured with focal therapies like partial gland cryoablation,” Dr. Wayne Brisbane, assistant professor of urology at UCLA’s David Geffen School of Medicine, said in a statement.
The study tested whether Unfold AI’s tumor-volume mapping would aid doctors in predicting a patient’s likelihood for successful outcomes from a treatment called “partial gland cryoablation,” a minimally invasive procedure that freezes and eradicates only cancerous areas of the prostate instead of removing or irradiating the entire gland. The treatment minimizes damage to vital areas, which reduces side effects in an effort to maintain patients’ quality of life, researchers found.
Current methods of predicting treatment success — tumor grade and PSA levels — often underestimate tumor size can miss smaller cancerous areas, often leading to incomplete treatment and cancer recurrence.
“The study marks an important advance in integrating AI into prostate cancer treatment decision-making, offering the potential for more personalized prostate cancer care,” Brisbane said.
Although the findings are promising, researchers emphasized the need for broader trials to validate the results.
“Such a method has not been previously available,” Dr. Leonard Marks, professor and deKernion Endowed Chair in Urology UCLA’s medical school, said in a statement. “It’s important because tumor volume is a major determinant of treatment success or failure.”
Marks, who is also a member of the UCLA Health Jonsson Comprehensive Cancer Center and senior author of the study, added, “Using AI to predict tumor volume and shape gives a clearer picture and could help choose better candidates for focal cryotherapy.”
Unfold AI was developed by researchers at UCLA and Avenda Health.
The study was published in BJUI Compass, a peer-reviewed medical journal specializing in urology, and is available online at pmc.ncbi.nlm.nih.gov/articles/PMC11771490.
