AI healthcare firm Avenda Health is touting the results of a study showing how the company's Unfold AI can identify prostate tumor margins and predict the efficacy of focal therapy treatments.
The study was presented at the 2024 American Urological Association’s annual meeting by Wayne Brisbane, MD, from University of California, Los Angeles Health. It demonstrated that Unfold AI, Avenda's AI-powered cancer mapping technology, was a better predictor of focal therapy success than other factors, including the size or grade of the tumor, according to Avenda.
In the study, Unfold AI was retrospectively applied to 118 previously untreated men undergoing hemi-gland cryotherapy for prostate cancer ablation. MRI-guided biopsies, both targeted and systematic, were performed before cryotherapy and six months after cryotherapy to assess treatment outcomes.
The study found that the baseline Gleason Grade Group (GG), which categorizes the aggressiveness of prostate cancer (GG1 indicating low-grade and GG5 high-grade), consisted of 66.8% GG2, 28% GG3, and 5.3% GG4 cases. Treatment success, defined as the absence of >GG2 on post-cryotherapy MRI-guided biopsies, was achieved in 77.7% of cases and was not found to be correlated with baseline GG.
The study also found that Unfold AI’s patient-specific encapsulation confidence score, which is generated based on multiple patient data points, including MRI scans, biopsy results, and Gleason scores among other data, can predict treatment success. These findings show that Unfold AI can aid in treatment decision-making for prostate cancer patients, Avenda said.
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
