AI Tool Improves Prostate Cancer Treatment Outcomes by Accurately Measuring Tumor Size, UCLA Study Finds
Published by the University of California – Los Angeles Health Sciences on March 18, 2025, a study led by UCLA investigators shows that artificial intelligence (AI) could play a key role in improving treatment outcomes for men with prostate cancer. The research highlights the potential of AI to assist physicians in determining which patients are most likely to benefit from partial gland cryoablation, a minimally invasive procedure that targets localized prostate tumors.
Researchers assessed an AI tool called Unfold AI, developed by UCLA researchers in collaboration with Avenda Health. The study, published in BJUI Compass, found that Unfold AI precisely estimates prostate tumor volume, thus aiding in the identification of patients with a higher probability of successful treatment. The study suggests that using AI to measure tumor size could reduce treatment failures by over 70%.
“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,” said Dr. Wayne Brisbane, assistant professor of urology at the David Geffen School of Medicine at UCLA, and first author of the study.
Partial Gland Cryoablation: A Targeted Approach
Partial gland cryoablation is a procedure that freezes and destroys only the cancerous portion of the prostate, in contrast to removing or treating the entire gland. This approach minimizes damage to critical areas, leading to fewer side effects than traditional surgery or radiation, potentially offering patients a better quality of life. MRI is used to accurately locate the tumor and guide the treatment, using imaging to monitor treatment progress. Unfortunately, current methods can underestimate tumor size and miss smaller cancerous areas, leading to incomplete treatment and possible cancer recurrence.
Unfold AI: A Promising Advancement
Unfold AI addresses this challenge by analyzing data from MRI scans and biopsies to create a detailed, three-dimensional map of the prostate tumor. This enhanced visualization helps doctors more accurately assess the true size and boundaries of the cancer.
To evaluate the software’s accuracy, the team enrolled 204 men with localized prostate cancer who underwent partial gland cryoablation in a clinical trial at UCLA between 2017 and 2022. All participants received MRI-guided biopsies, and follow-up biopsies were performed at 6 and 18 months post-treatment to monitor for cancer recurrence. The doctors used Unfold AI during the trial to generate 3D maps of each tumor, estimating its actual volume. Tumor volume was then compared to other indicators such as tumor grade and PSA levels to predict treatment outcomes.
Key Findings
The study revealed that tumor volume was the strongest predictor of treatment success, while tumor grade did not correlate with successful outcomes. Patients with tumors smaller than 1.5 cubic centimeters showed significantly better results after cryotherapy, and this group was less likely to require further treatment or develop metastases. According to the study, employing this tumor volume threshold as part of the eligibility criteria would have prevented 72% of treatment failures.
“With Unfold AI, doctors now have a method to determine the volume of cancer within a prostate tumor,” said Dr. Leonard Marks, professor and deKernion Endowed Chair in Urology at the David Geffen School of Medicine at UCLA, and senior author of the study. “Such a method has not been previously available.”
Future Directions
While the findings are promising, the researchers emphasize the need for larger, multi-center trials to validate these results.
“The study marks an important advance in integrating AI into prostate cancer treatment decision-making, offering the potential for more personalized prostate cancer care,” said Brisbane.
The collaborative research at UCLA and the UCLA-backed startup Avenda Health that led to the development of Unfold AI was supported by grants from the National Institutes of Health.
Other contributors to the study encompass Alan Priester, Anissa Nguyen, Mark Topoozian, Merdie Delfin, Samantha Gonzalez, Kyla Grunden, Shannon Richardson and Shyan Natarajan from UCLA and Sakina Mota from Avenda Health. Professor Marks and Natarajan are cofounders of Avenda Health.
Source
University of California – Los Angeles Health Sciences
Journal Reference
Brisbane, W. G., et al. (2024). Focal therapy of prostate cancer: Use of artificial intelligence to define tumour volume and predict treatment outcomes. BJUI Compass. doi.org/10.1002/bco2.456.
