A novel artificial intelligence (AI) tool, called Unfold AI, may help to determine which men with prostate cancer are most likely to benefit from partial gland cryoablation, according to a recent study published by Brisbane et al in BJUI Compass. The findings may play a key role in improving treatment outcomes.
Background
Partial gland cryoablation—a minimally invasive procedure designed to treat localized prostate tumors—freezes and destroys the cancerous part of the prostate rather than removing or treating the entire gland. The approach eliminates cancer cells while minimizing damage to vital areas, resulting in fewer side effects compared with surgery or radiation as well as offering patients a better quality of life. The technique involves using imaging guidance such as magnetic resonance imaging (MRI) to accurately locate the tumor and aid treatment. Real-time imaging during the procedure may help to monitor treatment progress and ensure the precise delivery of energy to the intended area.
However, current methods tend to underestimate the size of the tumor and may miss smaller cancers, which can lead to incomplete treatment and cancer recurrence. Unfold AI addresses this issue by analyzing data from MRI scans and biopsies to create a detailed, three-dimensional map of the prostate tumor. The technology may help physicians more accurately determine the true size and boundaries of prostate tumors.
Study Methods and Results
In this study, researchers evaluated the accuracy of the Unfold AI software among 204 men with localized prostate cancer who underwent partial gland cryoablation in a clinical trial between 2017 and 2022. All of the participants had MRI-guided biopsies at diagnosis as well as follow-up biopsies at 6 and 18 months after treatment to monitor for cancer recurrence. Physicians used Unfold AI to generate a three-dimensional map of each tumor, estimating its true volume. They then compared tumor volume with traditional indicators such as tumor grade and prostate-specific antigen levels to predict treatment outcomes.
The researchers found that the novel AI tool was capable of accurately estimating prostate tumor volume and identifying patients with a higher likelihood of responding to treatment. Tumor volume was the strongest predictor of treatment success, whereas tumor grade did not correlate with a successful outcome. The patients with tumors smaller than 1.5 cm experienced better outcomes after cryotherapy and were less likely to require further treatment or develop metastases. Using this tumor volume threshold as an eligibility criterion would have reduced the lack of treatment response by more than 70%.
Conclusions
“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,” highlighted lead study author Wayne Brisbane, MD, Assistant Professor of Urology at the David Geffen School of Medicine at the University of California, Los Angeles (UCLA), and a member of the UCLA Health Jonsson Comprehensive Cancer Center. “The study marks an important advance in integrating AI into prostate cancer treatment decision-making, offering the potential for more personalized prostate cancer care,” he added.
Despite the positive findings, the researchers emphasized the need for larger, multicenter trials to confirm their results.
“With Unfold AI, [physicians] now have a method to determine the volume of cancer within a prostate tumor,” underscored senior study author Leonard Marks, MD, Professor and the deKernion Endowed Chair in Urology at the David Geffen School of Medicine at UCLA and a member of the UCLA Health Jonsson Comprehensive Cancer Center. “Such a method has not been previously available. It’s important because tumor volume is a major determinant of treatment success or failure. Using AI to predict tumor volume and shape gives a clearer picture and could help choose better candidates for focal cryotherapy,” he concluded.
Disclosure: The research in this study was supported by grants from the National Institutes of Health. For full disclosures of the study authors, visit bjui-journals.onlinelibrary.wiley.com.
